The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index; none of the 20 sources its claims cite is checked for support yet.
The need for uncertainty quantification in machine-assisted medical decision making
Open accessOverview
AI snapshot
Written from the paper’s full text.
TL;DR
This perspective argues that machine-assisted medical decision making, especially deep learning, requires a principled and formal discipline of uncertainty quantification (UQ) comparable to that used in nuclear stockpile stewardship and risk management. It maps where uncertainty enters the DL pipeline, identifies four overlapping challenge areas, and sketches research directions for building UQ for DL.
Key findings
- The paper contends that predictions without UQ "are neither predictions nor actionable," and that automated clinical systems not analyzable via known causal connections will require formal UQ to be adopted, as happened in nuclear security.
- It identifies four overlapping challenge groups for UQ of data-driven approaches: (1) absence of theory (no "hard laws" in medicine), (2) absence of causal models (DL exploits correlations without causal links), (3) sensitivity to imperfect data (missing elements and errors with patterned confounds), and (4) computational expense of recomputation for uncertainty bounds.
- It proposes that uncertainty must be quantified across at least four pipeline steps: collection/selection of training data and its coverage of the medical phenomenon, accuracy and completeness of labelling, selection and understanding of the DL model and its performance bounds, and model performance against operational (clinical inference) data.
- It highlights three research directions: quantifying and limiting overfitting (noting classical information criteria fail given DL's parameter counts and capacity to memorize random noise), understanding DL internals, and training DL to provide its own uncertainty estimates—suggesting GANs for detecting out-of-sample cases as "particularly fruitful."
- Cited (not original) performance claims: DL transfer-learning applications reported performance comparable to human experts or better, and DL function estimators reported performance better than state-of-the-art classical predictive models.
Methods
- Design: a conceptual/perspective article (no empirical study, dataset, or experiment conducted by the authors).
- Content: narrative discussion of the role of DL in clinical decision making, the proposed place of UQ, anticipated challenges, and foreseen research directions, illustrated by a figure of uncertainty sources in the DL pipeline.
- Analysis: argumentative synthesis drawing analogies to UQ practice in nuclear security and risk management; no statistical analysis is performed.
Limitations
- Stated by the paper: the domains where DL is applied lack underlying mechanistic theory to ground uncertainties; DL lacks causal models, limiting conclusions; real-world data is imperfect with patterned errors that can confound prediction; and recomputation for uncertainty bounds may currently be prohibitively expensive.
- Evident in the text: the article is a position/perspective piece with no empirical validation, no concrete UQ framework or method proposed, and no quantitative results of its own; the authors explicitly note that "it is possible that the entire new field of UQ for DL might need to be developed" and that a review of ongoing research is beyond its scope.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
29 Own interpretation · 17 No basis given · 10 Not checked yet
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we are ultimately operating without the fundamental, underlying mathematical model which we could otherwise use to ground our uncertainties and to bound any assumptions we make.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4 Anticipated Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Advancements in UQ now provide measures of confidence necessary to inform national or international security decisions.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
What the sources say
- Not checked yetcites [1] Oberkampf, W. L. & Roy, C. J. Verfication and Validation in Scientific Computing (Cambridge Univ. Press, Cambridge, 2010). source
- Not checked yetcites [2] National Research Council Evaluation of Quantification of Margins and Uncertainties: Methodology for Assessing and Certifying the Reliability of the Nuclear Stockpile (National Academies Press, Washington DC, 2009).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The absence of a causal connection, however, means garnering limited conclusions from DL models”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“most partial theories in medicine still explain an extremely small fraction of the observed phenomena and variations 3,4 .”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2 Machine-assisted Clinical Decision Making and Research
What the sources say
- Not checked yetcites [3] Zuk, O., Hechter, E., Sunyaev, S. R. & Lander, E. S. The mystery of missing heritability: Genetic interactions create phantom heritability. Proc. Natl Acad. Sci. USA 109, 1193–1198 (2012). source
- Not checked yetcites [4] Choi, J. D. & Lee, J.-S. Interplay between epigenetics and genetics in cancer. Genomics Inform. 11, 164–173 (2013). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The applications of DL techniques based on transfer learning have reported performance comparable to that of the human experts 5 , , 6 or better 7 ., 8”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2.1 The Current Roles and Applications of AI
What the sources say
- Not checked yetcites [5] Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122–1131 (2018). source
- Not checked yetcites [6] Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017). source
- Not checked yetcites [7] Mar, V. & Soyer, H. Artificial intelligence for melanoma diagnosis: How can we deliver on the promise? Ann. Oncol. 29, 1625–1628 (2018). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“uncertainty in generalization depends on the density of training points in an appropriately defined neighborhood of the prediction target.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.3 Training DL to provide its own uncertainty estimates
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“A particularly fruitful approach seems to be the use of Generative Adversarial Networks (GANs) for detecting out-of-sample cases.[24][25][26]”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.3 Training DL to provide its own uncertainty estimates
What the sources say
- Not checked yetcites [24] Brahma, P. P., Huang, Q. & Wu, D. O. Structured memory based deep model to detect as well as characterize novel inputs. Preprint at http://arxiv.org/abs/1801.09859 (2018).
- Not checked yetcites [25] Yu, Y., Qu, W., Li, N. & Guo, Z. Open-category classification by adversarial sample generation. Preprint at http://arxiv.org/abs/1705.08722 (2017). source
- Not checked yetcites [26] Ge, Z., Demyanov, S., Chen, Z. & Garnavi, R. Generative openmax for multi-class open set classification. Preprint at http://arxiv.org/abs/1707.07418 (2017). source
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“the capacity of DL networks to memorize random noise 18”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.1 Quantifying and limiting overfitting
What the sources say
- Not checked yetcites [18] Zhang, C., Bengio, S., Hardt, M., Recht, B. & Vinyals, O. Understanding deep learning requires rethinking generalization. Preprint at http://arxiv.org/abs/1611.03530 (2016).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 44
- It may state two separate claims as one. 16
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“computing capacity in support of DL is growing exponentially”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“UQ today underpins many decision processes in nuclear security, our risk management and associated investments, which can be at the scale of billions of dollars.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we propose that all of these steps (illustrated in figure 1) would need to be quantified in order to arrive at even crude, overall measures of the uncertainty of the DL-based decision model.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 3 The Role for UQ in DL
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“as DL-structured neural networks are particularly suitable for recognition of visually manifested conditions such as changes in tissue, lesions and growth, etc.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2.1 The Current Roles and Applications of AI
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Real world data is usually imperfect-typically containing missing elements and errors-and these imperfections have patterns that can confound prediction.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“the domains where the DL is usually applied, such as medicine, do not have such”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4 Anticipated Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We see at least four overlapping groups of challenges associated with the uncertainty quantification of the data-driven approaches such as DL:”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4 Anticipated Challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“To achieve this confidence, UQ extends the traditional discipline of statistical error analysis to also capture uncertainties due to possibly incomplete, inaccurate, and contradictory input data, missing and undetected mechanisms and dependencies, expert judgment, and variations between reasonable model forms and modeling strategies.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“use of scientific insights and attempts at a cohesive framework incorporating the major clinical predictors are likely to be increasingly useful as predictive models are able to efficiently summarize more complex correlations in the data.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2 Machine-assisted Clinical Decision Making and Research
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Predictions without UQ are neither predictions nor actionable.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although AI-based research has long played an important role in medicine, it has, nevertheless, been one of the more challenging areas for AI to see an effective adoption.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2 Machine-assisted Clinical Decision Making and Research
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Rests on an assumption: The reluctance to delegate to machine intelligence a function of life-critical and patient-safety-related decision making is a primary reason for the slow adoption of AI in medicine.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In most of the presented cases, the applications of AI are based on the DL neural networks, trained on a very large number of labeled data sets, and their learning tuned with the large number of hyperparameters.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2.1 The Current Roles and Applications of AI
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A need to systematize a similar situation is what actually led us to develop the formal approach to UQ in US national security sciences.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“medical AI, especially in its modern data-rich Deep Learning guise, needs to develop a principled and formal Uncertainty Quantification (UQ) discipline, just as we have seen in fields such as nuclear stockpile stewardship or risk management.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
- Rests on an assumption: The reluctance to delegate to machine intelligence a function of life-critical and patient-safety-related decision making is a primary reason for the slow adoption of AI in medicine.
None of the sources cited for this claim have been checked yet.
In the paper
“A notable example is the US support of a nuclear test moratorium since 1992, whereby we annually provide detailed measures of confidence in the safety, security, and performance of the nuclear stockpile--guaranteed through virtual testing 1,2 .”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
What the sources say
- Not checked yetcites [1] Oberkampf, W. L. & Roy, C. J. Verfication and Validation in Scientific Computing (Cambridge Univ. Press, Cambridge, 2010). source
- Not checked yetcites [2] National Research Council Evaluation of Quantification of Margins and Uncertainties: Methodology for Assessing and Certifying the Reliability of the Nuclear Stockpile (National Academies Press, Washington DC, 2009).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The data-rich world of AI-based learning, and the frequent absence of a well-understood underlying theory poses its own unique challenges to straightforward adoption of UQ.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Obviously, there are many steps in such scenarios where there are uncertainties that would need to be quantified.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 3 The Role for UQ in DL
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“ad hoc solutions, such as sensitivity analysis and study of model variability, have sometimes been employed to mitigate some the problems we outline.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“once a low-dimensional representation is arrived at describing certain correlations (e.g., the difference between cancerous and matched normal cells), it can raise hypotheses that can be tested.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These are then”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2.1 The Current Roles and Applications of AI
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This may not seem like a limitation since prediction does not need causal relation.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Understanding prediction system structure and defensibly quantifying uncertainty is possible, and, if done, can significantly benefit both research and practical applications of AI in this critical domain.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Automated systems adoption, especially systems not analyzable in terms of known causal connections, will require principled and formal UQ to play a transformative role, just as we have seen in the nuclear security domain.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2 Machine-assisted Clinical Decision Making and Research
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
In the paper
“techniques are being developed 17 to approximate some of the UQ-relevant calculations.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
What the sources say
- Not checked yetcites [17] Gal, Y. & Ghahramani, Z. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Preprint at https://arxiv.org/abs/1506.02142 (2015).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But numerical results, without a measure of their veracity do not provide the trust needed to inform decisions.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The training of the DL models is computationally expensive, and any further recomputation and re-evaluation of the models, aimed, for example, at the calculation of uncertainty bounds might currently be prohibitively expensive.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These challenges, while not trivial, also present significant new research opportunities for the development of new theoretical approaches, and for the practical applications of UQ in the area of machine-assisted medical decision making.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“furthermore, it is imperative to understand how the training data must be similar to prediction data.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Specific UQ methods, therefore, need to be developed to quantify the sensitivity of models to imperfect data.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“DL is essentially exploiting correlations in the data, without paying attention to any causal link.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2. Absence of causal models:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“To develop consequential decision-support from”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Unlike statistical approaches where mathematical models are used to explain variations observed in data, and to propose the margin of errors on inferences, with these recent applications, different learning architectures are combined with a large number of DL network parameters to form universal approximators.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 2.1 The Current Roles and Applications of AI
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Data-driven methods are emerging as the foundations of evidence-based decision making, and the future of data-driven scientific discovery.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Some approaches, such as attempts to empirically learn generalizable patterns with insertion of random noise 19,20 , or the use of cross-validation to determine the progression of generalizable learning, move us forward in this problem space, while still carrying the problem of overfitting 21 .”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.1 Quantifying and limiting overfitting
What the sources say
- Not checked yetcites [19] Arpit, D. et al. A closer look at memorization in deep networks. Preprint at https://arxiv.org/abs/1706.05394 (2017).
- Not checked yetcites [20] Zhang, C., Vinyals, O., Munos, R. & Bengio, S. A study on overfitting in deep reinforcement learning. Preprint at http://arxiv.org/abs/1804.06893 (2018).
- Not checked yetcites [21] Cawley, G. C. & Talbot, N. L. C. On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11, 2079–2107 (2010).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The wider application of DL in the biomedical field now requires an extension of these methods to this emerging field.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“an effective way of addressing some of the mentioned UQ problems might be to re-shape the DL engine itself to provide an uncertainty estimate on its predictions.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.3 Training DL to provide its own uncertainty estimates
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Overfitting, or the problem of a model performing well on the training set, but generalizing poorly for unseen datasets, is one of the fundamental problems of all data-centric methods, and therefore DL.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.1 Quantifying and limiting overfitting
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The details of the medical applications and DL networks are, however, significantly different since the theoretical foundations are far less developed and there are deep psychological and sociological implications in delegating to machines decisions that affect the life or health of human beings.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“progress in understanding the structure of these predictive systems, merging model and data driven approaches with strongly defensible UQ, and the formalization of the UQ for DL discipline will be needed to make DL and other data-centric tools and methods practically useful.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These have been studied in other scientific disciplines and decision-making arena, and we can learn from those.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“UQ for DL will likely not be simply a set of tools or procedures to apply, but a more complex wrap-up of disparate methods that in total help bound the overall confidence in predictions.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In high-dimensional problems, typical to the medical setting (images, large numbers of phenotypes, etc.), every point, however, can be isolated in some other dimension, and a density of points makes sense only after irrelevant dimensions, are projected out”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.3 Training DL to provide its own uncertainty estimates
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“With DL, and the large number of model parameters involved as well as the capacity of DL networks to memorize random noise 18 , classical approaches do not work.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.1 Quantifying and limiting overfitting
What the sources say
- Not checked yetcites [18] Zhang, C., Bengio, S., Hardt, M., Recht, B. & Vinyals, O. Understanding deep learning requires rethinking generalization. Preprint at http://arxiv.org/abs/1611.03530 (2016).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Advances in understanding of how DL works internally will allow for a more effective UQ of interpreting DL.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.2 Understanding DL
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“there is a unifying structure to this problem in its various guises of complex predictive correlations in large data sets and engineering black boxes.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 6 Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“there are ongoing studies that attempt to understand what DL does, 22 and how it learns 23”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.2 Understanding DL
What the sources say
- Not checked yetcites [22] Brahma, P. P., Wu, D. & She, Y. Why deep learning works: A manifold disentanglement perspective. IEEE Trans. Neural Netw. Learn. Sys. 27, 1997–2008 (2016). source
- Not checked yetcites [23] Raghu, M., Gilmer, J., Yosinski, J. & Sohl-Dickstein, J. SVCCA: Singular vector canonical correlation analysis for deep learning dynamics and interpretability. Preprint at https://arxiv.org/abs/1706.05806 (2017).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the network itself can be used to study this uncertainty empirically and provide the uncertainty bounds.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 5.3 Training DL to provide its own uncertainty estimates
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the end, it is possible that the entire new field of UQ for DL might need to be developed.”
§ The Need for Uncertainty Quantification in Machine-assisted Medical Decision Making > 4. Computational Expense:
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper relies on this without support.
The reluctance to delegate to machine intelligence a function of life-critical and patient-safety-related decision making is a primary reason for the slow adoption of AI in medicine.
“There are many reasons for this, primarily the reluctance to delegate to machine intelligence a function of life-critical and patient-safety-related decision making.”
The authors state this as an assumption.
Fair sampling in the training data holds.
“assuming fair sampling in the training data”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Better decision-making: AI, ML, and DL can enable robots to make better decisions based on data analysis and pattern recognition, leading to improved performance and outcomes [52] .”
From Artificial intelligence, machine learning and deep learning in advanced robotics, a review (2023) · cites this paper as [52]
Experimental — accuracy not yet measuredIn the citing paper
“However, these models have black-box nature and lack underlying theoretical foundation behind their decisions [8]”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [8]
In the citing paper
“However, due to the unavailability of sound fundamental laws and models, the explanation of DL cannot be produced up-to the required scale.”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [8]
Citations
Cites
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018) · Cell · doi:10.1016/j.cell.2018.02.010 · Cited by 4,842
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838
Scalable and accurate deep learning with electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0029-1 · Cited by 2,648 · cited 1×
“…DL methods have been used in the predictive scenarios related to quality of care, and clinical outcomes where large neural networks were used as function estimators in place of classical predictive models, with reported performance better than the state-of-the-art, classical model approaches 9–11 .”
MethodScalable and accurate deep learning with electronic health records.
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · eScholarship (California Digital Library) · Cited by 2,242
(2010) · doi:10.5555/1756006.1859921 · Cited by 1,924
Verification and Validation in Scientific Computing
Oberkampf, W. L., & Roy, C. J. (2010) · doi:10.1017/cbo9780511760396 · Cited by 1,556
The mystery of missing heritability: Genetic interactions create phantom heritability
Zuk, O., Hechter, E., Sunyaev, S. R., & Lander, E. S. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1119675109 · Cited by 1,542
Can machine-learning improve cardiovascular risk prediction using routine clinical data?
Weng, S. F., Reps, J., Kai, J., Garibaldi, J. M., & Qureshi, N. (2017) · PLOS ONE · doi:10.1371/journal.pone.0174944 · Cited by 1,346
Cited by
Sorted by citations
Items 101–200 of 583
Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model
Shen, M., Bu, Y., Sattigeri, P., Ghosh, S. K., Das, S., & Wornell, G. W. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26167 · Cited by 30
Mervin, L., Trapotsi, M., Afzal, A. M., Barrett, I. P., Bender, A., & Engkvist, O. (2021) · Journal of Cheminformatics · doi:10.1186/s13321-021-00539-7 · Cited by 33
Uncertainty quantification and attention-aware fusion guided multi-modal MR brain tumor segmentation
Zhou, T., & Zhu, S. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107142 · Cited by 33
Incorporating Artificial Intelligence into Healthcare Workflows: Models and Insights
Dai, T., & Abràmoff, M. D. (2023) · Tutorials in Operations Research: Advancing the Frontiers of OR/MS: From Methodologies to Applications · doi:10.1287/educ.2023.0257 · Cited by 29
A data science roadmap for open science organizations engaged in early-stage drug discovery
Edfeldt, K., Edwards, A. M., Engkvist, O., Günther, J., Hartley, M., Hulcoop, D. G., Leach, A. R., Marsden, B. D., Menge, A., Misquitta, L., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-49777-x · Cited by 33
PRIME 2.0: Proposed Requirements for Cardiovascular Imaging-Related Multimodal-AI Evaluation
Kagiyama, N., Tokodi, M., Hathaway, Q. A., Arnaout, R., Davies, R. H., Dey, D., Duchateau, N., Fraser, A. G., Goto, S., Jamthikar, A. D., et al. (2025) · JACC. Cardiovascular imaging · doi:10.1016/j.jcmg.2025.08.004 · Cited by 36
Lu, C., Angelopoulos, A. N., & Pomerantz, S. R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16452-1_52 · Cited by 29
A review on AI Safety in highly automated driving
Wäschle, M., Thaler, F., Berres, A., Pölzlbauer, F., & Albers, A. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.952773 · Cited by 28
“As summarized in Berlinic (2019), AI Safety may conclude that AI is beneficial or detrimental.”
BackgroundVerhelst, H. M., Stannat, A., & Mecacci, G. (2020) · Science and Engineering Ethics · doi:10.1007/s11948-020-00254-w · Cited by 30
“While the judgment of the accuracy of a machine learning algorithm on the labelled training set is possible, its performance in ‘the real world’ cannot be estimated a priori (Begoli et al. 2019; Dunson 2018).”
BackgroundPrognosticating the outcome of intensive care in older patients—a narrative review
Beil, M., Moreno, R. P., Fronczek, J., Kogan, Y., Moreno, R. P., Flaatten, H. K., Guidet, B., de Lange, D. W., Leaver, S. K., Nachshon, A., et al. (2024) · Annals of Intensive Care · doi:10.1186/s13613-024-01330-1 · Cited by 29
“Reflections about prognostic uncertainty should go beyond a simple acknowledgement [9] and extend to quantification [85, 95].”
BackgroundRamadevi, P., & Das, R. (2024) · IEEE Access · doi:10.1109/access.2024.3422449 · Cited by 32
“Despite the promising results of AI research in several domains, the implementation of AI in the medical business remains challenging [2].”
BackgroundNanayakkara, T., Clermont, G., LANGMEAD, C. J., & Swigon, D. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000012 · Cited by 31
“Reinforcement Learning in Medicine Reinforcement Learning has been used for various healthcare applications.”
BackgroundBeil, M., van Heerden, P. V., de Lange, D. W., Szczeklik, W., Leaver, S. K., Guidet, B., Flaatten, H. K., Jung, C., Sviri, S., & Leo Joskowicz, B. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02094-z · Cited by 27
“In general, quantification of information and uncertainty improves the transparency of decisionmaking processes and supports standardisation of decisions [25, 26].”
BackgroundInterpretable AI in Healthcare: Enhancing Fairness, Safety, and Trust
MacDonald, S., Steven, K., & Trzaskowski, M. (2022) · Springer eBooks · doi:10.1007/978-981-19-1223-8_11 · Cited by 25
Chen, C., Wang, C., Guo, J., Cui, P., Zheng, J., & Liu, Z. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111431 · Cited by 25
Timing errors and temporal uncertainty in clinical databases—A narrative review
Goodwin, A. J., Eytan, D., Dixon, W., Goodfellow, S. D., Doherty, Z. B., Greer, R. W., McEwan, A. L., Tracy, M. B., Laussen, P. C., Assadi, A., et al. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2022.932599 · Cited by 29
Huang, Y., Padarian, J., Minasny, B., & McBratney, A. B. (2025) · SOIL · doi:10.5194/soil-11-553-2025 · Cited by 23
Beyond K-complex binary scoring during sleep: probabilistic classification using deep learning
Lechat, B., Hansen, K. L., CATCHESIDE, P. G., & Zajamšek, B. (2020) · SLEEP · doi:10.1093/sleep/zsaa077 · Cited by 23
“Probabilistic scoring, through Bayesian statistics [20], can quantify uncertainties re-lated to the training data selection and labeling accuracy [21].”
BackgroundConformal prediction for uncertainty quantification in dynamic biological systems
Portela, A., Banga, J., & Matabuena, M. (2025) · PLoS Comput. Biol. · doi:10.1371/journal.pcbi.1013098 · Cited by 22
“It helps in understanding the underlying uncertainties in the model parameters and predictions, thereby improving the model’s predictive power and its utility in decision-making processes [26,27].”
An active learning method for diabetic retinopathy classification with uncertainty quantification
Ahsan, M. A., Qayyum, A., Razi, A., & Qadir, J. (2022) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-022-02633-w · Cited by 22
“[5] described three such challenges that include; (i) lack”
BackgroundBai, Y., Mei, S., Wang, H., & Xiong, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.07856 · Cited by 22
“As the confidence is often comprehended as an estimate of the true accuracy, such over-confidence could be dangerous, especially in risk-sensitive domains such as medical AI (Begoli et al., 2019), self-driving cars (Michelmore et al., 2018), and so on.”
BackgroundSalvi, M., Acharya, M. R., Seoni, S., Faust, O., Tan, R., Barua, P. D., García, S., Molinari, F., & Acharya, U. R. (2024) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1530 · Cited by 26
“(cid:129) Uncertainty quantification : Assessing prediction uncertainty is an emerging priority in AI (Begoli et al., 2019).”
BackgroundSynthesizability of materials stoichiometry using semi-supervised learning
Jang, J., Noh, J., Zhou, L., Gu, G. H., Gregoire, J. M., & Jung, Y. (2024) · Matter · doi:10.1016/j.matt.2024.05.002 · Cited by 21
Frank, D., Chrysochou, P., Mitkidis, P., Otterbring, T., & Dan Ariely, C. (2024) · Technology in Society · doi:10.1016/j.techsoc.2024.102732 · Cited by 23
Haraz, A., Abualsaud, K., & Massoud, A. M. (2025) · IEEE Access · doi:10.1109/access.2025.3539792 · Cited by 21
“…the completeness and accuracy of the training data, (iii) a comprehensive understanding of the deep learning (or traditional ML) model, including its performance boundaries and limitations, and (iv) uncertainties related to the model’s performance when applied to real-world operational data [16].”
Reliability engineering, risk management, and trustworthiness assurance for AI systems
Zhang, X., Wang, T., Ma, L., & Mahadevan, S. (2025) · Journal of Reliability Science and Engineering · doi:10.1088/3050-2454/adcef2 · Cited by 29
Chen, W., Li, C., Chen, D., & Luo, X. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.09.001 · Cited by 22
Modeling unknowns: A vision for uncertainty-aware machine learning in healthcare
Campagner, A., Biganzoli, E. M., Balsano, C., Cereda, C., & Cabitza, F. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.106014 · Cited by 25
Uncertainty Quantification and Estimation in Medical Image Classification
Yang, S., & Fevens, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86365-4_54 · Cited by 20
A New Fuzzy-Based Classification Method for Use in Smart/Precision Medicine
Zaitseva, E., Levashenko, V., Rabčan, J., & Kvaššay, M. (2023) · Bioengineering · doi:10.3390/bioengineering10070838 · Cited by 22
“In many cases, the ambiguity and vagueness of medical data can be caused by experts’ knowledge, which is typical in healthcare [53,56].”
BackgroundLiu, Q., Chen, X., & Tang, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122279 · Cited by 20
Zhou, X., Tang, T., He, Q., Zhao, L., Kuang, G., & Liu, L. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.07.014 · Cited by 19
Huynh, T.-M.-T., Ni, C., Su, Y.-S., Ngân, N. V. C., Lee, I.-H., Lin, C.-P., & Hiep, N. H. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph191912180 · Cited by 21
“Modelers need more evidence beyond accuracy to convince the general public or managers to trust predicted values [11].”
BackgroundCoscrato, V., & Bridge, D. (2023) · ACM Transactions on Recommender Systems · doi:10.1145/3584021 · Cited by 19
An Uncertainty-Aware Deep Learning Model for Reliable Detection of Steel Wire Rope Defects
Yi, W., Chan, W. K., Lee, H. H., Boles, S. T., & Zhang, X. (2023) · IEEE Transactions on Reliability · doi:10.1109/tr.2023.3335958 · Cited by 19
Sources of Uncertainty in Supervised Machine Learning—a Statisticians’ View
Gruber, C., Schenk, P. O., Schierholz, M., Kreuter, F., & Kauermann, G. (2026) · Statistical Science · doi:10.1214/25-sts1003 · Cited by 85
Bousoulas, P., Tsioustas, C., Hadfield, J., Aslanidis, V., Limberopoulos, S., & Tsoukalas, D. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3160140 · Cited by 19
Uncertainty quantification in medical image synthesis
Barbano, R., Arridge, S., Jin, B., & Tanno, R. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824349-7.00033-5 · Cited by 18
Space Applications of a Trusted AI Framework: Experiences and Lessons Learned
Mandrake, L., Doran, G. B., Goel, A., Ono, H., Amini, R., Feather, M. S., Fesq, L. M., Slingerland, P. C., Perry, L., Bycroft, B. P., et al. (2022) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero53065.2022.9843322 · Cited by 18
Mehrtens, H. A., Kurz, A., Bucher, T.-C., & Brinker, T. J. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102914 · Cited by 27
“One commonly given reason [Begoli et al., 2019, Kompa et al., 2021, van der Laak et al., 2021] is their inability to provide well-calibrated estimates of their predictive uncertainty [Guo et al., 2017], thereby prohibiting the practitioner from judging the reliability of the system’s decision,…”
BackgroundThe Bionic Radiologist: avoiding blurry pictures and providing greater insights
Dewey, M., & Wilkens, U. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0142-9 · Cited by 19
Clairvoyance: A Pipeline Toolkit for Medical Time SeriesPreprint
Jarrett, D. P., Yoon, J., Bica, I., Qian, Z., Ercole, A., & van der Schaar, M. (2021) · arXiv (Cornell University) · doi:10.17863/cam.70020 · Cited by 21
EvidenceCap: Towards trustworthy medical image segmentation via evidential identity capPreprint
Zou, K., Yuan, X., Shen, X., Chen, Y., Wang, M., Goh, R. S. M., Liu, Y., & Fu, H. (2023) · Research Square · doi:10.21203/rs.3.rs-2558155/v1 · Cited by 18
A Bayesian deep recommender system for uncertainty-aware online physician recommendation
Cui, F., Yu, S., Chai, Y., Qian, Y., Jiang, Y., Liu, Y., Liu, X., & Li, J. (2024) · Information & Management · doi:10.1016/j.im.2024.104027 · Cited by 17
Transforming memristor noises into computational innovations
Ding, C., Ren, Y., Liu, Z., & Wong, N. (2025) · Communications Materials · doi:10.1038/s43246-025-00876-2 · Cited by 23
Joshi, P., & Dhar, R. (2022) · Scientific Reports · doi:10.1038/s41598-022-18874-6 · Cited by 20
“Here a measure of confidence or uncertainty with each prediction is important to ascertain the reliability of class predictions and can greatly benefit clinical decision-making 35 .”
BackgroundA general framework for quantifying uncertainty at scale
Farcaș, I.-G., Merlo, G., & Jenko, F. (2022) · Communications Engineering · doi:10.1038/s44172-022-00045-0 · Cited by 17
“(17), (20) and (21) on a fixed grid in five-dimensional phase space using a mix of spectral, finite difference, and finite volume methods.”
MethodUncertainty, Evidence, and the Integration of Machine Learning into Medical Practice
Grote, T., & Berens, P. (2023) · The Journal of Medicine and Philosophy A Forum for Bioethics and Philosophy of Medicine · doi:10.1093/jmp/jhac034 · Cited by 18
Frequentist uncertainty estimates for deep learning.Preprint
Tagasovska, N., & López-Paz, D. (2018) · arXiv (Cornell University) · Cited by 17
Machine Learning for Clinical Decision-Making: Challenges and OpportunitiesPreprint
Sanchez‐Martinez, S., Cámara, Ó., Piella, G., Čikeš, M., Ballester, M. Á. G., Miron, M., Vellido, A., Gómez, E., Fraser, A. G., & Bijnens, B. H. (2019) · Preprints.org · doi:10.20944/preprints201911.0278.v1 · Cited by 17
Towards Trustworthy AI in Healthcare: Epistemic Uncertainty Estimation for Clinical Decision Support
Lindenmeyer, A., Blattmann, M., Franke, S., Neumuth, T., & Schneider, D. (2025) · Journal of Personalized Medicine · doi:10.3390/jpm15020058 · Cited by 17
“In the healthcare domain, where decisions are safety-critical and ethically relevant, it is imperative that such automated methods employed in clinical decision support systems (CDSSs) are not only effective but also trustworthy [6–8, 10, 11].”
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511112 · Cited by 19
“…with low confidence scores [23], it is important to further investigate an approach to estimate the confidence score of a model and determine if the prediction of a model can be utilized it to better identify samples with low confidence scores and build a trustful interaction with the user [7, 23].”
BackgroundESVM‐SWRF : Ensemble SVM ‐based sample weighted random forests for liver disease classification
Padmakala, S., Subasini, C. A., Karuppiah, S. P., & Sheeba, A. (2021) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.3525 · Cited by 16
U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging
Heremans, E. R. M., Seedat, N., Buyse, B., Testelmans, D., van der Schaar, M., & Vos, M. D. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108205 · Cited by 16
Shallow Learning vs. Deep Learning in Engineering Applications
Jafari, F., Moradi, K., & Shafiee, Q. (2024) · The Springer series in applied machine learning · doi:10.1007/978-3-031-69499-8_2 · Cited by 18
Kalman Bayesian Neural Networks for Closed-Form Online Learning
Wagner, P., Wu, X., & Huber, M. F. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26200 · Cited by 19
Clinicians must participate in the development of multimodal AI
Banerji, C. R. S., Shah, A. B., Dabson, B., Chakraborti, T., Hellon, V., Harbron, C. G., & MacArthur, B. D. (2025) · EClinicalMedicine · doi:10.1016/j.eclinm.2025.103252 · Cited by 19
Li, S., Yuan, M., Dai, X., & Zhang, C. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102574 · Cited by 16
Bentegeac, R., Guellec, B. L., Kuchcinski, G., Amouyel, P., & Hamroun, A. (2025) · Journal of Medical Internet Research · doi:10.2196/64348 · Cited by 24
“Therefore, their use in high-stakes settings such as answering to patients’ inquiries requires a careful evaluation of both their knowledge and their ability to clearly express uncertainty [14,15].”
Deep generative classification of blood cell morphology
Deltadahl, S., Gilbey, J., Laer, C. V., Boeckx, N., Leers, M. P. G., Freeman, T., Aiken, L., Farren, T., Smith, M., Zeina, M., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01122-7 · Cited by 23
“Finally, the model should be able to quantify the uncertainty attached to its decision, a feature often neglected in model assessments [11].”
Pharmaceutical Supply Chains and Drug Shortages
Zhao, H. (2023) · doi:10.1287/educ.2023.0258 · Cited by 15
Borgonovo, E. (2023) · doi:10.1287/educ.2023.0259 · Cited by 15
Building robust pathology image analyses with uncertainty quantification
Gomes, J., Kong, J., Kurç, T., de Melo, A. C. M. A., Ferreira, R. C., Saltz, J. H., & Teodoro, G. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106291 · Cited by 16
Pepe, A., Egger, J., Codari, M., Willemink, M. J., Gsaxner, C., Li, J., Roth, P. M., Schmalstieg, D., Mistelbauer, G., & Fleischmann, D. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107365 · Cited by 14
A modified GNN architecture with enhanced aggregator and Message Passing Functions
Sarkar, D., Roy, S., Malakar, S., & Sarkar, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106077 · Cited by 14
Prince, E. W., Ghosh, D., Görg, C., & Hankinson, T. C. (2023) · Diagnostics · doi:10.3390/diagnostics13061132 · Cited by 15
“It is critical to know the predictive uncertainty of a DL model in a high-risk scenario, such as neuro-oncology, because errors can have devastating effects [19].”
BackgroundLiu, X.-F., Prince, J. L., Xing, F.-X., Zhuo, J., Reese, T., Stone, M., Fakhri, G. E., & Woo, J. (2023) · Medical Image Anal. · doi:10.1016/j.media.2023.102851 · Cited by 15
“Quantifying model uncertainty is crucial in medical image analysis (Begoli et al., 2019).”
Optimized Bayesian convolutional neural networks for invasive breast cancer diagnosis system
Ezzat, D., & Hassanien, A. E. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110810 · Cited by 13
Vicario, C. M., Rodríguez-Salas, D., Maier, A., Hock, S. W., Kuramatsu, J. B., Kallmuenzer, B., Thamm, F., Taubmann, O., Ditt, H., Schwab, S., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-55761-8 · Cited by 16
“Additionally, the reluctance to entrust machines with life-critical decisions, potentially leading to severe consequences, poses another barrier 12 .”
Lester, C. A., Rowell, B. E., Zheng, Y., Co, Z., Marshall, V. D., Kim, J. Y., Chen, Q., Kontar, R. A., & Yang, X. J. (2025) · JMIR Medical Informatics · doi:10.2196/64902 · Cited by 13
“Uncertainty-aware AI models present the model’s uncertainty, or confidence in its decision, alongside its prediction [11], thus providing a metric for the user to assess the AI’s reliability [12].”
Robust crop disease detection using multi-domain data augmentation and isolated test-time adaptation
Fu, R., Jiao, H., Sun, Y., Wang, S., Al-Absi, M. A., Wang, X., & Sun, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127324 · Cited by 13
Fast Predictive Uncertainty for Classification with Bayesian Deep NetworksPreprint
Hobbhahn, M., Kristiadi, A., & Hennig, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01227 · Cited by 13
“Quantifying the uncertainty of Neural Networks’ (NNs) predictions is important in safety-critical applications such as medical-diagnosis [Begoli et al., 2019] and self-driving vehicles [McAllister et al., 2017, Michelmore et al., 2018], but it is often limited by computational constraints.”
BackgroundSimulation Optimization in the New Era of AI
Peng, Y., Chen, C., & Fu, M. C. (2023) · doi:10.1287/educ.2023.0264 · Cited by 12
Vo, K., El‐Khamy, M., & Choi, Y. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781630 · Cited by 12
“This would make the model more trustworthy and give patients and clinicians greater confidence in using it for medical diagnosis [30].”
Transformer Models improve the acoustic recognition of buzz-pollinating bee species
Ferreira, A. I. S., da Silva, N. F. F., Mesquita, F. N., Rosa, T. C., Buchmann, S. L., & Neto, J. N. M. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103010 · Cited by 14
Kelly, A., Jensen, E. S., Grua, E. M., Mathiasen, K., & van de Ven, P. W. J. (2025) · JMIR Medical Informatics · doi:10.2196/64617 · Cited by 10
“Issues of confidence and robustness that are important for ML models aimed at medical DSSs [25] have been addressed.”
Breaking CAPTCHA with Capsule Networks
Mocanu, I. G., Yang, Z., & Belle, V. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.06.041 · Cited by 12
Bayesian neuroevolution using distributed swarm optimization and tempered MCMC
Kapoor, A., Nukala, E., & Chandra, R. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109528 · Cited by 12
Setting the Right Expectations: Algorithmic Recourse Over Time
Fonseca, J., Bell, A. S., Abrate, C., Bonchi, F., & Stoyanovich, J. (2023) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3617694.3623251 · Cited by 12
“Artificial intelligence (AI) systems are becoming increasingly common in consequential decision-making settings such as health-care [3, 9], finance [19], and hiring [14, 25, 29].”
BackgroundImproving Conditional Coverage via Orthogonal Quantile RegressionPreprint
Feldman, S., Bates, S., & Romano, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.00394 · Cited by 12
Reliable machine learning models in genomic medicine using conformal prediction
Papangelou, C., Kyriakidis, K., Natsiavas, P., Chouvarda, I., & Malousi, A. (2025) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2025.1507448 · Cited by 12
Exploring trust factors in AI-healthcare integration: a rapid review
Mertz, M., Toskovich, K., Shields, G., Attema, G., Dumond, J., & Cameron, E. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1658510 · Cited by 14
Nguyen, T. X., Jiang, M., Yang, D., Ran, A. R., Tang, Z., Zhang, S., Hu, X., Tran, V. T., Dai, T. B. L., Le, D. T., et al. (2024) · NEJM AI · doi:10.1056/aioa2400091 · Cited by 11
Meta transfer evidence deep learning for trustworthy few-shot classification
Liu, T., Wen, C., Xiong, Q., & Li, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125371 · Cited by 11
Using system dynamics to support a functional exercise for pandemic preparedness and response
Green, C., Beishuizen, B. H. H., Stein, M. L., Bleeker‐Rovers, C. P., Tostmann, A., de Jong, D. L. K., Houareau, C., Perseke, K., Spieker, C., Grote, U., et al. (2024) · System Dynamics Review · doi:10.1002/sdr.1786 · Cited by 12
User Trust in Assisted Decision-Making Using Miniaturized Near-Infrared Spectroscopy
Jiang, W., Sarsenbayeva, Z., van Berkel, N., Wang, C., Yu, D., Wei, J., Gonçalves, J., & Kostakos, V. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445710 · Cited by 11
“This factor may be amplified in high-stakes decision-making scenarios, such as healthcare [6] and commercial decisions [7].”
BackgroundMethodInfluentialSalybekov, A. A., Wolfien, M., Kobayashi, S., Steinhoff, G., & Asahara, T. (2021) · Cells · doi:10.3390/cells10123266 · Cited by 10
“This is due to the lack of trust in unfamiliar interfaces and hesitancy to rely on a machine or mathematical algorithm for making critical life decisions [100,101].”
BackgroundChagas, P., Souza, L., Pontes, I., Calumby, R. T., Ângelo, M. F., Duarte, A. A., dos‐Santos, W. L. C., & de Oliveira, L. R. (2022) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2022.2029573 · Cited by 11
“Begoli et al. (2019) emphasise the need to estimate a reliable uncertainty score for medical imaging applications, stating that a proper uncertainty score can help in both research and real-life problems in the medical field.”
BackgroundPeeters, D., Alves, N., Venkadesh, K. V., Dinnessen, R., Saghir, Z., Scholten, E. T., Schaefer‐Prokop, C. M., Vliegenthart, R., Prokop, M., & Jacobs, C. (2024) · European Radiology · doi:10.1007/s00330-024-10714-7 · Cited by 10
“Estimating uncertainty is crucial to identify situations where the algorithm harbors doubt about its predictions and helps identify cases prone to potential DL interpretation errors [8].”
Reducing overconfident errors in molecular property classification using Posterior Network
Fan, Z., Yu, J., Zhang, X., Chen, Y., Sun, S., Zhang, Y., Chen, M., Xiao, F., Wu, W., Li, X., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.100991 · Cited by 11
Phillips, V. J. (2025) · AI & Society · doi:10.1007/s00146-025-02337-3 · Cited by 11
“However, these immediate challenges must be balanced against emerging evidence of benefits documented by Begoli et al. (2019), Davenport and Kalakota (2019), and Sayres et al. (2019), who demonstrate that well-implemented explainable systems can enhance diagnostic accuracy, appropriate trust, and…”
Hernández, S., & López-Cortés, X. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08219-3 · Cited by 10
“There are several reasons for this reluctance, therefore, giving an artificial intelligence technique the power to take life-critical decision is still challenging [5].”
BackgroundTowards an autonomous clinical decision support system
Gershov, S., Raz, A., Karpas, E., & Laufer, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107215 · Cited by 10
Does the world need to change its vaccine distribution strategy for COVID-19?
Sharma, R., Jain, G., & Paul, J. (2023) · Technovation · doi:10.1016/j.technovation.2023.102819 · Cited by 9
Ahmad, T. M., Guida, A., Stewart, S. A., Barrett, N., Jiang, X. W., Vincer, M., & Afifi, J. K. (2024) · European Radiology · doi:10.1007/s00330-024-11028-4 · Cited by 10
Vogt, E. V., Gordon, A. C., Diaz‐Ordaz, K., & Cro, S. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02489-2 · Cited by 10
“Understanding how uncertain subgroup effects are is paramount for these methods to contribute fully to the world of personalised medicine [39].”
Joo, B. (2025) · Neurointervention · doi:10.5469/neuroint.2025.00283 · Cited by 12
“53,54 In addition, reporting inter-and intrarater variability of features annotated for the reference standard may be considered to address this issue, as recommended in the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guideline.”
A Review of Methods for Assessing the Quality of Measurement Systems and Results
Razumić, A., Runje, B., Alar, V., Štrbac, B., & Trzun, Z. (2025) · Applied Sciences · doi:10.3390/app15179393 · Cited by 9
Investigating How Clinicians Form Trust in an AI-Based Mental Health Model: Qualitative Case Study
Kelly, A., Bhardwaj, N., Holmberg, T. T., van de Ven, P. W. J., Melia, R., Williams, J. E., Mathiasen, K., & Nielsen, A. S. (2025) · JMIR Human Factors · doi:10.2196/79658 · Cited by 12
“Although confidence and uncertainty estimation are considered essential for safe clinical deployment of AI [12], most machine learning methods in the recent medical literature are said to neglect the important issue of model uncertainty [10].”
Wang, D., Wu, Z., Shen, C., Bao, L., Luo, H., Wang, Z., Yao, H., De, K., Luo, C., & Hou, T. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac592 · Cited by 9
Metadata
- Authors
- Begoli, E., Bhattacharya, T., & Kusnezov, D.
- Affiliations
- Oak Ridge National Laboratory (US)
- United States Department of Energy (US)
- Corresponding author
- Begoli, Edmon
- ORCID
- Begoli, Edmon
- Venue
- Nature Machine Intelligence
- Published
- 2019-01-07
- Volume
- 1
- Issue
- 1
- Pages
- 20-23
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W2904422658
- Semantic Scholar
- a73eef4e0ec8e49be1c0e6abb04cc1967a681c50
- Cited by
- 597
- References
- 22
- Citations by year
- 2026: 158 · 2025: 102 · 2024: 73 · 2023: 94 · 2022: 72 · 2021: 47 · 2020: 33 · 2019: 16
- FWCI
- 6.47
- Type
- journal article
- Language
- en
- Open access
- green
- www.osti.gov
- Licence
- Locations
- Nature Machine Intelligence (publishedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- Funders
- Battelle (DE-AC05- 00OR22725, DE-AC05)
- UT-Battelle (DE-AC05, DEAC05-00OR22725, AC05-00OR22725)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- uncertainty quantification, artificial intelligence in healthcare, deep learning, patient safety, trust in AI, forecast uncertainty
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
