The DOI matches its Crossref record; 75 of the 82 references it cites were found in a registry or an index; 23 of the 80 sources its claims cite were checked for support.
Artificial Intelligence and Surgical Decision-making.
Open accessAbstract
Review of AI as an augmentation to complex, high-stakes surgical decision-making, emphasizing interpretability, careful implementation, ethical challenges, accountability, and preservation of human intuition and bedside assessment.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
24 Own interpretation · 18 No full text of the sources · 13 Partly supported · 4 Couldn’t confirm · 4 Sources not found · 3 Supported · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Traditional clinical decision support tools, such as the National Surgical Quality Improvement Program (NSQIP) Surgical Risk Calculator, can reduce variability and mitigate risks, but their clinical adoption is hindered by suboptimal accuracy and time-consuming manual data acquisition and entry requirements.3–8”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
What the sources say
- Not checked — no full text of the sourcecites [3] source
- Not checked — no full text of the sourcecites [4] source
- Not checked — no full text of the sourcecites [5] source
- Not checked — no full text of the sourcecites [6] source
- Not checked — no full text of the sourcecites [7] source
- Partly supportedcites [8] sourceExperimental — accuracy not yet measured
The Introduction (page unavailable) says the NSQIP Risk Calculator produces more consistent assessments of surgical complications, supporting the variability claim. It says enhanced use may improve care through risk profiling and targeted interventions, but does not establish that the calculator mitigates surgical risks. (LLM, conf=0.83)
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.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Parametric regression prognostic scoring systems assume that relationships among input variables are linear.22,29”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not checked — no full text of the sourcecites [22] source
- Could not verifycites [29] sourceExperimental — accuracy not yet measured
The Methods section identifies APACHE III as a logistic-regression-based prediction model, and the Results compare it with machine-learning models. Neither section states that parametric prognostic models assume linear relationships among input variables; searches for linearity, nonlinearity, and model assumptions found no passage addressing that point. (LLM, conf=0.72)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Even the most successful and widely used static variable cutoff values do not accurately represent individual patient pathophysiology, as reflected by their suboptimal accuracy.34,43,56”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Partly supportedcites [34] sourceExperimental — accuracy not yet measured
The Introduction describes the Strate rule as a robust model for severe acute lower intestinal bleeding, and the Results report that it was less accurate than a neural network (AUC 0.656 versus 0.979). The paper does not establish that static cutoffs generally fail to represent individual patient pathophysiology; its comparison is limited to this prediction rule and patient population. Page numbers were not available in our copy. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [43] source
- Not checked — no full text of the sourcecites [56] source
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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“When applied to the same variable set used to calculate SOFA scores, deep models outperform traditional SOFA modeling in predicting in-hospital mortality for ICU patients.42”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Supportedcites [42] source
The Methods (Data Processing) state that the deep-learning models were limited to SOFA input variables to permit direct comparison. The Results (External validation of DeepSOFA model) report that DeepSOFA significantly outperformed traditional SOFA models in predicting in-hospital mortality in ICU cohorts. (LLM, conf=0.94)
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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Traditional clinical decision support tools, such as the National Surgical Quality Improvement Program (NSQIP) Surgical Risk Calculator, can reduce variability and mitigate risks, but their clinical adoption is hindered by suboptimal accuracy and time-consuming manual data acquisition and entry requirements.3–8”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
What the sources say
- Not checked — no full text of the sourcecites [3] source
- Not checked — no full text of the sourcecites [4] source
- Not checked — no full text of the sourcecites [5] source
- Not checked — no full text of the sourcecites [6] source
- Not checked — no full text of the sourcecites [7] source
- Partly supportedcites [8] sourceExperimental — accuracy not yet measured
The Results (Table 2) identify slow, cumbersome information entry as a barrier to using surgical risk calculators, and the Discussion identifies poor integration with electronic records and workflows. The paper does not specifically establish time-consuming manual data acquisition as a separate barrier. (LLM, conf=0.83)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“When the relationships are nonlinear, the scoring system is similar to a coin toss.11”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Partly supportedcites [11] sourceExperimental — accuracy not yet measured
The Discussion describes the evaluated scores as regression-based, and the Performance of mortality prediction models in the entire dataset section reports poor discrimination in colorectal surgery, with several AUCs near 0.5. But the paper does not examine nonlinear relationships among input variables or attribute the scores’ performance to them; its finding is also limited to the surgical patients studied. Page numbers were not provided in our copy. (LLM, conf=0.84)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Machine learning has been used to accurately predict sepsis, in-hospital mortality, and acute kidney injury using intraoperative time-series data.9,21,27,32”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Partly supportedcites [9] sourceExperimental — accuracy not yet measured
The Abstract Methods and Conclusions describe a machine-learning model that uses intraoperative physiological time-series data to improve prediction of postoperative acute kidney injury. The paper does not report using that model to predict sepsis or in-hospital mortality; its Results list sepsis as an observed outcome, not a prediction target. (LLM, conf=0.88)
- Not checked — no full text of the sourcecites [21] source
- Not checked — no full text of the sourcecites [27] source
- Not checked — no full text of the sourcecites [32] source
plaincorrelational- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Traditional clinical decision support tools, such as the National Surgical Quality Improvement Program (NSQIP) Surgical Risk Calculator, can reduce variability and mitigate risks, but their clinical adoption is hindered by suboptimal accuracy and time-consuming manual data acquisition and entry requirements.3–8”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
What the sources say
- Not checked — no full text of the sourcecites [3] source
- Not checked — no full text of the sourcecites [4] source
- Not checked — no full text of the sourcecites [5] source
- Not checked — no full text of the sourcecites [6] source
- Not checked — no full text of the sourcecites [7] source
- Partly supportedcites [8] sourceExperimental — accuracy not yet measured
In Results (Table 2; page unavailable), residents identify lack of evidence as a barrier, including one concern that the database cannot accurately stratify risk. The paper documents a perceived accuracy concern among surgical trainees, but does not establish that the calculator’s accuracy is suboptimal or that this is a general cause of poor clinical adoption. (LLM, conf=0.85)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Academic intensivists make approximately 56 patient care and resource use decisions per day.36”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Partly supportedcites [36] sourceExperimental — accuracy not yet measured
The Results report almost 56 ad hoc decisions per intensivist in two university-hospital ICUs, covering patient care and ICU operations. But 56 is a count per observed intensivist, not a daily rate: recordings lasted two to six hours per person, and the paper gives a separate per-day estimate for ICU shift leaders collectively. (LLM, conf=0.88)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Traditional clinical decision-support systems require time-consuming manual data acquisition and entry, which impairs their adoption.8,33”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Partly supportedcites [8] sourceExperimental — accuracy not yet measured
In Results (Table 2; page unavailable), a surgical trainee identifies entering information into a risk calculator as “way too slow and cumbersome,” and the Discussion links underuse to poor integration with clinical workflows. This supports time-consuming entry as an adoption barrier for surgical risk calculators, but the paper does not establish that traditional clinical decision-support systems generally require manual data acquisition. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [33] source
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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“In an assessment of medical student and resident intensive care unit (ICU) patient presentations, potentially important data were omitted from 157 of 157 presentations.10”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Supportedcites [10] source
The Results (page not provided) report 157 ICU patient presentations and state that 100% of trainee presentations contained data omissions. The same section identifies medical students and postgraduate trainees among the presenters. The paper did not assess the clinical importance of each omission, but the claim’s “potentially important” wording does not assert that every omitted item was important. (LLM, conf=0.94)
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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In a prospective study, the algorithm predicted postoperative complications with greater accuracy than physicians.17”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Partly supportedcites [17] sourceExperimental — accuracy not yet measured
The Methods describe a prospective pilot study using a simulated workflow. The Results report that MySurgeryRisk was more accurate than physicians’ initial assessments for the postoperative complications tested except cardiovascular complications. The claim omits that exception and the simulated-workflow setting. (LLM, conf=0.88)
plaincorrelational- 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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“For example, the Framingham heart study primarily included white participants. A model trained on this data may reflect racial and ethnic bias because associations between cardiovascular risk factors and events differ by race and ethnicity.25”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
What the sources say
- Supportedcites [25] source
The Introduction says the Framingham Risk Score was developed in a largely White population and that risk scores can under- or overestimate risk across racial and ethnic groups. The Discussion reports that the magnitude of several risk-factor associations with cardiovascular events differs across groups, supporting the citing sentence’s qualified concern about model bias. (LLM, conf=0.91)
hedgedconditional- 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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Intuition can also identify patients with life-threatening conditions that would be underappreciated by traditional clinical parameters alone.47,48”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Partly supportedcites [47] sourceExperimental — accuracy not yet measured
The Results (Diagnostic added value of gut feeling) show that clinicians’ gut feeling flagged serious infections in children whose clinical assessment suggested a non-serious illness. The Discussion (Implications for practice) says the data are restricted to children in primary care and cannot necessarily be extrapolated to adults or other settings. The broader claim about patients with life-threatening conditions therefore exceeds what this study establishes. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [48] source
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.
- Partly supported
In the paper
“Surgeons report that lapses in judgment are the most common cause of their major errors.”
- Also stated in: § CONCLUSIONS AND RELEVANCE · plain
“Surgeons report that lapses in judgment are the most common cause of their major errors.2”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
What the sources say
- Not checked — no full text of the sourcecites [2] source
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.
- Also stated in: § CONCLUSIONS AND RELEVANCE · plain
In the paper
“Diagnostic and judgment errors are the second most common cause of preventable harm incurred by surgical patients.1”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
What the sources say
- Not checked — no full text of the sourcecites [1] source
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.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Herein lies the strength of artificial intelligence for predictive analytics in medicine: human disease is simply too broad and complex to be explained and interpreted by rules.59,60”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
plain- 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.
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
“Despite their utility for predictive analytics, deep learning only provides outcome probabilities that loosely correspond to specific decisions and actions.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
plaincorrelational- 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.
In the paper
“Emotions surrounding an acute surgical condition may also create a sense of urgency and pressure on surgeons to perform futile operations.37”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [37] source
hedgedconditional- 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 weaknesses of traditional approaches may be overcome by artificial intelligence models fed with livestreaming intraoperative and EHR data to augment surgical decision-making through hpreoperative, intraoperative, and postoperative phases of care (Figure 2).”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
hedgedconditional- 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.
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
“However, because decision aids apply to heterogeneous patient populations with 1 common clinical presentation or choice, they do not consider individual patient physiology and risk factors.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
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.
In the paper
“A meta-analysis43 found that the optimal postoperative day 3 CRP cutoff value was 172 mg/L (to convert to nanomoles per liter, multiply by 9.524).”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not checked — no full text of the sourcecites [43] 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 claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Heuristics may lead to bias or predictable and systematic cognitive errors, as described in Table 2.16,35”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
hedgedconditional- 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
“Each step introduces variability and opportunities for error.40”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [40] source
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.
In the paper
“For example, elevated serum levels of C-reactive protein (CRP) are associated with anastomotic leak after colorectal surgery.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not checked — no full text of the sourcecites [43] source
plaincorrelational- 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
“Surgical decision-making is often hindered by uncertainty owing to missing or incomplete data.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
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.
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
“When algorithms are trained on data sets that are influenced by bias, algorithm outputs will likely reflect similar bias.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
hedgedconditional- 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
“In 1 prominent example, a model designed to augment judicial decision-making by predicting the likelihood of crime recidivism demonstrated predilection for racial/ethnic discrimination.75”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
What the sources say
- Not matchedcites [75]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boostedcorrelational- 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.
- Not matched
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
“When data used to train an algorithm are predominantly derived from patient populations with different demographics than the patient for whom the algorithm is applied, accuracy may suffer.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
hedgedconditional- 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.
None of the sources cited for this claim have been checked yet.
In the paper
“Human intuition seems to arise from dopaminergic limbic system neurons that modify their connections with one another when a certain pattern or situation leads to a reward or penalty such as pleasure or pain.69,70”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Not matchedcites [69]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [70] 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.
- Not matched
In the paper
“Within 6 years, more than 4 of 5 US hospitals adopted EHRs.66”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Not checked — no full text of the sourcecites [66] 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
“Accountability for errors poses another challenge.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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
“Automated artificial intelligence models fed with livestreaming EHR data can address these weaknesses.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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.
In the paper
“However, efforts to use manual data entry to feed machine learning models for surgical risk prediction on mobile devices have been successful.14”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Not checked — no full text of the sourcecites [14] source
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
“Because EHRs are continuously updated as patient data become available, artificial intelligence models can provide real-time predictions and recommendations.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
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. 21
- Probably not a substantial claim. 18
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Surgical diseases may evoke fear and anger, which influence perceptions of risks and benefits.23,51”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Partly supportedcites [23] sourceExperimental — accuracy not yet measured
The Introduction says that changes in health status may evoke fear or anger, and the Discussion reports small, preliminary effects of those emotions on some risk perceptions. The study used a hypothetical medication decision, not surgical diseases, and did not establish an effect on perceptions of benefits. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [51] source
hedgedconditional- 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.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“These impairments are exacerbated by acute and chronic sleep deprivation, which occurs in as many as two-thirds of all acute care surgeons taking in-house call.52,53”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [52] source
- Could not verifycites [53] sourceExperimental — accuracy not yet measured
The Sleep-dependent memory enhancement section discusses how sleep deprivation affects volunteers’ performance on memory tasks, not how often surgeons are sleep-deprived. Searches for acute care surgeons, in-house call, and the two-thirds figure found no passage addressing the claimed prevalence. (LLM, conf=0.76)
hedged- 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 cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To capitalize on this phenomenon, Super Learner ranks a set of candidate algorithms20,28,38,39 by their performance and applies an optimal weight to each, creating ensemble algorithms that can accurately predict transfusion requirements and mortality among trauma patients.20,28,38,39”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Partly supportedcites [20] sourceExperimental — accuracy not yet measured
The Methods (SuperLearner Prediction; page not available) describe evaluating multiple algorithms and using cross-validation to form an optimally weighted ensemble. The Results (SL Discrimination of Mortality; page not available) report accurate mortality prediction in three trauma cohorts. The paper does not report prediction of transfusion requirements. (LLM, conf=0.88)
- Partly supportedcites [28] sourceExperimental — accuracy not yet measured
The Methods (page unavailable) say SuperLearner uses cross-validation to combine candidate algorithms and select the best-performing approach. The Abstract Results and Results > Prediction report predictions of ongoing transfusion and death in trauma patients. Our copy does not specify that SuperLearner applies an optimal weight to each candidate algorithm. (LLM, conf=0.82)
- Partly supportedcites [38] sourceExperimental — accuracy not yet measured
The Introduction and Prediction Algorithms section describe ranking candidate algorithms by predictive performance and combining them with optimal weights. The Results report accurate ICU mortality prediction, but the study included a mixed ICU population rather than evaluating trauma patients separately, and it did not assess transfusion requirements (Results > Patients; Patients and Methods > Data Collection and Patients). (LLM, conf=0.90)
- Partly supportedcites [39] sourceExperimental — accuracy not yet measured
The Super Learner section describes comparing candidate algorithms by cross-validated risk and combining them with weights chosen to minimize estimated risk. The paper studies propensity-score estimation in simulated data; it does not establish accurate prediction of transfusion requirements or mortality among trauma patients. (LLM, conf=0.88)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Parametric regression equations also fail to represent the complex, nonlinear associations among input variables, further limiting the accuracy of traditional multivariable regression models.22,29”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [22] source
- Partly supportedcites [29] sourceExperimental — accuracy not yet measured
The Results (III.3; page not provided) report that the decision-tree model had a larger ROC area than logistic regression, offering some support for a limitation in its predictive performance in this ICU comparison. The paper does not say that parametric regression equations fail to represent complex, nonlinear associations among inputs or identify that as the reason for the difference; it also reports that all four models had good discriminatory performance. (LLM, conf=0.78)
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.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Approximately 153 billion GB of data were generated in 2013, with projected growth of 48% per year.67”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Could not verifycites [67] sourceExperimental — accuracy not yet measured
The Introduction discusses growth in publications about emotion, while Global Organismic States discusses methods for measuring brain activity; neither addresses data generated in 2013. Searches for “153 billion GB” and “48% per year” found no passage supporting either figure in our copy. (LLM, conf=0.78)
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.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“This would require several elements that communicate with one another reliably and efficiently, including robust quality filters, a public key infrastructure, and encryption that can only be deciphered by the intended receiver.68”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Could not verifycites [68] sourceExperimental — accuracy not yet measured
The passages from the paper’s Abstract discuss amygdala-related learning and social decision-making, not a system for delivering model outputs to mobile devices. Searches for quality filters, public key infrastructure, encryption, and secure delivery found no passage addressing those requirements. (LLM, conf=0.77)
hedgeddirect- 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.
- Could not verify
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
“Surgical decision-making is dominated by hypothetical deductive reasoning and individual judgment, which are highly variable and ill-suited to remedy these errors.”
§ Artificial Intelligence and Surgical Decision-Making > Abstract > CONCLUSIONS AND RELEVANCE
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.
- Rests on an assumption: Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics.
In the paper
“Even when data collection and analysis are complete, high decision-making volume begets decision fatigue, manifesting as procrastination, less persistence when facing adversity, decreased physical stamina, and lower quality and quantity of mathematic calculations.49”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [49] source
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 claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“However, input variables must be entered manually, and its predictive accuracy is suboptimal, especially for nonelective operations, representing opportunities for improvement.4–7”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
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.
It may state two separate claims as one.
In the paper
“The negative predictive value was 97%, such that a low value usually indicates no leak, but the positive predictive value was 21%.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not checked — no full text of the sourcecites [43] 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.
It may state two separate claims as one.
In the paper
“Reinforcement learning has been used to recommend optimal fluid resuscitation and vasopressor administration strategies for patients with sepsis.31 Ninety-day mortality was lowest when care provided by clinicians was concordant with model recommendations.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [31] source
plaincorrelational- 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 claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Most diseases are not driven by a single physiologic parameter; therefore, prognostic scoring systems often incorporate multiple parameters for tasks such as measuring illness severity and predicting stroke and severe gastrointestinal bleeding.24,45,57”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
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
“For a surgical oncologist with a busy outpatient clinic, automated production of prognostic data from artificial intelligence models could improve efficiency and preserve face-to-face patient-surgeon interactions by obviating manual data acquisition and entry into prognostic models.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
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: 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.
In the paper
“Understanding and incorporating these values is essential to an effective shared decision-making process.50”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
What the sources say
- Not checked — no full text of the sourcecites [50] source
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: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In a systematic review44 including 31 043 patients facing screening or treatment decisions, patients exposed to decision aids felt more knowledgeable and played a more active role in the decision-making process.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not matchedcites [44]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelationaln = 31,043- 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.
- Not matched
In the paper
“Reinforcement learning has also been used to recommend basal and bolus insulin administration for virtual type 1 diabetics.46 The algorithm performed as well as standard intermittent self-monitoring and continuous glucose monitoring methods, but with fewer episodes of hypoglycemia.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
What the sources say
- Not matchedcites [46]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Not matched
In the paper
“In a systematic review of 17 studies investigating decisions made by surgical patients, decision aids were associated with more knowledge regarding treatment options, preference for less invasive treatments, and no observable differences in anxiety, quality of life, morbidity, or mortality.30”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Traditional Predictive Analytics and Clinical Decision Support
What the sources say
- Not checked — no full text of the sourcecites [30] source
plaincorrelational- 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
“Patient values are individualized by nature, precluding the creation of a criterion standard of optimal decision-making.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges in Surgical Decision-Making
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: 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
“Similar methods could be applied to augment the decision to operate.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Artificial Intelligence Predictive Analytics and Augmented Decision-Making
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.
In the paper
“Initial prospective implementation should occur on a small scale under close monitoring, similar to phase 1 and 2 clinical trials for experimental medications, with analysis of how decision-support tools affect decisions across populations and among individual patients.74”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
What the sources say
- Not matchedcites [74]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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: 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. It may state two separate claims as one.
- Not matched
In the paper
“The My Surgery Risk platform uses EHR data for 285 variables to predict 8 postoperative complications with an area under the curve (AUC) of 0.82–0.94 and to predict mortality at 1, 3, 6, 12, and 24 months with an AUC of 0.77–0.83.15”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Implementation
What the sources say
- Not checked — no full text of the sourcecites [15] source
plaincorrelational- 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
“If model inputs are flawed or model outputs are not carefully monitored by data scientists and interpreted by astute clinicians, many patients could be harmed in a short time frame.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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.
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 produce models that may be integrated with any EHR in any setting, data must be standardized.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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
“Artificial intelligence models must be rigorously analyzed in a retrospective fashion with robust external validation prior to prospective clinical application under the close scrutiny of astute clinicians and data scientists.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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.
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
“Artificial intelligence models trained on erroneous or misrepresentative data are likely to obscure the truth.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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: 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
“Prior to clinical implementation, machine and deep learning models must be rigorously analyzed in a retrospective fashion and externally validated to ensure generalizability.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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.
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
“Successful integration of artificial intelligence with surgical decision-making would require data standardization, advances in model interpretability, careful implementation and monitoring, attention to ethical challenges, and preservation of bedside assessment and human intuition in the decision-making process.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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. 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
“Our justice system is well-equipped to address scenarios in which an individual clinician is responsible for making an errant decision, but it may prove difficult to assign blame to a computer program and its developers.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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
“Surgical decision-making is impaired by time constraints, uncertainty, complexity, decision fatigue, hypothetical-deductive reasoning, and bias, leading to preventable harm.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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.
It may state two separate claims as one.
- Rests on an assumption: Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics.
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
“Traditional decision-support systems are compromised by time-consuming manual data entry and suboptimal accuracy.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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.
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
“Because studies with positive results are more likely to be submitted and published, artificial intelligence literature may be overly optimistic.”
§ Artificial Intelligence and Surgical Decision-Making > Observations > Challenges to Adoption
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.
- Rests on an assumption: Studies with positive results are more likely to be submitted and published.
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
“Properly applied, artificial intelligence has the potential to transform surgical care by augmenting the decision to operate, the informed consent process, identification and mitigation of modifiable risk factors, recognition and management of complications, and shared decisions regarding resource use.”
§ Artificial Intelligence and Surgical Decision-Making > Conclusions
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.
The paper relies on this without support.
Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics.
“Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics.”
The paper relies on this without support.
There is a relative paucity of research investigating surgical decision-making and strategies to improve it.
“Although decision-making is one of the most difficult and important tasks that surgeons perform, there is a relative paucity of research investigating surgical decision-making and strategies to improve it.”
The paper relies on this without support.
The volume of data generated by electronic health records is ideal for artificial intelligence models, which thrive on large data sets.
“This data volume is ideal for artificial intelligence models, which thrive on large data sets.”
The paper relies on this without support.
Automated surgical risk predictions with mobile device outputs have not yet been reported.
“To our knowledge, automated surgical risk predictions with mobile device out puts have not yet been reported.”
The paper relies on this without support.
Diligent clinicians and informed patients will want to know why a computer program made a certain prediction or recommendation.
“Diligent clinicians and informed patients will want to know why a computer program made a certain prediction or recommendation.”
The paper relies on this without support.
Studies with positive results are more likely to be submitted and published.
“Because studies with positive results are more likely to be submitted and published, artificial intelligence literature may be overly optimistic.”
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 cited source says what the claim attributes to it.
In the citing paper
“In the perioperative domain, MySurgeryRisk [30] demonstrated that ML-based prediction of postoperative complications could complement physician judgment”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [30]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, these approaches did not establish a structured benchmark that translates subjective physician judgment into reproducible, imbalance-aware performance metrics.”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [30]
Experimental — accuracy not yet measured
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Vincent, J. L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., Reinhart, C. K., Suter, P. M., & Thijs, L. G. (1996) · Intensive Care Medicine · doi:10.1007/bf01709751 · Cited by 11,674 · cited 1×
“24,45,57 Parametric regression prognostic scoring systems assume that relationships among input variables are linear.”
BackgroundDecision aids for people facing health treatment or screening decisions
Stacey, D., Légaré, F., Lewis, K., Barry, M. J., Bennett, C. L., Eden, K. B., Holmes-Rovner, M., Llewellyn-Thomas, H., Lyddiatt, A., Thomson, R., et al. (2017) · Cochrane Database of Systematic Reviews · doi:10.1002/14651858.cd001431.pub5 · Cited by 6,685
A guide to deep learning in healthcare
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312 · cited 1×
“60,62,63 Deep models have successfully performed patient phenotyping, disease prediction, and mortality prediction tasks.”
BackgroundDeciding advantageously before knowing the advantageous strategy
Bechara, A., Damasio, H., Tranel, D., & Damasio, A. R. (1997) · Science · doi:10.1126/science.275.5304.1293 · Cited by 3,547
The neural basis of economic decision-making in the Ultimatum Game.
Sanfey, A. G., Rilling, J. K., Aronson, J. A., Nystrom, L. E., & Cohen, J. D. (2003) · Science · doi:10.1126/science.1082976 · Cited by 3,375 · cited 1×
“69,70 Subsequently, similar patterns or situations evoke positive and negative emotions, or gut feelings, which are powerful and effective decision-making tools.”
BackgroundBurnout and Medical Errors Among American Surgeons
Shanafelt, T. D., Balch, C. M., Bechamps, G., Russell, T., Dyrbye, L., Satele, D., Collicott, P., Novotny, P. J., Sloan, J., & Freischlag, J. (2010) · Annals of Surgery · doi:10.1097/sla.0b013e3181bfdab3 · Cited by 2,099 · cited 2×
“Articles were screened by reviewing their abstracts for the following criteria: (1) published in English, (2) published in a peer-reviewed journal, and (3) primary literature or a review article.”
MethodSleep-dependent memory consolidation
Stickgold, R. (2005) · Nature · doi:10.1038/nature04286 · Cited by 1,857 · cited 1×
“52,53 For a surgical oncologist with a busy outpatient clinic, automated production of prognostic data from artificial intelligence models could improve efficiency and preserve face-to-face patient-surgeon interactions by obviating manual data acquisition and entry into prognostic models.”
BackgroundShickel, B., Tighe, P. J., Bihorac, A., & Rashidi, P. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2767063 · Cited by 1,688 · cited 1×
“61 Automatic feature extraction also promotes discovery of novel patterns and phenotypes that may have been overlooked by handcrafted feature selection techniques.”
BackgroundSelf-citationRethinking the Emotional Brain
LeDoux, J. (2012) · Neuron · doi:10.1016/j.neuron.2012.02.004 · Cited by 1,594 · cited 1×
“71, 72 Intuition can also identify patients with life-threatening conditions that would be underappreciated by traditional clinical parameters alone.”
Background
Research works printed but not linked: 1
- Kahneman, 2013, Thinking, Fast and Slow
Cited by
Sorted by citations
Expanding Explainability: Towards Social Transparency in AI systems
Ehsan, U., Liao, Q. V., Muller, M., Riedl, M. O., & Weisz, J. D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445188 · Cited by 538
“being employed in high stakes decision-making scenarios in industries such as healthcare [63], finance [76], college admissions [79], hiring [19], and criminal justice [37], the need for explainability becomes paramount.”
BackgroundMcGenity, C., Clarke, E. L., Jennings, C., Matthews, G., Cartlidge, C., Freduah-Agyemang, H., Stocken, D. D., & Treanor, D. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01106-8 · Cited by 290
Artificial intelligence in surgery
Varghese, C., Harrison, E. M., O’Grady, G., & Topol, E. J. (2024) · Nature Medicine · doi:10.1038/s41591-024-02970-3 · Cited by 287
“The advantages of AI in hypothetico-deductive surgical decision-making are expertly overviewed by Loftus et al. 25 .”
How human–AI feedback loops alter human perceptual, emotional and social judgements
Glickman, M., & Sharot, T. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-02077-2 · Cited by 289
Artificial Intelligence in Dermatology Image Analysis: Current Developments and Future Trends
Li, Z., Koban, K. C., Schenck, T. L., Giunta, R. E., Li, Q., & Sun, Y. (2022) · Journal of Clinical Medicine · doi:10.3390/jcm11226826 · Cited by 291
Metadata
- Authors
- Loftus, T. J., Tighe, P. J., Filiberto, A. C., Efron, P. A., Brakenridge, S. C., Mohr, A. M., Rashidi, P., Upchurch, G. R., & Bihorac, A.
- Affiliations
- University of Florida Health (US)
- University of Florida (US)
- ORCID
- Venue
- JAMA Surgery
- Publisher
- American Medical Association (AMA)
- Published
- 2020-02-01
- Volume
- 155
- Issue
- 2
- Pages
- 148
- ISSN
- 2168-6254 (ISSN-L)
- PMC
- PMC7286802
- OpenAlex
- W2995887567
- Cited by
- 650
- References
- 82
- Citations by year
- 2026: 141 · 2025: 147 · 2024: 120 · 2023: 91 · 2022: 65 · 2021: 54 · 2020: 28
- FWCI
- 1.97
- Type
- journal article
- Language
- en
- Open access
- green
- europepmc.org
- Locations
- JAMA Surgery (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health (5r01gm113945-05)
- National Institute on Aging (K07AG066813, R01AG055337)
- National Institute of General Medical Sciences (R01 GM-113945, R01GM114290, R01GM105893, P50GM111152, T32GM008721, R01GM110240)
- National Institute of Biomedical Imaging and Bioengineering (R21EB027344)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- artificial intelligence, surgical decision-making, clinical decision support systems, predictive analytics, algorithmic bias, model interpretability, electronic health records, informed consent, shared decision-making, postoperative care, surgical risk factors, human intuition
- MeSH terms
- Clinical Decision-Making, Artificial Intelligence, Emotions, Humans, Surgical Procedures, Operative, Time Factors, Intuition, Decision Support Systems, Clinical, Uncertainty, Electronic Health Records
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 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
