The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index; 63 of the 87 sources its claims cite were checked for support.
Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction
Open accessAbstract
PURPOSE: BACKGROUND: Sepsis is a leading cause of mortality in intensive care units (ICUs), and its rapid progression poses significant challenges for early detection. Traditional scoring systems, such as SOFA and APACHE II, provide clinical benchmarks but often fail to capture subtle early signs of deterioration. Machine learning (ML) and deep learning (DL) models have demonstrated strong predictive performance; however, their “black-box” nature limits transparency, clinician trust, and adoption in real-world ICU settings. Explainable artificial intelligence (XAI) clarifies how predictions are derived. METHODOLOGY: This systematic review examines studies published between 2020 and 2025 that applied XAI methods, including SHAP, LIME, Grad-CAM, and sensitivity analysis, to predict sepsis onset and ICU mortality. We analyzed the datasets used (e.g., MIMIC-III/IV, Emory University Hospital, Ruijin Hospital), model architectures, interpretability strategies, and the clinical features most strongly associated with predictions. RESULTS: Findings indicate that XAI-enhanced models not only maintain high predictive accuracy but also highlight clinically meaningful indicators such as respiratory rate, blood urea nitrogen (BUN), urine output, and the Glasgow Coma Scale (GCS), thereby improving clinician confidence and facilitating adoption. CONCLUSION: Despite these advances, challenges remain, including limited prospective evaluation, inconsistent interpretability metrics, and variable integration into clinical workflows. We conclude by recommending future research priorities, including real-world validation, user-centered design, and multimodal data integration, to ensure that XAI can reliably support timely and informed decision-making in critical care environments.
Overview
CoChat Summary
## TL;DR
This systematic review synthesized 43 studies (2020–2025) on explainable AI for sepsis onset and ICU mortality/readmission prediction in adult ICUs. It finds that XAI methods, especially SHAP, can preserve strong predictive performance while highlighting clinically meaningful features, but prospective validation and standardized interpretability evaluation remain limited.
## Key findings
- The review included 43 studies; 15 were summarized as representative studies in Table 1.
- Across the reviewed literature, XAI-enhanced models often reported strong discrimination, with AUC values above 0.84 and some reaching up to 0.94 (e.g., Random Forest on MIMIC-IV) and 0.89 for early sepsis prediction.
- Commonly highlighted predictive features were respiratory rate, Glasgow Coma Scale (GCS), blood urea nitrogen (BUN), urine output, and mean arterial pressure (MAP).
- The most commonly used interpretability methods were SHAP, LIME, and sensitivity analysis; Grad-CAM was also used in some studies.
## Methods
- Design: Systematic review conducted according to PRISMA 2020 guidelines.
- Data/sample: Studies published between January 2020 and January 2025 on adult ICU sepsis onset, ICU readmission, or in-hospital mortality; sources included ResearchGate, IEEE Xplore, Scopus, Web of Science, and Google Scholar.
- Analysis: Two reviewers independently screened studies and extracted data; study quality/risk of bias was assessed with PROBAST, and evidence was synthesized by dataset, model type, validation approach, performance metrics, XAI method, and top features.
## Limitations
- The paper states that many included studies relied on retrospective data, often from single-center datasets, which limits generalizability.
- It also states that external/temporal validation, prospective studies, and clinician-centered evaluations were limited, and that interpretability metrics were inconsistent across studies.
- Evident from the text: the review’s conclusions are based on a literature synthesis rather than new patient-level experimentation, so its claims depend on the quality and reporting of the included studies.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Fig. 1 Illustration of explainable AI (XAI) in ICU settings, showing how model transparency supports clinical decision-making (adapted from Chaddad et al. [3])](https://figures.cochat.ai/paper-figures/c6fde044e3e04ce7bfb564b0e3e4676e/explainable-ai-for-critical-care-a-systematic-review-of-interpretable-models-for-figure-1.jpg)



Verification
Claims the paper makes
19 Valid · 6 Not valid · 7 Not checked · 45 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation II (APACHE II) were designed to quantify organ dysfunction and estimate mortality risk rather than to diagnose sepsis or support early detection.”
§ Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction > Introduction > Background
What the sources say
- Disputedcites [9] Huang M, Cai S, Su J. The pathogenesis of sepsis and potential therapeutic targets. Int J Mol Sci. 2019;20(21):5376. https://doi.org/10.3390/ijms20215376. sourceExperimental — accuracy not yet measured
The Definition section explicitly describes SOFA as a sepsis diagnostic criterion for ICU patients with infection or suspected infection, contrary to the claim that it is not used to diagnose sepsis. The paper cautions that SOFA is not an independent definition of sepsis and that relying on it can delay diagnosis, but those qualifications do not support the categorical claim. Its mention of APACHE II in the Biomarkers section does not establish what that score was designed to do. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
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.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Moreover, comprehensive comparisons of different XAI approaches across diverse ICU datasets are lacking [12, 13, 18].”
§ Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction > Introduction > Problem statement
What the sources say
- Not checked — no full text of the sourcecites [12] Jiang Z, Liu H, Wang Y, Tang W, Yuan X, Zhang X, et al. Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care. Comput Methods Programs Biomed. 2023;241:107772. https://doi.org/10.1016/j.cmpb.2023.107772. source
- Partly supportedcites [13] Hu C, Li L, Li Y, Wang F, Hu B, Peng Z. Interpretable machine learning for early prediction of prognosis in sepsis: a discovery and validation study. Infect Dis Ther. 2022;11(3):1117–32. https://doi.org/10.1007/s40121-022-00628-6. sourceExperimental — accuracy not yet measured
The Introduction and Discussion (page unavailable) identify a lack of transparency in sepsis prognosis models and say previous models had not used SHAP to interpret sepsis mortality predictions. That supports a narrower gap in explainability, but the paper does not establish that comprehensive comparisons of different XAI approaches across diverse ICU datasets are lacking. Its Methods describe data from a single-center ICU database. (LLM, conf=0.78)
- Could not verifycites [18] Chen Q, Guo X, Pan Y, Wang Y, Zhao X. Transferability and interpretability of the sepsis prediction models in the intensive care unit. BMC Med Inf Decis Mak. 2022;22(1):343. https://doi.org/10.1186/s12911-022-02090-3. sourceExperimental — accuracy not yet measured
The Methods’ Interpretive analysis section describes using SHAP, and the Results discuss several ICU datasets, but neither states that comprehensive comparisons of XAI approaches are lacking. Searches for comparisons of interpretability methods and for a gap across ICU cohorts found no passage making that claim. The indexed copy provides section labels but no page numbers. (LLM, conf=0.73)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“many of these systems function as “black boxes,” generating predictions without providing explanations for their reasoning.”
- Also stated in: § Background · plain
“However, these models often operate as “black boxes,” making it challenging for clinicians to trust the predictions and incorporate them into timely decision-making.”
§ Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction > Introduction > Problem statement
What the sources say
- Partly supportedcites [1] Panayides AS, Pattichis MS, Leandrou S, Pitris C, Calvetti D, Costaridou L, et al. AI in medical imaging informatics: current challenges and future directions. IEEE J Biomed Health Inf. 2020;24(7):1837–57. https://doi.org/10.1109/JBHI.2020.2991043. sourceExperimental — accuracy not yet measured
The “CNN Interpretability” section describes deep CNNs as black-box functions and says researchers need to understand how they derive classification decisions. That supports the general point about unexplained predictions, but the discussion concerns medical imaging, not systems predicting sepsis onset or patient outcomes. The passages found for sepsis and patient outcomes do not establish that narrower application. (LLM, conf=0.87)
- Partly supportedcites [2] Prentzas N, Kakas A, Pattichis CS. Explainable AI applications in the medical domain: a systematic review. arXiv preprint arXiv:2308.05411. 2023.https://arxiv.org/abs/2308.05411. sourceExperimental — accuracy not yet measured
The discussion of explainability says that machine-learning models, including deep neural networks, are opaque and less explainable (Explainable AI applications in the Medical; page not provided). The review supports the general black-box characterization, but the passages found do not establish it specifically for systems predicting sepsis onset or patient outcomes. (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.
- Also stated in: § Background · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Furthermore, multi-centre validation and prospective testing remain rare [12, 13, 18], making it difficult to identify which interpretability techniques are most reliable in real-world practice.”
§ Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction > Introduction > Research gap Although explainable artificial intelligence has demonstrated potential in supporting the prediction of sepsis and ICU mortality [4–6], its application in real clinical environments is still limited. Most published studies rely on retrospective data and are often based on a single institution or dataset [12–17]. This narrow scope restricts the generalizability of the findings and raises concerns about how these models would perform across diverse patient populations and healthcare settings. In addition, much of the current research prioritizes improving prediction accuracy while giving less attention to whether the explanations produced by XAI models are truly understandable and useful for clinicians [1, 2, 12]. As a result, there is uncertainty about the practical value of these explanations in time-critical ICU situations. Another important limitation is the lack of clinician-centred evaluation. Only a small number of studies have examined how healthcare professionals interpret XAI outputs, how these explanations influence clinical decisions, or how easily such tools can be incorporated into existing ICU workflows. Furthermore, multi-centre validation and prospective testing remain rare [12, 13, 18], making it difficult to identify which interpretability techniques are most reliable in real-world practice. These gaps underline the need for future research that goes beyond model performance alone. There is a clear requirement for studies that integrate external validation, clinician involvement, and rigorous assessment of interpretability. Developing XAI models that are both accurate and genuinely understandable in varied ICU environments is essential for safe and effective clinical adoption, ultimately supporting better decision-making and improved patient outcomes.
What the sources say
- Not checked — no full text of the sourcecites [12] Jiang Z, Liu H, Wang Y, Tang W, Yuan X, Zhang X, et al. Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care. Comput Methods Programs Biomed. 2023;241:107772. https://doi.org/10.1016/j.cmpb.2023.107772. source
- Partly supportedcites [13] Hu C, Li L, Li Y, Wang F, Hu B, Peng Z. Interpretable machine learning for early prediction of prognosis in sepsis: a discovery and validation study. Infect Dis Ther. 2022;11(3):1117–32. https://doi.org/10.1007/s40121-022-00628-6. sourceExperimental — accuracy not yet measured
The Discussion (page not provided) describes this explainable sepsis model as a single-center retrospective study lacking external validation and calls for prospective trials. The Introduction says few machine-learning models have reached clinical practice, but the paper does not establish how rare multi-centre validation or prospective testing is across sepsis and ICU-mortality models. (LLM, conf=0.83)
- Partly supportedcites [18] Chen Q, Guo X, Pan Y, Wang Y, Zhao X. Transferability and interpretability of the sepsis prediction models in the intensive care unit. BMC Med Inf Decis Mak. 2022;22(1):343. https://doi.org/10.1186/s12911-022-02090-3. sourceExperimental — accuracy not yet measured
The Background (page unavailable) stresses the need for external validation and reports that models often perform worse on external samples; the References also list a study describing external validation as infrequent. But this paper does not establish that multi-centre validation or prospective testing of explainable AI models for sepsis and ICU mortality is rare. Its Background instead mentions several prospective sepsis-prediction studies. (LLM, conf=0.74)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In addition, much of the current research prioritizes improving prediction accuracy while giving less attention to whether the explanations produced by XAI models are truly understandable and useful for clinicians [1, 2, 12].”
§ Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction > Introduction > Research gap Although explainable artificial intelligence has demonstrated potential in supporting the prediction of sepsis and ICU mortality [4–6], its application in real clinical environments is still limited. Most published studies rely on retrospective data and are often based on a single institution or dataset [12–17]. This narrow scope restricts the generalizability of the findings and raises concerns about how these models would perform across diverse patient populations and healthcare settings. In addition, much of the current research prioritizes improving prediction accuracy while giving less attention to whether the explanations produced by XAI models are truly understandable and useful for clinicians [1, 2, 12]. As a result, there is uncertainty about the practical value of these explanations in time-critical ICU situations. Another important limitation is the lack of clinician-centred evaluation. Only a small number of studies have examined how healthcare professionals interpret XAI outputs, how these explanations influence clinical decisions, or how easily such tools can be incorporated into existing ICU workflows. Furthermore, multi-centre validation and prospective testing remain rare [12, 13, 18], making it difficult to identify which interpretability techniques are most reliable in real-world practice. These gaps underline the need for future research that goes beyond model performance alone. There is a clear requirement for studies that integrate external validation, clinician involvement, and rigorous assessment of interpretability. Developing XAI models that are both accurate and genuinely understandable in varied ICU environments is essential for safe and effective clinical adoption, ultimately supporting better decision-making and improved patient outcomes.
What the sources say
- Partly supportedcites [1] Panayides AS, Pattichis MS, Leandrou S, Pitris C, Calvetti D, Costaridou L, et al. AI in medical imaging informatics: current challenges and future directions. IEEE J Biomed Health Inf. 2020;24(7):1837–57. https://doi.org/10.1109/JBHI.2020.2991043. sourceExperimental — accuracy not yet measured
The CNN Interpretability section (page unavailable) says deep CNNs have achieved high accuracy but remain black boxes, and describes interpretability as an emerging research area. It does not say that much current research prioritizes accuracy over evaluating whether XAI explanations are understandable and useful to clinicians. (LLM, conf=0.82)
- Supportedcites [2] Prentzas N, Kakas A, Pattichis CS. Explainable AI applications in the medical domain: a systematic review. arXiv preprint arXiv:2308.05411. 2023.https://arxiv.org/abs/2308.05411. source
In “Accuracy vs Interpretability,” the review says most examined solutions reported better predictive performance than comparison models. In the Conclusions, it says very few works involved physicians in evaluating explanations, supporting the contrast with attention to whether explanations are useful and understandable to clinicians. (LLM, conf=0.87)
- Not checked — no full text of the sourcecites [12] Jiang Z, Liu H, Wang Y, Tang W, Yuan X, Zhang X, et al. Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care. Comput Methods Programs Biomed. 2023;241:107772. https://doi.org/10.1016/j.cmpb.2023.107772. 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.
- Partly supported
30 more claims · 4 with their cited sources checked
Create a free account to see all 77 claims and every source verdict.
- It may state two separate claims as one. 35
- Probably not a substantial claim. 14
Citations
Cites
The third international consensus definitions for sepsis and septic shock (Sepsis-3).
Singer, M., Deutschman, C. S., Seymour, C. W., Shankar-Hari, M., Annane, D., Bauer, M., Bellomo, R., Bernard, G. R., Chiche, J.-D., Coopersmith, C. M., et al. (2016) · JAMA · doi:10.1001/jama.2016.0287 · Cited by 28,250 · cited 8×
“2 Traditional scoring systems versus AI/XAI pipelines for sepsis and ICU mortality prediction [4–6], are applied to reveal the key factors influencing predictions and to align model outputs with established clinical scoring systems like SOFA and APACHE II [7, 9].”
InfluentialGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555 · cited 3×
“Among the most widely used interpretability methods are SHAP [4], LIME [5], sensitivity analysis [25], and visualization techniques like Grad-CAM [6].”
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401 · cited 3×
“By leveraging large-scale and diverse datasets, including MIMIC-IV, Emory University Hospital, UCSD, and Ruijin Hospital [10], the study evaluates various machine learning and deep learning approaches to uncover clinically meaningful patterns in patient data [11–17].”
The Pathogenesis of Sepsis and Potential Therapeutic Targets
Huang, M., Cai, S., & Su, J. (2019) · International Journal of Molecular Sciences · doi:10.3390/ijms20215376 · Cited by 776 · cited 3×
“Sepsis is a severe, life-threatening condition caused by a dysregulated immune response to infection and remains a major contributor to ICU mortality worldwide [7–9].”
Fleuren, L. M., Klausch, T. L. T., Zwager, C. L., Schoonmade, L. J., Guo, T., Roggeveen, L. F., Swart, E. L., Girbes, A. R. J., Thoral, P., Ercole, A., et al. (2020) · Intensive Care Medicine · doi:10.1007/s00134-019-05872-y · Cited by 755 · cited 1×
“Fleuren et al. [30] demonstrated that while predictive models often perform well, transparency regarding the contributing patient factors is critical for clinical trust.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions
Panayides, A. S., Amini, A., Filipovic, N. D., Sharma, A., Tsaftaris, S. A., Young, A., Foran, D., Do, N., Golemati, S., Kurc, T., et al. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2991043 · Cited by 713 · cited 3×
“In critical care, where timely decisions can directly affect patient survival, this lack of transparency can reduce clinician confidence, delay necessary interventions, and limit the practical adoption of AI tools [1, 2].”
A Review of Explainable Artificial Intelligence in Healthcare
Sadeghi, Z., Alizadehsani, R., CIFCI, M. A., Kausar, S., Rehman, R., Mahanta, P., Bora, P. K., Almasri, A., Alkhawaldeh, R. S., Hussain, S., et al. (2024) · Computers and Electrical Engineering · doi:10.1016/j.compeleceng.2024.109370 · Cited by 598 · cited 1×
“Sadeghi et al. [27] note that XAI helps clinicians understand how AI models make decisions.”
Survey of Explainable AI Techniques in Healthcare
Chaddad, A., Peng, J., Xu, J., & Bouridane, A. (2023) · Sensors · doi:10.3390/s23020634 · Cited by 591 · cited 1×
“In the Participants domain, most studies (e.g. [3, 7, 11, 12]), demonstrated a low risk of bias, indicating that the study populations were carefully selected and accurately represented real-world ICU patients.”
A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients
Wang, D., Li, J., Sun, Y., Ding, X., Zhang, X., Liu, S., Han, B., Wang, H., Duan, X., & Sun, T. (2021) · Frontiers in Public Health · doi:10.3389/fpubh.2021.754348 · Cited by 185 · cited 1×
“Wang et al. [31] similarly developed a predictive framework that achieved strong accuracy while clearly highlighting key clinical features influencing outcomes, reinforcing the importance of interpretable results for effective medical decision-making.”
Research works printed but not linked: 4
- Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Advances in neural information processing systems (NeurIPS). Vol. 30. 2017. arXiv:1705.07874. · arXiv
- Nicolaou A, Panayides A, Pattichis C, Kakas A, Stylianides C. An overview of explainable AI studies in the prediction of sepsis onset and sepsis mortality. In: Digital health and informatics innovations for sustainable health. Elsevier; 2024.
- Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Advances in neural information processing systems (NeurIPS). Vol. 30. 2017. arXiv:1705.07874. · arXiv
- Zhang TY, Zhong M, Cheng YZ, Zhang MW. An interpretable machine learning model for real-time sepsis prediction based on basic physiological indicators. Eur Rev Med Pharmacological Sci. 2023;27(10):4348–56.
Cited by
Pranata, Y., Mirwanti, R., Bahtiar, Y. A., & Purwanti, H. (2026) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s621469 · Cited by 1
“Yang et al (2026) 17 mapped 86 multimodal ICU AI studies but treated XAI only as a secondary theme, while Athukorala et al (2026) 14 focused specifically on XAI but restricted their scope to three clinical outcomes (sepsis onset, ICU readmission, and mortality).”
Gu, H., Shi, X., & Zhang, J. (2026) · Research Square · doi:10.21203/rs.3.rs-9507966/v1
Sona, G., Anitha, D., & Narmatha, B. (2026) · Journal of Innovative Image Processing · doi:10.36548/jiip.2026.2.005
“However, this methodology cannot adequately address temporal dependencies within ICU time-series and relies predominantly on manually selected features [13].”
Artificial Intelligence for Hemodynamic Monitoring: The Art, Science, and the Machine!
Magoon, R. (2026) · Journal of Cardiac Critical Care TSS · doi:10.25259/jccc_21_2026
Smart Cardiac ICU: Digital Integration, Predictive Analytics, and Perioperative Inflammation
Azamfirei, L., Veres, M., Bora, S., Oiaga, M. C., Butiulca, M., Lazăr, A. E., Szederjesi, J., & Grigorescu, B. L. (2026) · Bioengineering · doi:10.3390/bioengineering13080921
“Model performance depends on preprocessing capacity, handling missing values, and clear definitions of the intended outcomes [43,44].”
Metadata
- Authors
- Athukorala, V. S., & Ilmini, W. M. K. S.
- Affiliations
- University of Sri Jayewardenepura (LK)
- Corresponding author
- Athukorala, V. S.
- Ilmini, W. M. K. S.
- ORCID
- Ilmini, W. M. K. S.
- Venue
- BMC Medical Informatics and Decision Making
- Published
- 2026-02-03
- Volume
- 26
- Issue
- 1
- ISSN
- 1472-6947 (ISSN-L)
- PMC
- PMC12955129
- OpenAlex
- W7127278855
- Semantic Scholar
- 86dc041b3a0707a0e39a8e104905b9babb1dc07a
- Cited by
- 10
- References
- 35
- Citations by year
- 2026: 10
- FWCI
- 11.53
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor, 28 d)
- Locations
- BMC Medical Informatics and Decision Making (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- explainable AI, sepsis prediction, ICU mortality prediction, model interpretability, SHAP, lime, Grad-CAM, sensitivity analysis, intensive care, clinical decision support, MIMIC-III, MIMIC-IV, early sepsis detection
- MeSH terms
- Predictive Learning Models, Artificial Intelligence, Critical Care, Humans, Intensive Care Units, Hospital Mortality, Sepsis
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction. https://app.cochat.ai/papers/10.1186/s12911-026-03344-0
- The paper
- Athukorala, V. S., & Ilmini, W. M. K. S. (2026). Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction. BMC Medical Informatics and Decision Making. https://doi.org/10.1186/s12911-026-03344-0
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.