Interpretable Machine Learning to Optimize Early In-Hospital Mortality Prediction for Elderly Patients with Sepsis: A Discovery Study
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
Sepsis-related mortality rates are high among elderly patients, especially those in intensive care units (ICUs). Early prediction of the prognosis of sepsis is critical, as prompt and effective treatment can improve prognosis. Researchers have predicted mortality and the development of sepsis using machine learning algorithms; however, few studies specifically focus on elderly patients with sepsis. This paper proposes a viable model for early prediction of in-hospital mortality among elderly patients diagnosed with sepsis. We extracted patient information from the Medical Information Mart for Intensive Care IV database. We employed several machine learning algorithms to predict the in-hospital mortality of elderly ICU patients with sepsis. The performance of the model was evaluated by using the AUROC and F 1 score. Furthermore, the SHAP algorithm was used to explain the model, analyze how the individual features affect the model output, and visualize the Shapley value for a single individual. Our study included 18522 elderly patients, with a mortality of 15.4%. After screening, 59 clinical variables were extracted to develop models. Feature importance analysis showed that age, PO2, RDW, SPO2, WBC, and urine output were significantly related to the in-hospital mortality. According to the results of AUROC (0.871 (95% CI: 0.854–0.888)) and F 1 score (0.547 (95% CI: 0.539–0.661)) analyses, the extreme gradient boosting (XGBoost) model outperformed the other models (i.e., LGBM, LR, RF, DT, and KNN). Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death. XGBoost machine learning framework gives good in-hospital mortality prediction of elderly patients with sepsis and can maximize prediction model accuracy. The XGBoost model could be an effective tool to assist doctors in identifying high-risk cases of in-hospital mortality among elderly patients with sepsis. This could be used to create a clinical decision support system in the future.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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 doesn’t support the claim as written.
In the citing paper
“Complementary approaches, including LIME and Grad-CAM, were implemented in select studies to provide additional insights into model behavior [14, 17, 19], while sensitivity analysis was specifically employed in sepsis detection with deep neural networks [25].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [17]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These interpretability strategies enabled the identification of key physiological variables driving model predictions, such as respiratory rate (RR), Glasgow Coma Scale, mean arterial pressure (MAP), lactate, creatinine, heart rate (HR), blood urea nitrogen (BUN), body temperature, platelet count, and urine output [7, 12–18, 22, 24, 25, 39].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [17]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Most models reported AUC values exceeding 0.84, with some attaining up to 0.89 for early sepsis prediction [7, 12, 13, 17, 19, 22].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [17]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Most published studies rely on retrospective data and are often based on a single institution or dataset [12–17].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [17]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
Rudd, K. E., Johnson, S. C., Agesa, K. M., Shackelford, K. A., Tsoi, D., Kievlan, D. R., Colombara, D. V., Ikuta, K. S., Kissoon, N., Finfer, S., et al. (2020) · The Lancet · doi:10.1016/s0140-6736(19)32989-7 · Cited by 7,971
Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021
Evans, L., Rhodes, A., Alhazzani, W., Antonelli, M., Coopersmith, C. M., French, C., Machado, F. R., Mcintyre, L., Ostermann, M., Prescott, H. C., et al. (2021) · Intensive Care Medicine · doi:10.1007/s00134-021-06506-y · Cited by 5,082 · cited 1×
“The PO2, SPO2, and lactate are widely applied as targets of initial resuscitation in patients with severe sepsis and septic shock associated with inadequate tissue perfusion and hypoxia [32].”
BackgroundCollins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · BMJ · doi:10.1136/bmj.g7594 · Cited by 4,388
Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · British Journal of Cancer · doi:10.1038/bjc.2014.639 · Cited by 3,293
Sagi, O., & Rokach, L. (2018) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1249 · Cited by 3,103
Big Data and Machine Learning in Health Care
Beam, A. L., & Kohane, I. S. (2018) · JAMA · doi:10.1001/jama.2017.18391 · Cited by 2,506 · cited 1×
“This big datadriven approach involving the use of an advanced machine learning algorithm has been demonstrated to be superior to traditional analytic models and score models [27].”
MethodBig data and machine learning algorithms for health-care delivery
Ngiam, K. Y., & Khor, I. W. (2019) · The Lancet Oncology · doi:10.1016/s1470-2045(19)30149-4 · Cited by 1,424
Chu, D. K., Kim, L. H.-Y., Young, P. J., Zamiri, N., Almenawer, S. A., Jaeschke, R., Szczeklik, W., Schünemann, H. J., Neary, J. D., & Alhazzani, W. (2018) · The Lancet · doi:10.1016/s0140-6736(18)30479-3 · Cited by 778
Hou, N., Li, M., He, L., Xie, B., Wang, L., Zhang, R., Yu, Y., Sun, X., Pan, Z., & Wang, K. (2020) · Journal of Translational Medicine · doi:10.1186/s12967-020-02620-5 · Cited by 568
Liu, Z., Meng, Z., Li, Y., Zhao, J., Wu, S., Gou, S., & Wu, H. (2019) · Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine · doi:10.1186/s13049-019-0609-3 · Cited by 340
The status of intensive care medicine research and a future agenda for very old patients in the ICU
Flaatten, H., de Lange, D. W., Artigas, A., Bin, D., Moreno, R., Christensen, S., Joynt, G. M., Bagshaw, S. M., Sprung, C. L., Benoit, D., et al. (2017) · Intensive Care Medicine · doi:10.1007/s00134-017-4718-z · Cited by 281
Goulden, R., Hoyle, M.-C., Monis, J., Railton, D., Riley, V., Martin, P., Martina, R., & Nsutebu, E. (2018) · Emergency Medicine Journal · doi:10.1136/emermed-2017-207120 · Cited by 250
Martin-Loeches, I., Guia, M. C., Vallecoccia, M. S., Suarez, D., Ibarz, M., Irazabal, M., Ferrer, R., & Artigas, A. (2019) · Annals of Intensive Care · doi:10.1186/s13613-019-0495-x · Cited by 199
Sepsis and Immunosenescence in the Elderly Patient: A Review
Martín, S., Pérez, A., & Aldecoa, C. (2017) · Frontiers in Medicine · doi:10.3389/fmed.2017.00020 · Cited by 180
Rowe, T. A., & McKoy, J. M. (2017) · Infectious Disease Clinics of North America · doi:10.1016/j.idc.2017.07.010 · Cited by 162
Serum albumin is a strong predictor of sepsis outcome in elderly patients
Arnau-Barrés, I., Güerri‐Fernández, R., Luque, S., Sorlí, L., Vázquez‐Ibar, O., & Miralles, R. (2019) · European Journal of Clinical Microbiology & Infectious Diseases · doi:10.1007/s10096-019-03478-2 · Cited by 156
Fluid management in the critically ill
Vincent, J. (2019) · Kidney International · doi:10.1016/j.kint.2018.11.047 · Cited by 148
Zhang, L., Huang, T., Xu, F., Li, S., Zheng, S., Lyu, J., & Yin, H. (2022) · BMC Emergency Medicine · doi:10.1186/s12873-022-00582-z · Cited by 114
Biomarkers of Infection and Sepsis
Opal, S. M., & Wittebole, X. (2019) · Critical Care Clinics · doi:10.1016/j.ccc.2019.08.002 · Cited by 111
Zhang, L., Yu, C.-H., Guo, K.-P., Huang, C.-Z., & Mo, L. (2020) · BMC Immunology · doi:10.1186/s12865-020-00369-6 · Cited by 106
Boonmee, P., Ruangsomboon, O., Limsuwat, C., & Chakorn, T. (2020) · Western Journal of Emergency Medicine · doi:10.5811/westjem.2020.7.47405 · Cited by 97
Predictive analytics with ensemble modeling in laparoscopic surgery: A technical note
Zhang, Z., Chen, L., Xu, P., & Hong, Y. (2022) · Laparoscopic, Endoscopic and Robotic Surgery · doi:10.1016/j.lers.2021.12.003 · Cited by 92
Iron Deficiency and Red Cell Indices in Patients with Heart Failure
Tkaczyszyn, M., Colet, J. C., Voors, A. A., van Veldhuisen, D. J., Enjuanes, C., Moliner, P., Rozentryt, P., Poloński, L., Banasiak, W., Ponikowski, P. P., et al. (2017) · European Journal of Heart Failure · doi:10.1002/ejhf.820 · Cited by 90
Prognostic values of SOFA score, qSOFA score, and LODS score for patients with sepsis
Li, Y., Yan, C., Gan, Z., Xi, X., Tan, Z., Li, J., & Li, G. (2020) · Annals of Palliative Medicine · doi:10.21037/apm-20-984 · Cited by 81
Zhu, Y., Zhang, R., Ye, X., Liu, H., & Wei, J. (2021) · International Journal of Infectious Diseases · doi:10.1016/j.ijid.2021.11.015 · Cited by 75
Brakenridge, S. C., Efron, P. A., Stortz, J. A., Ozrazgat-Baslanti, T., Ghita, G. L., Wang, Z., Bihorac, A., Mohr, A. M., Brumback, B., Moldawer, L. L., et al. (2018) · The Journal of Trauma: Injury, Infection, and Critical Care · doi:10.1097/ta.0000000000001921 · Cited by 73
Song, J., Moon, S., Park, D. W., Cho, H., Kim, J. Y., Park, J.-H., & Cha, J. H. (2020) · Medicine · doi:10.1097/md.0000000000020495 · Cited by 67
García-Gallo, J. E., Fonseca-Ruiz, N. J., Celi, L. A., & Duitama-Muñoz, J. F. (2020) · Medicina Intensiva · doi:10.1016/j.medin.2018.07.016 · Cited by 55
Zhang, T., Liu, H., Wang, D., Zong, P., Guo, C., Wang, F., Wu, D., Tang, M., Zhou, J., & Zhao, Y. F. (2017) · Shock · doi:10.1097/shk.0000000000000982 · Cited by 45
Hu, T., Lv, H., & Jiang, Y. (2021) · Scientific Reports · doi:10.1038/s41598-021-90806-2 · Cited by 45
Oxygen Treatment in Intensive Care and Emergency Medicine
Grensemann, J., Fuhrmann, V., & Kluge, S. (2018) · Deutsches Ärzteblatt international · doi:10.3238/arztebl.2018.0455 · Cited by 44
Prediction of Sepsis and In-Hospital Mortality Using Electronic Health Records
Tansakul, V., Li, X., Koszalinski, R., Paiva, W., & Khojandi, A. (2018) · Methods of Information in Medicine · doi:10.3414/me18-01-0014 · Cited by 44
Sepsis in Older Adults in Long‐Term Care Facilities: Challenges in Diagnosis and Management
Yoshikawa, T. T., Reyes, B. J., & Ouslander, J. G. (2019) · Journal of the American Geriatrics Society · doi:10.1111/jgs.16194 · Cited by 44
He, Z., Du, L., Zhang, P., Zhao, R., Chen, X., & Fang, Z. (2020) · Critical Care Medicine · doi:10.1097/ccm.0000000000004644 · Cited by 39
Knaus, W. A., & Marks, R. D. (2019) · JAMA · doi:10.1001/jama.2019.5794 · Cited by 36
Early Prediction of Sepsis From Clinical Data Using Ratio and Power-Based Features
Nesaragi, N., & Patidar, S. (2020) · Critical Care Medicine · doi:10.1097/ccm.0000000000004691 · Cited by 36
Kwon, Y. S., & Baek, M. S. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9030875 · Cited by 34
Red cell distribution width in predicting 30-day mortality in patients with pulmonary embolism
Zhou, X., Chen, H., & Ni, S. (2016) · Journal of Critical Care · doi:10.1016/j.jcrc.2016.09.024 · Cited by 33
Falsetti, L., Martino, M., Zaccone, V., Viticchi, G., Raponi, A., Moroncini, G., Fioranelli, A., Pentima, C. D., Martini, A., Nitti, C., et al. (2020) · Infection · doi:10.1007/s15010-020-01494-5 · Cited by 23
Jia, L., Hao, L., Li, X., Jia, R., & Zhang, H. (2021) · Annals of Palliative Medicine · doi:10.21037/apm-20-1355 · Cited by 18
Hasegawa, D., Yamakawa, K., Nishida, K., Okada, N., Murao, S., & Nishida, O. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9072113 · Cited by 17
Towards real-time diagnosis for pediatric sepsis using graph neural network and ensemble methods.
Chen, X., Zhang, R.-T., & Tang, X.-Y. (2021) · PubMed · doi:10.26355/eurrev_202107_26380 · Cited by 11
Research works printed but not linked: 1
- Lundberg S. M. Lee S.-I. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 31st Conference on Neural Information Processing Systems (NIPS 2017) 2017 Long Beach, CA, USA 4765 4774
Cited by
Advances and Challenges in Sepsis Management: Modern Tools and Future Directions
Santacroce, E., D’Angerio, M., Ciobanu, A. L., Masini, L., Tartaro, D. L., Coloretti, I., Busani, S., Rubio, I., Meschiari, M., Franceschini, E., et al. (2024) · Cells · doi:10.3390/cells13050439 · Cited by 119
Clinical Sepsis Phenotypes in Critically Ill Patients
Παπαθανάκος, Γ., Andrianopoulos, I., Xenikakis, M., Papathanasiou, A. I., Koulenti, D., Blot, S. I., & Koulouras, V. P. (2023) · Microorganisms · doi:10.3390/microorganisms11092165 · Cited by 57
Caterson, J., Lewin, A., & Williamson, E. (2024) · Digital Health · doi:10.1177/20552076241272657 · Cited by 58
Sepsis subphenotypes: bridging the gaps in sepsis treatment strategies
Zhang, X., Zhang, W., Zhang, H., & Liao, X. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1546474 · Cited by 39
AI Advances in ICU with an Emphasis on Sepsis Prediction: An Overview
Stylianides, C., Nicolaou, A., Sulaiman, W. A., Alexandropoulou, C.-A., Panagiotopoulos, I., Karathanasopoulou, K., Dimitrakopoulos, G., Kleanthous, S., Politi, E., Ntalaperas, D., et al. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7010006 · Cited by 28
“For sepsis mortality prediction models, built-in feature importance [113,240–242], SHAP [240,241,243–246], LIME [127,245,247], Break Down [241], Ceteris Paribus [241], and INVASE [242] are the explainable AI techniques used in literature.”
Metadata
- Authors
- Ke, X., Zhang, F., Huang, G., & Wang, A.
- Affiliations
- Central South University (CN)
- Department of Emergency Medicine, Xiangya Hospital, Central South University, Changsha, 410000 Hunan, China
- Venue
- Computational and Mathematical Methods in Medicine
- Publisher
- Wiley
- Published
- 2022-12-15
- Volume
- 2022
- Pages
- 1-10
- ISSN
- 1748-670X (ISSN-L)
- 1748-6718
- PMC
- PMC9779998
- OpenAlex
- W4311731279
- Cited by
- 16
- References
- 43
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 6 · 2023: 2
- FWCI
- 2.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Computational and Mathematical Methods in Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Informationszentrum Lebenswissenschaften (ZB MED) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Natural Science Foundation of Hunan Province (2022JJ70165)
- Topics
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- sepsis, in-hospital mortality prediction, elderly patients, intensive care unit, model interpretability, SHAP, XGBoost, feature importance, clinical decision support, MIMIC-IV
- MeSH terms
- Machine Learning, Aged, Algorithms, Critical Care, Humans, 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.
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
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.