Prediction and risk assessment of sepsis-associated encephalopathy in ICU based on interpretable machine learning
Open accessAbstract
Sepsis-associated encephalopathy (SAE) is a major complication of sepsis and is associated with high mortality and poor long-term prognosis. The purpose of this study is to develop interpretable machine learning models to predict the occurrence of SAE after ICU admission and implement the individual prediction and analysis. Patients with sepsis admitted to ICU were included. SAE was diagnosed as glasgow coma score (GCS) less than 15. Statistical analysis at baseline was performed between SAE and non-SAE. Six machine learning classifiers were employed to predict the occurrence of SAE, and the adjustment of model super parameters was performed by using Bayesian optimization method. Finally, the optimal algorithm was selected according to the prediction efficiency. In addition, professional physicians were invited to evaluate our model prediction results for further quantitative assessment of the model interpretability. The preliminary analysis of variance showed significant differences in the incidence of SAE among patients with pathogen infection. There were significant differences in physical indicators like respiratory rate, temperature, SpO 2 and mean arterial pressure ( P < 0.001). In addition, the laboratory results were also significantly different. The optimal classification model (XGBoost) indicated that the best risk factors (cut-off points) were creatinine (1.1 mg/dl), mean respiratory rate (18), pH (7.38), age (72), chlorine (101 mmol/L), sodium (138.5 k/ul), SAPSII score (23), platelet count (160), and phosphorus (2.4 and 5.0 mg/dL). The ranked features derived from the best model (AUC is 0.8837) were mechanical ventilation, duration of mechanical ventilation, phosphorus, SOFA score, and vasopressin usage. The SAE risk prediction model based on XGBoost created here can make very accurate predictions using simple indicators and support the visual explanation. The interpretable model was effectively evaluated by professional physicians and can help them predict the occurrence of SAE more intuitively.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 lack of standardized metrics for assessing explainability across studies complicates the comparison of different approaches and limits the evaluation of their reliability in real-world ICU settings.
“Furthermore, while XAI methods offer valuable interpretability, the lack of standardized metrics for assessing explainability across studies complicates the comparison of different approaches and limits the evaluation of their reliability in real-world ICU settings ([2, 20]).”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [20]
The Introduction and Discussion say interpretability helps ICU clinicians understand model predictions. The paper does not establish that explainability metrics lack standardization across studies or that this impedes comparisons and real-world reliability assessments; its Discussion instead identifies limits of its own validation and interpretability analysis. (LLM, conf=0.82)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · see citing works
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× · see citing works
“Although there are a large number of machine learning models to predict sepsis in the retrospective cohorts, model prediction results need to be interpreted and the performance of the models is expected to improve 15 .”
BackgroundGinestra, J. C., Giannini, H. M., Schweickert, W. D., Meadows, L., Lynch, M. J., Pavan, K., Chivers, C. J., Draugelis, M., Donnelly, P. J., Fuchs, B. D., et al. (2019) · Critical Care Medicine · doi:10.1097/ccm.0000000000003803 · Cited by 159 · see citing works
Flagged first, then by citations
Research works printed but not linked: 20
- [1]Catarina AV Branchini G Bettoni L Sepsis-associated encephalopathy: From pathophysiology to progress in experimental studies Mol. Neurobiol. 2021 58 2770 2779 10.1007/s12035-021-02303-2 33495934 · DOI · Paper page
- [2]Czempik PF Pluta MP Krzych LJ Sepsis-associated brain dysfunction: A review of current literature Int. J. Environ. Res. Public Health 2020 17 5852 10.3390/ijerph17165852 32806705 PMC7460246 · DOI
- [3]Ren C Yao RQ Zhang H Sepsis-associated encephalopathy: A vicious cycle of immunosuppression J. Neuroinflamm. 2020 17 1 15 10.1186/s12974-020-1701-3 PMC6953314 31924221 · DOI · Paper page
- [4]Kikuchi DS Campos A Qu H Poldip2 mediates blood-brain barrier disruption in a model of sepsis-associated encephalopathy J. Neuroinflamm. 2019 16 1 12 10.1186/s12974-019-1575-4 PMC6883676 31779628 · DOI
- [5]Mazeraud A Righy C Bouchereau E Septic-associated encephalopathy: A comprehensive review Neurotherapeutics 2020 17 392 403 10.1007/s13311-020-00862-1 32378026 PMC7283452 · DOI
- [6]Molnar L Fulesdi B Nemeth N Sepsis-associated encephalopathy: A review of literature Neurol. India 2018 66 352 361 10.4103/0028-3886.227299 29547154 · DOI
- [7]Rosenblatt K Walker KA Goodson C Cerebral autoregulation-guided optimal blood pressure in sepsis-associated encephalopathy: A case series J. Intensive Care Med. 2020 35 1453 1464 10.1177/0885066619828293 30760173 PMC6692246 · DOI
- [8]Esen F Orhun G Ozcan PE Diagnosing acute brain dysfunction due to sepsis Neurol. Sci. 2020 41 25 33 10.1007/s10072-019-04069-x 31520167 · DOI
- [10]Yamaga S Shime N Sonneville R Risk factors for sepsis-associated encephalopathy Intensive Care Med. 2017 43 1548 1549 10.1007/s00134-017-4875-0 28664452 · DOI
- [11]Chen J Shi X Diao M A retrospective study of sepsis-associated encephalopathy: Epidemiology, clinical features and adverse outcomes BMC Emerg. Med. 2020 20 77 10.1186/s12873-020-00374-3 33023479 PMC7539509 · DOI
- [12]Sonneville R de Montmollin E Poujade J Potentially modifiable factors contributing to sepsis-associated encephalopathy Intensive Care Med. 2017 43 1075 1084 10.1007/s00134-017-4807-z 28466149 · DOI · Paper page
- [14]Yang Y Liang S Geng J Development of a nomogram to predict 30-day mortality of patients with sepsis-associated encephalopathy: A retrospective cohort study J. Intensive Care 2020 8 45 10.1186/s40560-020-00459-y 32637121 PMC7331133 · DOI
- [17]Hu R Andreas J Darrell T Explainable Neural Computation Via Stack Neural Module Networks 2018 Springer
- [18]Schweingruber N Mader M Wiehe A A recurrent machine learning model predicts intracranial hypertension in neurointensive care patients Brain 2022 145 2910 10.1093/brain/awab453 35139181 PMC9486888 · DOI
- [19]Hu XY Liu H Zhao X Automated machine learning-based model predicts postoperative delirium using readily extractable perioperative collected electronic data CNS Neurosci. Ther. 2022 28 608 618 10.1111/cns.13758 34792857 PMC8928919 · DOI
- [20]Goldberger AL Amaral LA Glass L PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals Circulation 2000 101 E215 E220 10.1161/01.CIR.101.23.e215 10851218 · DOI · Paper page
- [22]Zhang Z Multiple imputation with multivariate imputation by chained equation (MICE) package Ann. Transl. Med. 2016 4 30 26889483 PMC4731595
- [24]Johnson, A., Pollard, T. J., & Shen, L., et al. MIMIC-III, a freely accessible critical care database. Scientific Data. PMC4878278 27219127
- [25]Seymour CW Liu VX Iwashyna TJ Assessment of clinical criteria for sepsis for the third international consensus definitions for sepsis and septic shock (Sepsis-3) JAMA, J. Am. Med. Assoc. 2016 315 762 774 10.1001/jama.2016.0288 PMC5433435 26903335 · DOI · Paper page
- [26]Zhao T Xia Y Wang D Association between elevated serum tau protein level and sepsis-associated encephalopathy in patients with severe sepsis Can. J. Infect. Dis. Med. Microbiol. 2019 2019 1 6 10.1155/2019/1876174 PMC6664571 31396296 · DOI
Cited by
Sorted by citations
Athukorala, V. S., & Ilmini, W. M. K. S. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03344-0 · Cited by 10 · see citing works
“In the Outcomes domain, most studies (e.g. [14, 17, 20]), maintained a low risk of bias, with clearly defined and consistently measured outcomes such as sepsis onset, ICU mortality, or readmission events.”
InfluentialHe, T. T., Jiao, T. Q., & An, X. M. (2026) · PeerJ · doi:10.7717/peerj.20770 · Cited by 2 · see citing works
- Authors
- Lu, X., Kang, H., Zhou, D., & Li, Q.
- Affiliations
- Beijing Institute of Technology (CN)
- Beijing Tongren Hospital (CN)
- Corresponding author
- Zhou, Dawei
- Li, Qin
- Venue
- Scientific Reports
- Published
- 2022-12-31
- Volume
- 12
- Issue
- 1
- Pages
- 22621-22621
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC9805434
- OpenAlex
- W4313397298
- Cited by
- 31
- References
- 3
- Citations by year
- 2026: 7 · 2025: 11 · 2024: 7 · 2023: 6
- FWCI
- 4.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Shandong Provincial Key Research and Development Program Major Scientific and Technological Innovation Project (no. 2019JZZY011016)
- Topics
- Health Sciences › Medicine › Epidemiology › 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-associated encephalopathy, sepsis, intensive care unit, risk prediction, model interpretability, XGBoost, Bayesian optimization, clinical risk factors, Glasgow Coma Scale, mechanical ventilation, SOFA score, vasopressor use, phosphorus
- MeSH terms
- Machine Learning, Bayes Theorem, Humans, Intensive Care Units, Prognosis, Retrospective Studies, ROC Curve, Risk Assessment, Sepsis, Sepsis-Associated Encephalopathy
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
