CoChat

Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission

Open access
Hu, Chang, Li, Lu, Li, Yiming, Wang, Fengyun, Hu, Bo, Peng, Zhiyong · 2022 · Infectious Diseases and Therapy

The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.

Abstract

INTRODUCTION: Septic patients requiring intensive care unit (ICU) readmission are at high risk of mortality, but research focusing on the association of ICU readmission due to sepsis and mortality is limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting in-hospital mortality in septic patients readmitted to the ICU using routinely available clinical data. METHODS: The data used in this study were obtained from the Medical Information Mart for Intensive Care (MIMIC-IV, v1.0) database, between 2008 and 2019. The study cohort included patients with sepsis requiring ICU readmission. The data were randomly split into a training (75%) data set and a validation (25%) data set. Nine popular ML models were developed to predict mortality in septic patients readmitted to the ICU. The model with the best accuracy and area under the curve (A.C.) in the validation cohort was defined as the optimal model and was selected for further prediction studies. The SHAPELY Additive explanations (SHAP) values and Local Interpretable Model-Agnostic Explanation (LIME) methods were used to improve the interpretability of the optimal model. RESULTS: A total of 1117 septic patients who had required ICU readmission during the study period were enrolled in the study. Of these participants, 434 (38.9%) were female, and the median (interquartile range [IQR]) age was 68.6 (58.4-79.2) years. The median (IQR) ICU interval duration was 2.60 (0.64-5.78) days. After feature selection, 31 of 47 clinical factors were ultimately chosen for use in model construction. Of the nine ML models tested, the best performance was achieved with the random forest (RF) model, with an A.C. of 0.81, an accuracy of 85% and a precision of 62% in the validation cohort. The SHAP summary analysis revealed that Glasgow Coma Scale score, urine output, blood urea nitrogen, lactate, platelet count and systolic blood pressure were the top six most important factors contributing to the RF model. Additionally, the LIME method demonstrated how the RF model works in terms of explaining risk of death prediction in septic patients requiring ICU readmission. CONCLUSION: The ML models reported here showed a good prognostic prediction ability in septic patients requiring ICU readmission. Of the features selected, the parameters related to organ perfusion made the largest contribution to outcome prediction during ICU readmission in septic patients.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s40121-022-00671-3

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Flow diagram of this study. MIMIC-IV Medical Information Mart for Intensive Care IV, XGBoost eXtreme Gradient Boosting, AdaBoost Adaptive Boosting
Fig. 1 Flow diagram of this study. MIMIC-IV Medical Information Mart for Intensive Care IV, XGBoost eXtreme Gradient Boosting, AdaBoost Adaptive BoostingCC BY-NC · PubMed Central
Fig. 2 Area under the receiver operator curve (ROC) and confusion matrix for each machine learning–based model to estimate mortality in the validation set. a ROC curves for the nine machine-learning models to predict in-hospital mortality, b confusion matrix for each machine learning–based model to estimate in-hospital mortality. AdaBoost adaptive boosting
Fig. 2 Area under the receiver operator curve (ROC) and confusion matrix for each machine learning–based model to estimate mortality in the validation set. a ROC curves for the nine machine-learning models to predict in-hospital mortality, b confusion matrix for each machine learning–based model to estimate in-hospital mortality. AdaBoost adaptive boostingCC BY-NC · PubMed Central
Fig. 3 Feature importance assessment for RF classifier using SHAP values in the validation set. Each dot represents 1 patient and accumulates vertically to depict the density. The color reflects the high and low values of each feature, with deep color indicating a higher value and light color indicating a lower value. The X-axis of the graph represents the SHAP value, and a positive SHAP value indicates that it contributes positively to predicting the model and that the probability of mortality occurring is high, and vice versa. SHAP SHAPELY Additive explanation, RF Random Forest, GCS Glasgow Coma Scale, BUN blood urea nitrogen, SBP systolic blood pressure, MAP mean arterial pressure, ALP alkaline phosphatase, DBP diastolic blood pressure, PTT partial thromboplastin time, PO2 partial pressure of oxygen, PaO2/FiO2 ratio of arterial oxygen partial pressure to fractional inspired oxygen
Fig. 3 Feature importance assessment for RF classifier using SHAP values in the validation set. Each dot represents 1 patient and accumulates vertically to depict the density. The color reflects the high and low values of each feature, with deep color indicating a higher value and light color indicating a lower value. The X-axis of the graph represents the SHAP value, and a positive SHAP value indicates that it contributes positively to predicting the model and that the probability of mortality occurring is high, and vice versa. SHAP SHAPELY Additive explanation, RF Random Forest, GCS Glasgow Coma Scale, BUN blood urea nitrogen, SBP systolic blood pressure, MAP mean arterial pressure, ALP alkaline phosphatase, DBP diastolic blood pressure, PTT partial thromboplastin time, PO2 partial pressure of oxygen, PaO2/FiO2 ratio of arterial oxygen partial pressure to fractional inspired oxygenCC BY-NC · PubMed Central
Fig. 4 SHAP dependence plot of the top 6 clinical features in the RF classifier. a GCS, b urine output, c BUN, d lactate, e platelet, f SBP. Values are plotted with a scatter plot. A feature has an impact on mortality when its SHAP value is > 0, and it has an impact on the patient’s survival when its SHAP value is < than 0. GCS Glasgow Coma Scale, BUN blood urea nitrogen, SBP systolic blood pressure, SHAP SHapley Additive explanation, RF Random Forest
Fig. 4 SHAP dependence plot of the top 6 clinical features in the RF classifier. a GCS, b urine output, c BUN, d lactate, e platelet, f SBP. Values are plotted with a scatter plot. A feature has an impact on mortality when its SHAP value is > 0, and it has an impact on the patient’s survival when its SHAP value is < than 0. GCS Glasgow Coma Scale, BUN blood urea nitrogen, SBP systolic blood pressure, SHAP SHapley Additive explanation, RF Random ForestCC BY-NC · PubMed Central
Fig. 5 Results of local interpretable model-agnostic explanations (LIME) for top 5 clinical features using RF classifier applied to the 4 patients in the validation set. Visualization of 4 individual patients for the explanation risk of death prediction, with blue denoting the negative case and orange denoting the positive case. GCS Glasgow Coma Scale, BUN blood urea nitrogen, PTT partial thromboplastin time, ALP alkaline phosphatase, MAP mean arterial pressure, RF Random Forest, LIME local interpretable model-agnostic explanations
Fig. 5 Results of local interpretable model-agnostic explanations (LIME) for top 5 clinical features using RF classifier applied to the 4 patients in the validation set. Visualization of 4 individual patients for the explanation risk of death prediction, with blue denoting the negative case and orange denoting the positive case. GCS Glasgow Coma Scale, BUN blood urea nitrogen, PTT partial thromboplastin time, ALP alkaline phosphatase, MAP mean arterial pressure, RF Random Forest, LIME local interpretable model-agnostic explanationsCC BY-NC · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 50 references

Cited by

See all 63

Metadata

Authors
Hu, C., Li, L., Li, Y., Wang, F., Hu, B., & Peng, Z.
Affiliations
Zhongnan Hospital of Wuhan University (CN)
Corresponding author
  • Hu, Bo
  • Peng, Zhiyong
Venue
Infectious Diseases and Therapy
Published
2022-07-14
Volume
11
Issue
4
Pages
1695-1713
ISSN
  • 2193-6382 (ISSN-L)
  • 2193-8229
OpenAlex
W4285388690
Cited by
63
References
49
Citations by year
2026: 13 · 2025: 16 · 2024: 21 · 2023: 13
FWCI
9.02
Type
journal article
Language
en
Open access
Licence
Locations
  • Infectious Diseases and Therapy (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
Funders
  • National Natural Science Foundation of China (81772046, 81971816)
  • Special Project for Significant New Drug Research and Development in the Major National Science and Technology Projects of China (2020ZX09201007)
  • Subject Cultivation Project of Zhongnan Hospital of Wuhan University (ZNXKPY2021001, ZNXKPY2021002)
  • Translational Medicine and Interdisciplinary Research Joint Fund of Zhongnan Hospital of Wuhan University (ZNJC202011)
  • the Open Project Program of the Jiangsu Provincial Key Laboratory of Critical Care Medicine (JSKLCCM-2021-02-003)
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, ICU readmission, mortality prediction, explainable machine learning, SHAP, lime, random forest, prognostic factors, Glasgow Coma Scale, lactate, urine output, MIMIC-IV, intensive care unit patients, clinical decision support, risk stratification, sepsis severity scoring systems, sepsis mortality

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

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 Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission. https://app.cochat.ai/papers/10.1007/s40121-022-00671-3
The paper
Hu, C., Li, L., Li, Y., Wang, F., Hu, B., & Peng, Z. (2022). Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission. Infectious Diseases and Therapy. https://doi.org/10.1007/s40121-022-00671-3

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.