Machine learning models for mortality prediction in patients with spontaneous subarachnoid hemorrhage following ICU treatment

Aug 5, 2026

Spontaneous subarachnoid hemorrhage (SAH) is a severe, potentially life-threatening cerebrovascular condition in which early mortality risk identification is essential for improving prognosis and guiding ICU care. A retrospective cohort analysis used MIMIC-IV first-day ICU admission data to predict in-hospital mortality. Eight machine-learning models were trained with features selected via LASSO and evaluated using discrimination, calibration, and Brier-type metrics, with SHAP-based explainability for the best-performing model. Logistic regression showed superior predictive discrimination.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Methods

Data source and outcomes

Feature selection and model construction

Results

Conclusions

TYPE Original Research PUBLISHED 17 September 2025 DOI 10. 3389/fneur.2025.1648353 OPEN ACCESS EDITED BY Elisa Gouvêa Bogossian, Université Libre de Bruxelles, Belgium REVIEWED BY Michael Veldeman, RWTH Aachen University, Germany Elda Diletta Sterchele, Université Libre de Bruxelles, Belgium *CORRESPONDENCE Jing Zhang [zjsjzz@hbmu.edu.cn](zjsjzz@hbmu.edu.cn) RECEIVED 17 June 2025 ACCEPTED 27 August 2025 PUBLISHED 17 September 2025 CITATION Hu W, Yu D, Zhang L and Zhang J (2025) Machine learning models for mortality prediction in patients with spontaneous subarachnoid hemorrhage following ICU treatment. Front. Neurol. 16:1648353 . doi: 10.3389/fneur.2025.1648353 COPYRIGHT © 2025 Hu, Yu, Zhang and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning models for mortality prediction in patients with spontaneous subarachnoid hemorrhage following ICU treatment Wenwen Hu1 , Danfeng Yu1 , Liwen Zhang2 and Jing Zhang1* 1 Department of Neurological Intensive Care Unit, Taihe Hospital, Hubei University of Medicine, Shiyan, China, 2 Graduate School, Hubei University of Medicine, Shiyan, China Background: Spontaneous subarachnoid hemorrhage (SAH) is a severe and potentially life-threatening acute cerebrovascular disease. Early identiﬁcation of the risk of death in patients with spontaneous SAH is of vital importance for improving prognosis, reducing mortality, and guiding clinical treatment. Methods: A retrospective cohort study was conducted using the public database, Medical Information Mart for Intensive Care IV (MIMIC)-IV. The primary outcome was in-hospital mortality following intensive care unit (ICU) treatment. All features were extracted from ﬁrst-day ICU admission data. Data analysis was performed by using R and Python, with feature selection conducted via least absolute shrinkage and selection operator (LASSO) regression. We constructed 8 models based on the 12 selected features in the training set and evaluated them in the test set by various metrics, including area under the curve (AUC), accuracy, precision (positive prediction value), recall (sensitivity), Brier score, Jordan index, and calibration slope. The most effective model was rendered explainable through the SHapley Additive exPlanations (SHAP) approach. Results: The study included 1,121 records, with 870 surviving and 251 deceased patients. We selected 43 features for the preliminary baseline analysis. Based on LASSO regression analysis and clinical practical signiﬁcance, 12 features were ﬁnally included in the construction of the machine learning models. We constructed eight machine learning models, among which the logistic regression (LR) model performed the best. Conclusions: In our study, the LR model exhibited superior discrimination in predicting risk of mortality among patients with spontaneous SAH compared to other models. This research contributes to facilitating the early identiﬁcation of mortality risk in patients with spontaneous SAH. External validation and further prospective studies are warranted to conﬁrm and reﬁne these predictive insights for clinical utilization. KEYWORDS subarachnoid hemorrhage, intensive care unit, machine learning, predictive model, MIMIC-IV database 1 Introduction Subarachnoid Hemorrhage (SAH) is a critical public health concern, which remains a serious disease associated with considerable disability and mortality ( 1) . The incidence of SAH is approximately 9 cases per 100,000 individuals, and it is the third most prevalent subtype of stroke (2) . This disord

FAQs

What is the primary goal of the study?

To predict in-hospital mortality among patients with spontaneous SAH after ICU treatment using machine learning models trained on first-day admission data.

Which dataset and time window were used?

The study retrospectively used the MIMIC-IV database, extracting all features from the first-day ICU admission information.

How were the models evaluated and interpreted?

Models were assessed with metrics such as AUC, accuracy, precision, recall, Brier score, and calibration measures, and the best model was made explainable using SHAP.

Aug 5, 2026

Upload by Clementine