Predicting one-year mortality risk in ICU patients with ischemic stroke using multi-algorithm machine learning and a
Jian Huang1, Yalin Dong2, Xiaozhu Liu3
1Department of Ultrasound, Sir Run Run Shaw Hospital, Zhejiang University College of Medicine, Hangzhou, China.
Insights
A new nomogram predicts one-year mortality risk in intensive care unit (ICU) patients with ischemic stroke. This tool integrates key clinical factors, outperforming existing scoring systems for better risk stratification.
Area of Science:
- Neurology
- Critical Care Medicine
- Biostatistics
Background:
- Ischemic stroke is a major cause of death.
- Patients admitted to the intensive care unit (ICU) after ischemic stroke have a poor prognosis.
- Accurate risk stratification is crucial for managing these high-risk patients.
Purpose of the Study:
- To develop and validate a predictive model for estimating one-year mortality risk in ICU-admitted ischemic stroke patients.
- To create a practical tool for clinical use in risk stratification.
Main Methods:
- Retrospective cohort study using the MIMIC-IV database (1974 patients).
- Data split into training (80%) and test (20%) sets.
- Machine learning algorithms used for feature selection, followed by multivariate logistic regression and nomogram construction.
- Model performance evaluated using discrimination, calibration, and clinical utility metrics, compared against established scoring systems.
Main Results:
- A nomogram was developed incorporating nine predictors: age, heart rate, weight, glucose, anion gap, calcium, alkaline phosphatase (ALP), red cell distribution width (RDW), and mean corpuscular hemoglobin concentration (MCHC).
- The model achieved an AUC of 0.739 in the training set and 0.737 in the test set.
- The nomogram demonstrated good calibration, favorable clinical net benefit, and superior discriminatory ability compared to SOFA, SAPS II, LODS, OASIS, and GCS scores.
Conclusions:
- A validated, practical nomogram effectively predicts one-year mortality risk in ICU patients with ischemic stroke.
- The nomogram integrates key clinical variables for robust risk stratification.
- This tool has potential clinical utility for improving patient management and outcomes.
Abstract:
Introduction: Ischemic stroke is a leading cause of mortality, and patients requiring intensive care unit (ICU) admission carry a guarded prognosis. We aimed to develop and validate a predictive model for estimating one-year mortality risk in ICU-admitted ischemic stroke patients.MethodsIn this retrospective cohort study, data from 1974 ischemic stroke patients were extracted from the MIMIC-IV database. Patients were randomly allocated into a training set (n = 1582) and a test set (n = 392) in an 8:2 ratio. Five machine learning algorithms (CART, RF, SVM, GBM, and NB) were employed for initial feature screening. Key predictors were subsequently integrated into a multivariate logistic regression model, which was visualized as a nomogram. The model's performance was evaluated using discrimination, calibration, and clinical utility metrics and was compared against established severity scores (SOFA, SAPS II, LODS, OASIS, GCS).ResultsThe final nomogram incorporated nine predictors: age, heart rate, weight, glucose, anion gap, calcium, alkaline phosphatase (ALP), red cell distribution width (RDW), and mean corpuscular hemoglobin concentration (MCHC). The model demonstrated an AUC of 0.739 (95% CI: 0.715-0.764) in the training set and 0.737 (95% CI: 0.688-0.786) in the test set. Calibration curves indicated good agreement between predictions and observations. Decision curve and clinical impact curve analyses confirmed the nomogram's favorable clinical net benefit, and it outperformed all comparator scoring systems in discriminatory ability.ConclusionsWe developed and validated a practical nomogram that effectively integrates key clinical variables to predict one-year mortality risk in ICU patients with ischemic stroke. This tool demonstrates robust performance and potential clinical utility for risk stratification.
