Machine Learning-Based Approaches for Prediction of Patients' Functional Outcome and Mortality after Spontaneous
Rui Guo1, Renjie Zhang1,2, Ran Liu3
1Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu 610041, China.
Insights
Machine learning models can predict outcomes for spontaneous intracerebral hemorrhage (SICH) patients. These models show promise in forecasting 90-day functional status and mortality, aiding clinical decision-making.
Area of Science:
- Neurology
- Medical Informatics
- Biostatistics
Background:
- Spontaneous intracerebral hemorrhage (SICH) presents significant morbidity and mortality, particularly in China.
- Accurate prediction of patient outcomes is crucial for effective management.
Purpose of the Study:
- To develop and evaluate machine learning (ML) models for predicting 90-day functional outcomes and mortality in SICH patients.
- To compare the efficacy of ML models against the traditional intracerebral hemorrhage (ICH) score.
Main Methods:
- Retrospective analysis of clinical, radiographic, and laboratory data from 751 SICH patients.
- Development and comparison of six ML-based predictive models.
- Evaluation of predictive performance using area under the receiver operating characteristic curves (AUC).
Main Results:
- Logistic regression (LR) and logistic regression CV (LRCV) achieved the highest AUC for functional outcome prediction (0.890 and 0.887).
- Category boosting demonstrated the best performance for mortality prediction (AUC = 0.841).
- ML models outperformed the traditional ICH score in predictive accuracy.
Conclusions:
- Machine learning models show significant potential in predicting the prognosis of spontaneous intracerebral hemorrhage.
- These ML tools could assist clinicians in forecasting patient outcomes and guiding treatment strategies.
Abstract:
Spontaneous intracerebral hemorrhage (SICH) has been common in China with high morbidity and mortality rates. This study aims to develop a machine learning (ML)-based predictive model for the 90-day evaluation after SICH. We retrospectively reviewed 751 patients with SICH diagnosis and analyzed clinical, radiographic, and laboratory data. A modified Rankin scale (mRS) of 0-2 was defined as a favorable functional outcome, while an mRS of 3-6 was defined as an unfavorable functional outcome. We evaluated 90-day functional outcome and mortality to develop six ML-based predictive models and compared their efficacy with a traditional risk stratification scale, the intracerebral hemorrhage (ICH) score. The predictive performance was evaluated by the areas under the receiver operating characteristic curves (AUC). A total of 553 patients (73.6%) reached the functional outcome at the 3rd month, with the 90-day mortality rate of 10.2%. Logistic regression (LR) and logistic regression CV (LRCV) showed the best predictive performance for functional outcome (AUC = 0.890 and 0.887, respectively), and category boosting presented the best predictive performance for the mortality (AUC = 0.841). Therefore, ML might be of potential assistance in the prediction of the prognosis of SICH.
