AUTHOR=Huang Jian , Jin Wanlin , Duan Xiangjie , Liu Xiaozhu , Shu Tingting , Fu Li , Deng Jiewen , Chen Huaqiao , Liu Guojing , Jiang Ying , Liu Ziru 

TITLE=Twenty-eight-day in-hospital mortality prediction for elderly patients with ischemic stroke in the intensive care unit: Interpretable machine learning models

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.1086339

DOI=10.3389/fpubh.2022.1086339

ISSN=2296-2565

ABSTRACT=Background: Risk stratification of elderly patients with ischemic stroke (IS) who are admitted to the ICU remains challenging. This study aims to establish and validate predictive models based on novel ML algorithms for 28-day in-hospital mortality in elderly patients with IS admitted to the ICU.
Methods: Data of elderly patients with IS were extracted from the eICU Collaborative Research Database (eICU-CRD) dataset between 2014 and 2015. All selected participants were randomly divided into two sets: training set and validation set in the ratio of  8:2. ML algorithms such as Naïve Bayes (NB) and eXtreme Gradient Boosting (xgboost) and logistic regression (LR) were applied for model construction by utilizing tenfold cross-validation. Performance was measured by area under receiver operating characteristic curve (AUC) analysis and accuracy. We used interpretable ML methods to provide insight into the model’s prediction and outcome using the SHAP (SHapley Additive exPlanations) method. 
Results: The analysis included 1236 elderly patients with IS in the ICU, of whom 164 (13.3%) died during hospitalization. Upon feature selection, a total of 8 variables were selected for model construction. In the training set, the xgboost, and NB models had a specificity of 0.681 and 0.595, respectively. The xgboost model identified patients who died with an AUC of 0.733 in the internal validation set, better than LR model identifying patients who died with AUC values with an AUC of 0.627 or other ML models.

Conclusion: The xgboost model has the best predictive performance that predicts mortality in elderly patients with IS in the ICU. By making the ML model explainable and Restricted cubic spline models, clinicians would be able to better understand the reasoning behind the outcome.