AUTHOR=Deng Jiewen , He Zhaohui 

TITLE=Characterizing Risk of In-Hospital Mortality Following Subarachnoid Hemorrhage Using Machine Learning: A Retrospective Study

JOURNAL=Frontiers in Surgery

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/surgery/articles/10.3389/fsurg.2022.891984

DOI=10.3389/fsurg.2022.891984

ISSN=2296-875X

ABSTRACT=Background Subarachnoid hemorrhage has a high rate of disability and mortality, and the ability to use existing disease severity scores to estimate the risk of adverse outcome is limited. Using in-hospital data available to develop more accurate risk prediction models, using logistic regression (LR) and machine learning (ML) technologies, combined with biochemical information.
Methods Patient-level data were extracted from MIMIC-IV data. The primary outcome was in-hospital mortality. The models were trained and tested on a dataset (split 70:30) including age and key past medical history. The Recursive feature elimination (RFE) algorithm is used to screen the characteristic variables, then the ML algorithm is used to analyze and establish the prediction model, and the validation set is used to further to verify the effectiveness of the model.
Result Of the 1787 patients included in the mimic database, a total of 379 died during hospitalization. Recursive feature abstraction (RFE) selected 20 variables. After simplification, we determine the features as 10, including GCS score, glucose, sodium, chloride, spo2, bicarbonate, temperature, white blood cell (wbc), use heparin and sofa score. The validation set and Delong test show that the simplified RF model has a high AUC of 0.949, which is not significantly different from the best model. Furthermore, in the DCA curve, the simplified GBM model has relatively higher net benefits. In the subgroup analysis of non-traumatic subarachnoid hemorrhage, the simplified GBM model has a high AUC of 0.955 and has relatively higher net benefits.
Conclusions ML approaches significantly enhance predictive discrimination for mortality following subarachnoid hemorrhage compared to existing illness severity scores and LR. The discriminative ability of these ML models requires validation in external cohorts to establish generalizability.