AUTHOR=Fang Gang , Huang Zhennan , Wang Zhongrui 

TITLE=Predicting Ischemic Stroke Outcome Using Deep Learning Approaches

JOURNAL=Frontiers in Genetics

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2021.827522

DOI=10.3389/fgene.2021.827522

ISSN=1664-8021

ABSTRACT=Predicting functional outcomes after an Ischemic Stroke (IS) is highly valuable for patients and desirable for clinicians. This allows clinicians to set reasonable goals for patients and cooperate with patients and relatives effectively, furthermore to reach shared after-care decisions for recovery and make exercise plan to facilitate rehabilitation. The aim of this study was to apply various Deep learning (DL) approaches for 6-month stroke outcome predictions, using openly accessible International Stroke Trial (IST) dataset. Furthermore, another objective of this study is to compare performance of various DL approaches with Machine learning (ML) for clinical prediction modeling. After comparing various ML methods (Deep Forest, Random Forest, Support Vector Machine, etc.) with current DL frameworks (CNN, LSTM, Resnet), there are no evidence of superior performance of DL over ML. Improvements in methodology and reporting are needed for studies that compare modeling algorithms.