Saved in:
Bibliographic Details
Main Authors: Cheng, Yuxiao, Song, Xinxin, Wang, Ziqian, Zhong, Qin, He, Kunlun, Suo, Jinli
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.02109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916597191409664
author Cheng, Yuxiao
Song, Xinxin
Wang, Ziqian
Zhong, Qin
He, Kunlun
Suo, Jinli
author_facet Cheng, Yuxiao
Song, Xinxin
Wang, Ziqian
Zhong, Qin
He, Kunlun
Suo, Jinli
contents Recent advances in deep learning (DL) have prompted the development of high-performing early warning score (EWS) systems, predicting clinical deteriorations such as acute kidney injury, acute myocardial infarction, or circulatory failure. DL models have proven to be powerful tools for various tasks but come with the cost of lacking interpretability and limited generalizability, hindering their clinical applications. To develop a practical EWS system applicable to various outcomes, we propose causally-informed explainable early prediction model, which leverages causal discovery to identify the underlying causal relationships of prediction and thus owns two unique advantages: demonstrating the explicit interpretation of the prediction while exhibiting decent performance when applied to unfamiliar environments. Benefiting from these features, our approach achieves superior accuracy for 6 different critical deteriorations and achieves better generalizability across different patient groups, compared to various baseline algorithms. Besides, we provide explicit causal pathways to serve as references for assistant clinical diagnosis and potential interventions. The proposed approach enhances the practical application of deep learning in various medical scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care
Cheng, Yuxiao
Song, Xinxin
Wang, Ziqian
Zhong, Qin
He, Kunlun
Suo, Jinli
Machine Learning
Artificial Intelligence
Recent advances in deep learning (DL) have prompted the development of high-performing early warning score (EWS) systems, predicting clinical deteriorations such as acute kidney injury, acute myocardial infarction, or circulatory failure. DL models have proven to be powerful tools for various tasks but come with the cost of lacking interpretability and limited generalizability, hindering their clinical applications. To develop a practical EWS system applicable to various outcomes, we propose causally-informed explainable early prediction model, which leverages causal discovery to identify the underlying causal relationships of prediction and thus owns two unique advantages: demonstrating the explicit interpretation of the prediction while exhibiting decent performance when applied to unfamiliar environments. Benefiting from these features, our approach achieves superior accuracy for 6 different critical deteriorations and achieves better generalizability across different patient groups, compared to various baseline algorithms. Besides, we provide explicit causal pathways to serve as references for assistant clinical diagnosis and potential interventions. The proposed approach enhances the practical application of deep learning in various medical scenarios.
title Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.02109