Enhancing Cardiac Arrest Prediction in Critically Ill Patients: A Sequence-Based Embedding Approach with Mamba

Gim, Ukdong; Shin, Yunseob; Yoo, Dongjoon; Cho, Kyungjae; Lee, Hyung-chul; Lim, Leerang A.M.; Cho, Woo-hyun

doi:10.3233/SHTI251205

상세 보기

Enhancing Cardiac Arrest Prediction in Critically Ill Patients: A Sequence-Based Embedding Approach with Mamba

Gim, Ukdong;
Shin, Yunseob;
Yoo, Dongjoon;
Cho, Kyungjae;
Lee, Hyung-chul;
외 2명

Citations

SCOPUS

0

초록

We developed a novel model for cardiac arrest prediction using ICU data from SNUH and externally validated it on PNUYH. Our sequence-based embedding approach with a Mamba encoder outperformed NEWS and LightGBM, achieving AUROC 0.957 (internal) and 0.889 (external). This study highlights the potential of the proposed model as a robust and generalizable tool for early ICU intervention. © 2025 The Authors.

키워드

cardiac arrest; Intensive care unit; predictive model; validation study

제목: Enhancing Cardiac Arrest Prediction in Critically Ill Patients: A Sequence-Based Embedding Approach with Mamba

저자: Gim, Ukdong; Shin, Yunseob; Yoo, Dongjoon; Cho, Kyungjae; Lee, Hyung-chul; Lim, Leerang A.M.; Cho, Woo-hyun

DOI: 10.3233/SHTI251205

발행일: 2025-08

유형: Conference paper

저널명: Studies in Health Technology and Informatics

권: 329

페이지: 1768 ~ 1769