https://www.ncbi.nlm.nih.gov/pubmed/29945914
An Algorithm Based on Deep Learning for Predicting In-Hospital Cardiac Arrest.
Author information
- 1
- Department of Emergency Medicine, Mediplex Sejong Hospital, Incheon, Korea kwonjm@sejongh.co.kr.
- 2
- VUNO, Seoul, Korea.
- 3
- Department of Cardiology, Mediplex Sejong Hospital, Incheon, Korea.
Abstract
BACKGROUND:
In-hospital cardiac arrest is a major burden to public health, which affects patient safety. Although traditional track-and-trigger systems are used to predict cardiac arrest early, they have limitations, with low sensitivity and high false-alarm rates. We propose a deeplearning-based early warning system that shows higher performance than the existing track-and-trigger systems.
METHODS AND RESULTS:
This retrospective cohort study reviewed patients who were admitted to 2 hospitals from June 2010 to July 2017. A total of 52 131 patients were included. Specifically, a recurrent neural network was trained using data from June 2010 to January 2017. The result was tested using the data from February to July 2017. The primary outcome was cardiac arrest, and the secondary outcome was death without attempted resuscitation. As comparative measures, we used the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and the net reclassification index. Furthermore, we evaluated sensitivity while varying the number of alarms. The deep learning-based early warning system (AUROC: 0.850; AUPRC: 0.044) significantly outperformed a modified earlywarning score (AUROC: 0.603; AUPRC: 0.003), a random forest algorithm (AUROC: 0.780; AUPRC: 0.014), and logistic regression (AUROC: 0.613; AUPRC: 0.007). Furthermore, the deep learning-based early warning system reduced the number of alarms by 82.2%, 13.5%, and 42.1% compared with the modified early warning system, random forest, and logistic regression, respectively, at the same sensitivity.
CONCLUSIONS:
An algorithm based on deep learning had high sensitivity and a low false-alarm rate for detection of patients with cardiac arrest in the multicenter study.
© 2018 The Authors. Published on behalf of the American Heart Association, Inc., by Wiley.
KEYWORDS:
artificial intelligence; cardiac arrest; deep learning; machine learning; rapid response system; resuscitation
- PMID:
- 29945914
- DOI:
- 10.1161/JAHA.118.008678
JAHA
세종병원, VUNO. 세종 메디플렉스 응급의학과
병원내 심정지 예측
2개 병원, 52000명 학습데이터.
RNN
딥러닝 기반의 경고시스템 AUROC : 0.850 ( DEWS)
기존의 경고 시스템 AUROC : 0.603
랜덤 포레스트 AUROC : 0.78
로지스틱 회귀 AUROC : 0.61
4개의 vital sign 을 사용. (sBP, HR, RR, BT)
심정지 14시간전에 경고 날림 (50% 이상에서)
비효율적인 false 알람을 41.6% 감소
임상적인 변수 활용이 떨어져 보임. (ABGA, lactic acidosis, EKG, clinical underlying datt 활용이 없음.)
하지만 4가지 V/S 만으로도, 예측정확도가 높다면, 상당히 고무적임.
DOI : 10.1161/JAHA.118.008678
2018 JAHA An Algorithm Based on Deep Learning for Predicting In-Hospital cardiac arrest.pdf
