Background: Using deep learning for disease outcome prediction is an
approach that has made large advances in recent years. Notwithstanding its
excellent performance, clinicians are also interested in learning how input
affects prediction. Clinical validation of explainable deep learning models is
also as yet unexplored. This study aims to evaluate the performance of Deep
SHapley Additive exPlanations (D-SHAP) model in accurately identifying the
diagnosis code associated with the highest mortality risk. Methods:
Incidences of at least one in-hospital cardiac arrest (IHCA) for 168,693 patients
as well as 1,569,478 clinical records were extracted from Taiwan’s National
Health Insurance Research Database. We propose a D-SHAP model to provide insights
into deep learning model predictions. We trained a deep learning model to predict
the 30-day mortality likelihoods of IHCA patients and used D-SHAP to see how the
diagnosis codes affected the model’s predictions. Physicians were asked to
annotate a cardiac arrest dataset and provide expert opinions, which we used to
validate our proposed method. A 1-to-4-point annotation of each record (current
decision) along with four previous records (historical decision) was used to
validate the current and historical D-SHAP values. Results: A subset
consisting of 402 patients with at least one cardiac arrest record was randomly
selected from the IHCA cohort. The median age was 72 years, with mean and
standard deviation of 69
Announcements
Open Access
Original Research
Clinical Validation of Explainable Deep Learning Model for Predicting the Mortality of In-Hospital Cardiac Arrest Using Diagnosis Codes of Electronic Health Records
Chien-Yu Chi1, Hadi Moghadas-Dastjerdi2, Adrian Winkler2, Shuang Ao2, Yen-Pin Chen3, Liang-Wei Wang3, Pei-I Su3, Wei-Shu Lin3, Min-Shan Tsai3, Chien-Hua Huang3,*
Show Less
1
Department of Emergency Medicine, National Taiwan University Hospital Yunlin Branch, 640 Yunlin, Taiwan
2
Knowtions Research Inc., Toronto, Ontario M5J 2S1, Canada
3
Department of Emergency Medicine, National Taiwan University, 100 Taipei, Taiwan
*Correspondence: chhuang5940@ntu.edu.tw (Chien-Hua Huang)
Rev. Cardiovasc. Med. 2023, 24(9), 265;
https://doi.org/10.31083/j.rcm2409265
Submitted: 20 March 2023 | Revised: 12 June 2023 | Accepted: 26 June 2023 | Published: 21 September 2023
(This article belongs to the Section Cardiovascular Quality and Outcomes)
Copyright: © 2023 The Author(s). Published by IMR Press.
This is an open access article under the CC BY 4.0 license.
Abstract
Keywords
in-hospital cardiac arrest
artificial intelligence
explainable deep learning model
SHAP
electronic health record
Funding
109-2634-F-002-031/Ministry of Science and Technology, Taiwan
Figures
Fig. 1.