%0 Journal Article
%@ 2291-9694
%I JMIR Publications
%V 10
%N 2
%P e27936
%T Development of Deep Learning Models for Predicting In-Hospital Mortality Using an Administrative Claims Database: Retrospective Cohort Study
%A Matsui,Hiroki
%A Yamana,Hayato
%A Fushimi,Kiyohide
%A Yasunaga,Hideo
%+ Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 1130033, Japan, 81 3 5841 1887, ptmatsui-tky@umin.ac.jp
%K prognostic model
%K deep learning
%K real-world data
%K acute care
%K claims data
%K myocardial infarction
%K heart failure
%K stroke
%K pneumonia
%D 2022
%7 11.2.2022
%9 Original Paper
%J JMIR Med Inform
%G English
%X Background: Administrative claims databases have been used widely in studies because they have large sample sizes and are easily available. However, studies using administrative databases lack information on disease severity, so a risk adjustment method needs to be developed. Objective: We aimed to develop and validate deep learning–based prediction models for in-hospital mortality of acute care patients. Methods: The main model was developed using only administrative claims data (age, sex, diagnoses, and procedures on the day of admission). We also constructed disease-specific models for acute myocardial infarction, heart failure, stroke, and pneumonia using common severity indices for these diseases. Using the Japanese Diagnosis Procedure Combination data from July 2010 to March 2017, we identified 46,665,933 inpatients and divided them into derivation and validation cohorts in a ratio of 95:5. The main model was developed using a 9-layer deep neural network with 4 hidden dense layers that had 1000 nodes and were fully connected to adjacent layers. We evaluated model discrimination ability by an area under the receiver operating characteristic curve (AUC) and calibration ability by calibration plot. Results: Among the eligible patients, 2,005,035 (4.3%) died. Discrimination and calibration of the models were satisfactory. The AUC of the main model in the validation cohort was 0.954 (95% CI 0.954-0.955). The main model had higher discrimination ability than the disease-specific models. Conclusions: Our deep learning–based model using diagnoses and procedures produced valid predictions of in-hospital mortality. 
%M 34997958
%R 10.2196/27936
%U https://medinform.jmir.org/2022/2/e27936
%U https://doi.org/10.2196/27936
%U http://www.ncbi.nlm.nih.gov/pubmed/34997958