Open AccessInterpretable disease prediction using heterogeneous patient records with self-attentive fusion encoder
Author(s) -
Heeyoung Kwak,
Jooyoung Chang,
Byeongjin Choe,
Sang Min Park,
Kyomin Jung
Publication year - 2021
Publication title -
journal of the american medical informatics association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.614
H-Index - 150
eISSN - 1527-974X
pISSN - 1067-5027
DOI - 10.1093/jamia/ocab109
Subject(s) - computer science , artificial intelligence , concatenation (mathematics) , machine learning , health records , medical record , recurrent neural network , inference , population , sample (material) , disease , deep learning , autoencoder , artificial neural network , data mining , health care , medicine , mathematics , chemistry , environmental health , chromatography , combinatorics , pathology , economics , radiology , economic growth
We propose an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder. We assessed the model performance in predicting cardiovascular disease events, given the records of a general patient population.