id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-184194-zdxebonv	Chen, Lichin	Using Deep Learning and Explainable Artificial Intelligence in Patients' Choices of Hospital Levels	2020-06-24		.txt	text/plain	4915	270	47	This study used nationwide insurance data, accumulated possible features discussed in existing literature, and used a deep neural network to predict the patients choices of hospital levels. Focusing on the hospital levels of the patients' choices, this study used explainable artificial intelligence (XAI) methods to interpret the effecting features for the general public and individuals. According to a public opinion poll conducted in 2019 [35] , although 85.3% of the respondents agreed that for a mild condition the patient should go to the primary care service nearby instead of tertiary hospitals, 70% considered institutes with higher levels to possess better professional skills, and 49% expressed having confidence in determining the severity of their own condition. According to our result, three features could interpret the majority of patients' choices of hospital levels: the MFPC, LFPC, and physician density.	./cache/cord-184194-zdxebonv.txt	./txt/cord-184194-zdxebonv.txt