id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-326540-1r4gm2d4	Liu, Yuliang	Deep Learning-Based Method of Diagnosing Hyperlipidemia and Providing Diagnostic Markers Automatically	2020-03-11		.txt	text/plain	7093	367	44	[28] [29] [30] [31] In this paper, we sought to propose an auxiliary diagnosis algorithm that can not only diagnose hyperlipidemia rapidly and accurately according to human hematological parameters but also provide diagnostic markers automatically, which improves the objectivity of traditional methods and the interpretability of deep learning model algorithm. The research method of diagnostic markers based on deep learning technology proposed in this paper can not only automatically synthesize large quantities of data but also effectively simplify the research process, thus reducing the research cost, as shown in Figure 2 . In this paper, an algorithm of attention deep learning is proposed which has the potential to automatically diagnose hyperlipidemia with human hematological parameters and provide the diagnostic markers and the importance of different markers for the diagnosis results at the same time.	./cache/cord-326540-1r4gm2d4.txt	./txt/cord-326540-1r4gm2d4.txt