A Feature Optimized Deep Learning Model for Clinical Data Mining. Issue 3 (1st May 2020)

• Record Type: Journal Article
• Authors: Wu, Tianshu; Chen, Shuyu; Tian, Yingming; Wu, Peng
• Is Part Of: Chinese journal of electronics. Volume 29:Issue 3(2020)
• Page Start: 476
• Page End: 481
• Publication Date: 2020-05-01
• Subjects: data mining -- diseases -- medical information systems -- random forests -- recurrent neural nets; clinical data mining -- artificial intelligence -- random forest algorithm -- feature subset -- ICU data sets -- long short term memory -- early disease prediction -- ICU inpatients -- neural network -- machine learning -- deep learning -- LSTM; Clinical data mining -- Random forests (RF) -- Long short‐term memory (LSTM); Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2020.03.004
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : the Artificial intelligence (AI) has gradually changed from frontier technology to practical application with the continuous progress of deep learning technology in recent years. In this paper, the Random forest (RF) algorithm is adopted to preprocess and optimize the feature subset of ICU data sets. Then these optimized feature subsets are used as input of Long shortterm memory (LSTM) deep learning model, and the early disease prediction of ICU inpatients is carried out by the method of neural network deep learning. Experiments show that this prediction method has higher prediction accuracy compared with other machine learning and deep learning models.