A Smart Heart Disease Diagnostic System Using Deep Vanilla LSTM

作     者：Maryam Bukhari Sadaf Yasmin Sheneela Naz Mehr Yahya Durrani Mubashir Javaid Jihoon Moon Seungmin Rho 

作者机构：Department of Computer ScienceCOMSATS University IslamabadAttock CampusAttockPakistan Department of Computer ScienceCOMSATS University IslamabadIslamabadPakistan Department of Computer ScienceUET TaxilaTaxilaPakistan Department of AI and Big DataSoonchunhyang UniversityAsanKorea Department of Industrial SecurityChung-Ang UniversitySeoul06974Korea 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第77卷第10期

页      面：1251-1279页

核心收录：

学科分类：1002[医学-临床医学] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 10[医学] 

基　　金：supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)Support Program(IITP-2023-2018-0-01799) supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)and also the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2022R1F1A1063134) 

主　　题：Smart systems deep learning ECG signals heart disease concurrent learning LSTM generalized gated pooling 

摘      要：Effective smart healthcare frameworks contain novel and emerging solutions for remote disease diagnostics,which aid in the prevention of several diseases including heart-related *** this context,regular monitoring of cardiac patients through smart healthcare systems based on Electrocardiogram(ECG)signals has the potential to save many *** existing studies,several heart disease diagnostic systems are proposed by employing different state-of-the-art methods,however,improving such methods is always an intriguing area of ***,in this research,a smart healthcare system is proposed for the diagnosis of heart disease using ECG *** proposed framework extracts both linear and time-series information on the ECG signals and fuses them into a single framework *** linear characteristics of ECG signals are extracted by convolution layers followed by Gaussian Error Linear Units(GeLu)and time series characteristics of ECG beats are extracted by Vanilla Long Short-Term Memory Networks(LSTM).Following on,the feature reduction of linear information is done with the help of ID Generalized Gated Pooling(GGP).In addition,data misbalancing issues are also addressed with the help of the Synthetic Minority Oversampling Technique(SMOTE).The performance assessment of the proposed model is done over the two publicly available datasets named MIT-BIH arrhythmia database(MITDB)and PTB Diagnostic ECG database(PTBDB).The proposed framework achieves an average accuracy performance of 99.14%along with a 95%recall value.