Development of a portable ECG and electronic stethoscope device for screening cardiovascular disease in rural locations.

[摘要] ENGLISH ABSTRACT: Cardiovascular disease (CVD) is currently the number one cause of deathworldwide, resulting in 17.7 million deaths in 2015 (World Health Organisation, 2017). In South Africa, five people suffer a heart attack every hour, placing CVD as the second deadliest disease in the country, after HIV/AIDS(Pillay-van Wyk et al., 2013). Studies predict that by 2030, CVD will be responsiblefor more deaths in developing countries than the total combined fatalities of HIV/AIDS, malaria and tuberculosis (Beaglehole and Bonita, 2008).Medical equipment required by cardiologists to diagnose cardiovascular disease is expensive and only available at larger hospitals in major cities within South Africa. This presents a significant challenge for the 35% of South Africans residing in rural areas who require medical attention (The World Bank, 2017).Subsequently, many patients in rural areas live with lingering cardiovascular problems.This thesis entails the design and development of a point-of-care device capable of screening for cardiovascular disease in rural locations in Africa. The device consists of an electrocardiogram (ECG) and electronic stethoscope capable of recording electrical bio-signals and heart sounds, respectively. The ECG consistsof a reduced lead set that includes limb leads avL, avR, avF, I, II, III and precordial leads V2 and V4. The data recorded using the ECG can be used to autonomously identify patients with potential cardiovascular disease using machine learning techniques. Furthermore, the potential for reconstructing a full 12 lead ECG recording from a reduced lead set using machine learning is also investigated.Data acquired from the Physikalisch-Technische Bundesanstalt (PTB) onlinedatabase was used to train the machine learning models. A deep pattern recognitionneural network (DPRNN) was used to diagnose patients with normalor abnormal cardiac function. Additionally, a focus time-delay neural network(FTDNN) was used to reconstruct precordial leads V1, V3, V5 and V6from the reduced lead set. The machine learning models were tested on 70subjects recorded using the device in a clinical study conducted at TygerbergHospital. The classification method utilised first order features consisting ofECG amplitudes, intervals and segments, second order features derived fromwavelet entropy and Shannon's energy, as well as unsupervised features generatedusing stacked denoising autoencoders. The classification model, tested inthe clinical trial, produced an accuracy, sensitivity, specificity and area underthe curve (AUC) of 85%, 83%, 87% and 0.85, respectively. The ECG leadreconstruction produced acceptable root-mean-square error (RMSE) values of181 to 266µV, and excellent Pearson r correlation values of 0.91 - 0.95, forthe reconstructed precordial leads. All correlation values were statistically significantat p « 0.01. The results obtained in this study compare favourablywith an initial retrospective study as well as prior studies done in the researchfield. This evidence supports the possibility of deploying a low-cost portabledevice capable of referring patients with potential cardiac abnormalities, inrural locations, to hospitals for further examination.

[发布机构] Stellenbosch University