Detection of Cardiovascular Disease Based on PPG Signals Using Machine Learning with Cloud Computing

Area of Science:

• Biomedical Engineering
• Health Informatics
• Machine Learning

Background:

• Hypertension significantly contributes to cardiovascular diseases (CVDs), with chronic patient care strained by recent global health events.
• Effective early diagnosis and continuous monitoring of blood pressure (BP) are critical for preventing CVD complications and reducing mortality.
• Photoplethysmography (PPG) offers a low-cost, convenient method for detecting various cardiovascular parameters, including BP.

Purpose of the Study:

• To develop an efficient, cost-effective system for early CVD diagnosis and continuous patient monitoring.
• To integrate healthcare with information technology (IT) for remote patient monitoring (RPM) and reduced rehospitalization rates.
• To investigate the efficacy of machine learning (ML) and deep learning (DL) models in analyzing PPG signals for cardiovascular health assessment.

Main Methods:

• Utilized PPG signals from Internet of Things (IoT)-enabled wearable patient monitoring (WPM) devices for remote data acquisition.
• Investigated several ML algorithms: Decision Tree (DT), Naïve Bayes (NB), and Support Vector Machine (SVM).
• Employed a deep learning model, the 1D Convolutional Neural Network-Long Short-Term Memory (1D CNN-LSTM) network, for signal analysis.

Main Results:

• The 1D CNN-LSTM model achieved a high accuracy of 99.5% in analyzing the PPG-BP dataset.
• The proposed system demonstrates the potential for accurate remote monitoring of cardiovascular parameters.
• The integration of WPM devices and ML/DL models provides a robust solution for continuous patient oversight.

Conclusions:

• The developed system offers a cost-effective and efficient solution for continuous monitoring of cardiac patients, aiding physicians in early diagnosis and management.
• Leveraging PPG signals and advanced ML/DL techniques can significantly enhance the remote monitoring of cardiovascular health.
• This IT-integrated approach holds promise for reducing healthcare burdens and improving outcomes for patients with CVD.