Smart Health Solutions: Harnessing Deep Learning Models For Accurate Myocardial Infarction Detection Via PPG Database

The comprehensive study delves into the critical domain of myocardial infarction (MI) detection, emphasizing the integration of advanced technologies for timely identification and intervention. MI, colloquially known as a heart attack, stands as a severe medical condition characterized by sudden impediments to blood flow in a segment of the heart muscle. Leveraging automated cardiac analysis techniques with personal devices, particularly portable healthcare devices using electrocardiogram (ECG) and photoplethysmography (PPG), offers a promising avenue for MI detection. PPG measures the pulsatility of cutaneous blood vessels using optical sensors to provide important cardiac parameters such blood oxygen saturation and heart rate. The research emphasizes the crucial function of a deep learning (DL) model in this scenario, integrating preprocessing, feature extraction, and classification to evaluate PPG data for the purpose of monitoring myocardial infarction. Through the meticulous examination of waveforms gathered from PPG database, the model demonstrates its proficiency in identifying patterns indicative of potential MI indicators. The culmination of this approach not only showcases the potential of artificial intelligence in advancing cardiac health diagnostics but also underscores its effectiveness as a robust and automated system for early detection and intervention in cardiovascular health. This integrated methodology, bridging technological advancements with medical expertise, marks a significant stride in enhancing the prospects of successful recovery and long-term cardiovascular health monitoring.

• Publication year

  2024

• Venue

  2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS)

• Publication date

  2024-03-14

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICACCS60874.2024.10717133
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Cardiac arrhythmias classification using photoplethysmography database

  2024cited by this paper
• Prediction of Arrhythmias and Acute Myocardial Infarctions using Machine Learning

  2023cited by this paper
• Physical Activity Recognition Based on Deep Learning Using Photoplethysmography and Wearable Inertial Sensors

  2023cited by this paper
• Non-Invasive Classification of Blood Glucose Level Based on Photoplethysmography Using Time-Frequency Analysis

  2023cited by this paper
• Cuff-Less Blood Pressure Prediction Based on Photoplethysmography and Modified ResNet

  2023cited by this paper
• On the development of low power wearable devices for assessment of physiological vital parameters: a systematic review

  2023cited by this paper
• Blood Pressure Estimation From Photoplethysmography by Considering Intra- and Inter-Subject Variabilities: Guidelines for a Fair Assessment

  2023cited by this paper
• Non-invasive arterial blood pressure measurement and SpO2 estimation using PPG signal: a deep learning framework

  2023cited by this paper
• A Deep Learning Approach for Atrial Fibrillation Classification Using Multi-Feature Time Series Data from ECG and PPG

  2023cited by this paper
• CIsense: an automated framework for early screening of cerebral infarction using PPG sensor data

  2023cited by this paper
• Photoplethysmography in Wearable Devices: A Comprehensive Review of Technological Advances, Current Challenges, and Future Directions

  2023cited by this paper
• Performer: A Novel PPG-to-ECG Reconstruction Transformer for a Digital Biomarker of Cardiovascular Disease Detection

  2022cited by this paper
• DETECTION of HFrEF and HFpEF USING PPG-DERIVED HRV with MACHINE LEARNING METHODS

  2022cited by this paper
• Sensor Based Smart Real Time Monitoring of Patients Conditions Using Wireless Protocol

  2018cited by this paper

• No citing papers are available for this paper.