Schrödinger spectrum based continuous cuff-less blood pressure estimation using clinically relevant features from PPG...

Area of Science:

• Biomedical Engineering
• Signal Processing
• Machine Learning

Background:

• Accurate blood pressure (BP) monitoring is crucial for cardiovascular health management.
• Traditional BP measurement methods are invasive or cumbersome, necessitating development of non-invasive techniques.
• Photoplethysmography (PPG) signals offer a promising non-invasive source for BP estimation.

Purpose of the Study:

• To develop and validate a novel cuff-less blood pressure estimation method using PPG signals.
• To enhance PPG signal reconstruction for improved BP prediction accuracy.
• To evaluate the performance of machine learning models combined with semi-classical signal analysis (SCSA) for BP estimation.

Main Methods:

• Utilized multiple machine learning (ML) models and the semi-classical signal analysis (SCSA) technique for cuff-less BP estimation from PPG signals.
• Developed a novel signal reconstruction algorithm to optimize SCSA and improve accuracy-complexity trade-offs.
• Extracted spectral and morphological features from reconstructed PPG and its second derivative (SDPPG) for BP prediction using regression algorithms.

Main Results:

• Achieved a Mean Absolute Error (MAE) of 5.37 mmHg for systolic BP and 2.96 mmHg for diastolic BP using the CatBoost algorithm.
• Met the Association for the Advancement of Medical Instrumentation's standard and achieved Grade A in the British Hypertension Society protocol.
• Demonstrated robust performance on diverse datasets (in-silico, MIMIC-II, MIMIC-III, Queensland) and maintained accuracy under noisy conditions (up to 10 dB SNR).

Conclusions:

• The proposed cuff-less BP estimation technique, integrating ML and SCSA, offers high accuracy and meets clinical standards.
• The novel signal reconstruction algorithm enhances the reliability and applicability of SCSA for BP monitoring.
• The method's straightforward implementation and robustness make it suitable for mobile healthcare devices.