Login / Signup

Estimation of carotid-femoral pulse wave velocity from finger photoplethysmography signal.

Alessandro GentilinCantor TarperiAntonio CeveseAnna Vittoria MattioliFederico Schena
Published in: Physiological measurement (2022)
Objective . This project compared a new method to estimate the carotid-femoral pulse wave velocity (cf-PWV) to the gold-standard cf-PWV technique. Approach . The cf-PWV was estimated from the pulse transit time (FPS-PTT) calculated by processing the finger photoplethysmographic signal of Finapres (FPS) and subject's height only (brief mode) as well as along with other variables (age, heart rate, arterial pressure, weight; complete mode). Doppler ultrasound cf-PWVs and FPS-PTTs were measured in 90 participants equally divided into 3 groups (18-30; 31-59; 60-79 years). Predictions were performed using multiple linear regressions (MLR) and with the best regression model identified by using MATLAB Regression Learner App. A validation set approach (60 training datasets, 30 testing datasets; VSA) and leave-one-out cross-validation (LOOCV) were used. Main results . With MLR, the discrepancies were: 0.01 ± 1.21 m s -1 (VSA) and 0.001 ± 1.11 m s -1 (LOOCV) in brief mode; -0.02 ± 0.83 m s -1 (VSA) and 0.001 ± 0.84 m s -1 (LOOCV) in complete mode. Using a linear support vector machine model (SVM) in brief mode, the discrepancies were: 0.01 ± 1.19 m s -1 (VSA) and -0.01 ± 1.06 m s -1 (LOOCV). Using an Exponential Gaussian process regression model (GPR) in complete mode, the discrepancies were: -0.03 ± 0.79 m s -1 (VSA) and 0.01 ± 0.75 m s -1 (LOOCV). Significance . The cf-PWV can be estimated by processing the FPS-PTT and subjects' height only, but the inclusion of other variables improves the prediction performance. Predictions through MLR qualify as acceptable in both brief and complete modes. Predictions via linear SVM in brief mode improve but still qualify as acceptable. Interestingly, predictions through Exponential GPR in complete mode improve and qualify as excellent.
Keyphrases
  • heart rate
  • cystic fibrosis
  • blood pressure
  • body mass index
  • physical activity
  • deep learning
  • quality improvement
  • fatty acid
  • machine learning
  • weight gain
  • body weight