loading page

Blood pressure estimation from photoplethysmography by considering intra- and inter-subject variabilities: guidelines for a fair assessment
  • +4
  • Thiago Bulhões da Silva Costa ,
  • Felipe Meneguitti Dias ,
  • Diego Armando Cardona Cardenas ,
  • Marcelo Arruda Fiuza de Toledo ,
  • Daniel Mário de Lima ,
  • José Eduardo Krieger ,
  • Marco Antonio Gutierrez
Thiago Bulhões da Silva Costa
Universidade Federal do ABC, Universidade Federal do ABC

Corresponding Author:[email protected]

Author Profile
Felipe Meneguitti Dias
Author Profile
Diego Armando Cardona Cardenas
Author Profile
Marcelo Arruda Fiuza de Toledo
Author Profile
Daniel Mário de Lima
Author Profile
José Eduardo Krieger
Author Profile
Marco Antonio Gutierrez
Author Profile


Cardiovascular diseases are the leading causes of death, and blood pressure (BP) monitoring is essential for prevention, diagnosis, assessment, and treatment. Photoplethysmography (PPG) is a low-cost opto-electronic technique for BP measurement that allows the acquisition of a modulated light signal highly correlated with BP. There are several reports of methods to estimate BP from PPG with impressive results; in this study, we demonstrate that the previous results are excessively optimistic because of their train/test split configuration. To manage this limitation, we considered intra- and inter-subject data arrangements and demonstrated how they affect the results of feature-based BP estimation algorithms (i.e., XGBoost, LightGBM, and CatBoost) and signal-based algorithms (i.e., Residual U-Net, ResNet-18, and ResNet-LSTM). Inter-subject configuration performance is inferior to intra-subject configuration performance, regardless of the model. We also showed that, using only demographic attributes (i.e., age, sex, weight, and subject index number), a regression model achieved results comparable to those obtained in an intra-subject scenario. Although limited to a public clinical database, our findings suggest that algorithms that use an intra-subject setting without a calibration strategy may be learning to identify patients and not predict BP.