Blood Pressure Prediction Using Machine Learning

• Grant number: 25/08234-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2025
• End date: October 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Petra Maria Bartmeyer
• Grantee: Tiago Almeida Zanetti
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

This project proposes the development of a machine learning model for continuous and noninvasive prediction of blood pressure in individuals with spinal cord injury, using multivariate signals obtained by wearable sensors. To this end, databases of monkeys and humans with spinal cord injury will be consolidated, applying preprocessing techniques (common interval filtering, outlier removal and time warping) and feature engineering. Initially, a baseline model will be established with k-Nearest Neighbors adapted to time series; then, advanced architectures, such as LSTM, will be explored to capture spectrotemporal patterns. Hyperparameter optimization will be performed via grid search or Bayesian methods, and performance will be evaluated by regression metrics (RMSE, MRE and R²). The aim is to offer an affordable and accurate alternative to conventional measurement methods, with potential for integration into smartwatches and health applications, benefiting not only patients with spinal cord injury, but also expanding the options for continuous monitoring in health care.