Implementing machine learning to monitor human health

• Grant number: 23/16437-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2024
• End date: December 31, 2024
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Fernando Luis de Almeida
• Grantee: Beatriz Sayury Furuyama
• Host Institution: Faculdade de Tecnologia de Itaquera Miguel Reale (FATEC Itaquera). Centro Paula Souza (CEETEPS). Secretaria de Desenvolvimento Econômico (São Paulo - Estado). São Paulo , SP, Brazil

Abstract

In this scientific and technological initiation (ICT) project, an intelligent system will be developed consisting of a matrix with 60 gold microelectrodes (diameter E 50 µm) modified with conductive polymers, obtaining the microtransducers for electrochemical measurement and reference microelectrodes (Ag/AgCl or compatible) with similar function of auxiliary electrode and an area of 1,20 mm2 on the same wafer (paper, polymeric or glass substrate). This system will be used for the chronoamperometric measurement of various metabolites, for example: phosphates (PO43-); nitrite (NO2-); chlorides (Cl-) and uric acid (UA). Currently, there are several scientific studies in the literature that relate the concentration of these species to the energy metabolism of patients. However, electrochemical measurement in biological fluids (blood, saliva and/or sweat) involves considerable experimental complexity due to the infinite number of interfering species in the biochemical environment. In this sense, there are currently few procedures that address artificial intelligence and the chronoamperometric measurement of metabolites together with the evaluation of interfering species in biological fluids, which justifies the execution of this project. Finally, the array will be configured for chronoamperometric measurements of metabolites using a chemical reference solution (SQR) and methods of convolutional neural networks and deep learning for the implementation of Node-RED machine learning used in the analysis of these metabolites, correlating them with human health.