Prediction of fetal heartbeat through artificial intelligence and morphological, morphokinetic and patient-related variables

• Grant number: 20/07634-9
• Support Opportunities: Scholarships in Brazil - Master
• Start date: January 01, 2021
• End date: February 28, 2022
• Field of knowledge: Health Sciences - Medicine
• Principal Investigator: Marcelo Fábio Gouveia Nogueira
• Grantee: Dóris Spinosa Chéles
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

Assisted reproduction technologies are increasingly being used, however, although continuously improved, pregnancy is not guaranteed. The embryonic culture and in an uninterrupted way until the blastocyst stage, through the use of the time-lapse system, allowed improvements in the embryonic selection. Thus, from the video originating from monitoring via time-lapse, it is possible to obtain images of the embryo - which allow access to the morphology of the blastocyst -, in addition to the morphokinetic parameters, which are derived from the times of embryonic development. In addition to embryonic morphology and morphokinetics, information related to patients are the main variables that influences the success of assisted reproduction. These variables can be used as input to a software based on artificial intelligence: artificial neural networks combined with genetic algorithms. Artificial neural networks learn through experience and error: they receive stimuli from outside, process the information received and provide a result. Genetic algorithms allow networks with the best accuracy to be selected at each iteration of the algorithm. Therefore, the objective with this project is the application of variables from three different sources in a software based on artificial intelligence to predict pregnancy by fetal heartbeat. This software will make the evaluation objective, facilitating the choice of the best quality embryo by the embryologist and with the greatest chance of establishing pregnancy. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CHELES, DORIS SPINOSA; FERREIRA, ANDRE SATOSHI; DE JESUS, ISABELA SUEITT; FERNANDEZ, ELEONORA INACIO; PINHEIRO, GABRIEL MARTINS; DAL MOLIN, ELOIZA ADRIANE; ALVES, WALLACE; MILANEZI DE SOUZA, REBECA COLAUTO; BORI, LORENA; MESEGUER, MARCOS; et al. An Image Processing Protocol to Extract Variables Predictive of Human Embryo Fitness for Assisted Reproduction. APPLIED SCIENCES-BASEL, v. 12, n. 7, p. 20-pg., 2022-04-01. (20/07634-9, 18/24252-2, 19/26749-4, 17/19323-5, 19/26684-0)

DE ROSSI, HUGO; BORTOLIERO COSTA, CAMILA; RODRIGUES-ROSSI, LUANA TEIXEIRA; BARROS NUNES, GIOVANA; SPINOSA CHELES, DORIS; MARAN PEREIRA, ISABELLA; ROCHA, DANIELE F. O.; FEITOSA, ELOI; COLNAGHI SIMIONATO, ANA VALERIA; ZOCCAL MINGOTI, GISELE; et al. Modulating the lipid profile of blastocyst cell membrane with DPPC multilamellar vesicles. ARTIFICIAL CELLS NANOMEDICINE AND BIOTECHNOLOGY, v. 50, n. 1, p. 10-pg., 2022-12-31. (20/07634-9, 20/11596-5, 12/50533-2, 19/10732-5)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

CHÉLES, Dóris Spinosa. Prediction of fetal heartbeat through artificial intelligence and morphological, morphokinetic and patient-related variables. 2022. Master's Dissertation - Universidade Estadual Paulista (Unesp). Instituto de Biociências. Botucatu Botucatu.