Study of a prediction model for Tuberculosis treatment abandonment

• Grant number: 18/23963-2
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Start date: July 01, 2019
• End date: May 31, 2023
• Field of knowledge: Health Sciences - Collective Health - Public Health
• Principal Investigator: Antonio Ruffino Netto
• Grantee: Verena Hokino Yamaguti
• Host Institution: Faculdade de Medicina de Ribeirão Preto (FMRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil
• Associated scholarship(s): 21/08341-8 - Prediction model study for tuberculosis (TB) treatment outcome, BE.EP.DD

Abstract

Tuberculosis is the ninth leading cause of death in the world and the leading causes of death from infectious diseases. For effective control of the disease in Brazil, the Directly Observed Treatment Strategy is used. However, there is a significant number of new cases reported. The use of information system aims to improve the quality of planning, program implementation, and treatment control and information management. It is therefore crucial to provide such systems with capabilities that help health professionals to manage the resources available and focus their efforts on cases that require their attention. This study has as its main goal to propose a prediction model for TB treatment abandonment. This would provide a way to predict treatment abandonment and redirect resources in advance to improve the adherence of these cases, reducing the abandonment rate and the number of infections by resistant bacilli. Knowledge Discovery in Database (KDD) will be used as a methodology. The database is constituted of patients collected from different information systems (SISTB, TBWEB and SINAN) and the national cohort study database (support social study database of TB patients financed by CNPq, the study RePORT financed by the Decit/SCTIE/MS and the National Institute of Health/USA). By exploring the databases through KDD, there will be performed analysis to predict the abandonment risk of TB patients. The predictive model will be based on machine learning methods that take into account the relation of comorbidities to drug-resistant TB. (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)

YAMAGUTI, VERENA HOKINO; ALVES, DOMINGOS; CHARTERS LOPES RIJO, RUI PEDRO; BRANDAO MIYOSHI, NEWTON SHYDEO; RUFFINO-NETTO, ANTONIO. Development of CART model for prediction of tuberculosis treatment loss to follow up in the state of Sao Paulo, Brazil: A case-control study. INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, v. 141, SEP 2020. (18/00307-2, 18/23963-2)

Academic Publications

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

YAMAGUTI, Verena Hokino. Study of a prediction model for tuberculosis treatment loss to follow up. 2023. Doctoral Thesis - Universidade de São Paulo (USP). Faculdade de Medicina de Ribeirão Preto (PCARP/BC) Ribeirão Preto.