Machine learning algorithms using national registry data to predict loss to follow-up during tuberculosis treatment.

Autor: Rodrigues MMS; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil. moreno.rodrigues@fiocruz.br.; Laboratório de Análise e Visualização de Dados, Fundação Oswaldo Cruz, Porto Velho, Brazil. moreno.rodrigues@fiocruz.br.; Laboratório de Análise de Visualização de Dados, FIOCRUZ Rondônia, Rua da Beira, Laoga, Porto Velho, Rondônia, 7617, 76812-245, Brazil. moreno.rodrigues@fiocruz.br., Barreto-Duarte B; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil.; Programa de Pós-Graduação em Clínica Médica, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.; Instituto de Pesquisa Clínica e Translacional, Curso de Medicina, Salvador,Faculdade ZARNS,, Brazil.; Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Brazil., Vinhaes CL; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil.; Departamento de Infectologia, Hospital das Clínicas da Faculdade de Medicina da Universidade de Sao Paulo,, Sao Paulo, Brazil.; Curso de Medicina, Escola Bahiana de Medicina e Saúde Pública, Salvador, Brazil., Araújo-Pereira M; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil.; Instituto de Pesquisa Clínica e Translacional, Curso de Medicina, Salvador,Faculdade ZARNS,, Brazil.; Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Brazil., Fukutani ER; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil.; Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Brazil., Bergamaschi KB; Laboratório de Análise e Visualização de Dados, Fundação Oswaldo Cruz, Porto Velho, Brazil., Kristki A; Programa de Pós-Graduação em Clínica Médica, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.; Programa Acadêmico de Tuberculose da Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil., Cordeiro-Santos M; Fundação Medicina Tropical Doutor Heitor Vieira Dourado, Manaus, Brazil.; Faculdade de Medicina, Universidade Nilton Lins, Manaus, Brazil., Rolla VC; Laboratório de Pesquisa Clínica em Micobacteriose, Instituto Nacional de Infectologia Evandro Chagas, Fiocruz, Rio de Janeiro, Brazil., Sterling TR; Division of Infectious Diseases, Department of Medicine, Vanderbilt University School of Medicine, Nashville, TN, USA., Queiroz ATL; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil.; Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Brazil., Andrade BB; Multinational Organization Network Sponsoring Translational and Epidemiological Research (MONSTER) Initiative, Salvador, Brazil. bruno.andrade@fiocruz.br.; Programa de Pós-Graduação em Clínica Médica, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. bruno.andrade@fiocruz.br.; Instituto de Pesquisa Clínica e Translacional, Curso de Medicina, Salvador,Faculdade ZARNS,, Brazil. bruno.andrade@fiocruz.br.; Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Brazil. bruno.andrade@fiocruz.br.; Curso de Medicina, Escola Bahiana de Medicina e Saúde Pública, Salvador, Brazil. bruno.andrade@fiocruz.br.; Faculdade de Medicina, Universidade Federal da Bahia, Salvador, Brazil. bruno.andrade@fiocruz.br.; Programa Acadêmico de Tuberculose da Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. bruno.andrade@fiocruz.br.; Division of Infectious Diseases, Department of Medicine, Vanderbilt University School of Medicine, Nashville, TN, USA. bruno.andrade@fiocruz.br.; Laboratório de Inflamação e Biomarcadores, Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Rua Waldemar Falcão, 121, Candeal, Salvador, Bahia, 40296-710, Brazil. bruno.andrade@fiocruz.br.
Jazyk: angličtina
Zdroj: BMC public health [BMC Public Health] 2024 May 23; Vol. 24 (1), pp. 1385. Date of Electronic Publication: 2024 May 23.
DOI: 10.1186/s12889-024-18815-0
Abstrakt: Background: Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN).
Methods: We performed a retrospective study of all TB cases reported to SINAN between 2015 and 2022; excluding children (< 18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we splitted our data into training (~ 80% data) and test (~ 20%) sets, and then compared the model metrics using the test data set.
Results: Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring systems exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity and sensitivity. A user-friendly web calculator app was developed ( https://tbprediction.herokuapp.com/ ) to facilitate implementation.
Conclusions: Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement utilizing schooling level, sex, age, prior TB status, and substance use (drug, alcohol, and/or tobacco). This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje