Machine learning for predicting Chagas disease infection in rural areas of Brazil.

INTRODUCTION: Chagas disease is a severe parasitic illness that is prevalent in Latin America and often goes unaddressed. Early detection and treatment are critical in preventing the progression of the illness and its associated life-threatening complications. In recent years, machine learning algorithms have emerged as powerful tools for disease prediction and diagnosis. METHODS: In this study, we developed machine learning algorithms to predict the risk of Chagas disease based on five general factors: age, gender, history of living in a mud or wooden house, history of being bitten by a triatomine bug, and family history of Chagas disease. We analyzed data from the Retrovirus Epidemiology Donor Study (REDS) to train five popular machine learning algorithms. The sample comprised 2,006 patients, divided into 75% for training and 25% for testing algorithm performance. We evaluated the model performance using precision, recall, and AUC-ROC metrics. RESULTS: The Adaboost algorithm yielded an AUC-ROC of 0.772, a precision of 0.199, and a recall of 0.612. We simulated the decision boundary using various thresholds and observed that in this dataset a threshold of 0.45 resulted in a 100% recall. This finding suggests that employing such a threshold could potentially save 22.5% of the cost associated with mass testing of Chagas disease. CONCLUSION: Our findings highlight the potential of applying machine learning to improve the sensitivity and effectiveness of Chagas disease diagnosis and prevention. Furthermore, we emphasize the importance of integrating socio-demographic and environmental factors into neglected disease prediction models to enhance their performance.

Overview of Chagas disease surveillance in an endemic region in Southeastern Brazil.

Chagas disease (CD) is a neglected disease caused by the protozoan Trypanosoma cruzi. It has high morbidity and mortality rates and mainly affects socially vulnerable populations. This is a cross-sectional study, with retrospective and prospective data collection. Using questionnaires applied to environmental surveillance coordinators, we characterized the status of CD surveillance activities in municipalities endemic for the disease in Northern Minas Gerais State (MG) and Jequitinhonha Valley (Vale do Jequitinhonha). Moreover, we spatialized the vulnerability index for chronic CD in the study area. The population consisted of 22 environmental surveillance coordinators, active in 2020, from Northern MG and Jequitinhonha Valley, 21 municipalities included in the SaMi-Trop research project, and Montes Claros municipality. After applying the questionnaires to the coordinators, a descriptive analysis of the variables was performed. To characterize the active municipalities, the explanatory variables collected in the questionnaire were compared with the dichotomous variable. Bivariate descriptive analysis was performed. Finally, geoprocessing techniques were used to spatialize the data and prepare maps. Regarding the team of endemic combat agents (ECA), 90.9% reported the lack of a specific team for CD vector control actions. Of the 22 municipalities participating in this study, nine were active (41.1%). Only 25% (n=2) of active municipalities (9% of the municipalities studied) met the target of visiting 50% of households per year. Finally, 81.1% of the coordinators stated that in their municipality, they developed actions linked to primary health care (PHC). The implementation of CD surveillance activities weakened in the endemic region. Few municipalities have a surveillance team, with low regularity of active surveillance and noncompliance with the program's goal. The results suggest insufficient recording of activities in the information system, considering that there are municipalities that report performing the activities, but no production record was observed in the system.

Overview of Chagas disease surveillance in an endemic region in Southeastern Brazil

ABSTRACT Chagas disease (CD) is a neglected disease caused by the protozoan Trypanosoma cruzi. It has high morbidity and mortality rates and mainly affects socially vulnerable populations. This is a cross-sectional study, with retrospective and prospective data collection. Using questionnaires applied to environmental surveillance coordinators, we characterized the status of CD surveillance activities in municipalities endemic for the disease in Northern Minas Gerais State (MG) and Jequitinhonha Valley (Vale do Jequitinhonha). Moreover, we spatialized the vulnerability index for chronic CD in the study area. The population consisted of 22 environmental surveillance coordinators, active in 2020, from Northern MG and Jequitinhonha Valley, 21 municipalities included in the SaMi-Trop research project, and Montes Claros municipality. After applying the questionnaires to the coordinators, a descriptive analysis of the variables was performed. To characterize the active municipalities, the explanatory variables collected in the questionnaire were compared with the dichotomous variable. Bivariate descriptive analysis was performed. Finally, geoprocessing techniques were used to spatialize the data and prepare maps. Regarding the team of endemic combat agents (ECA), 90.9% reported the lack of a specific team for CD vector control actions. Of the 22 municipalities participating in this study, nine were active (41.1%). Only 25% (n=2) of active municipalities (9% of the municipalities studied) met the target of visiting 50% of households per year. Finally, 81.1% of the coordinators stated that in their municipality, they developed actions linked to primary health care (PHC). The implementation of CD surveillance activities weakened in the endemic region. Few municipalities have a surveillance team, with low regularity of active surveillance and noncompliance with the program's goal. The results suggest insufficient recording of activities in the information system, considering that there are municipalities that report performing the activities, but no production record was observed in the system.