Machine learning for predicting Chagas disease infection in rural areas of Brazil.
<h4>Introduction</h4>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, mac...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-04-01
|
| Series: | PLoS Neglected Tropical Diseases |
| Online Access: | https://journals.plos.org/plosntds/article/file?id=10.1371/journal.pntd.0012026&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595706353811456 |
|---|---|
| author | Fabio De Rose Ghilardi Gabriel Silva Thallyta Maria Vieira Ariela Mota Ana Luiza Bierrenbach Renata Fiuza Damasceno Lea Campos de Oliveira Alexandre Dias Porto Chiavegatto Filho Ester Sabino |
| author_facet | Fabio De Rose Ghilardi Gabriel Silva Thallyta Maria Vieira Ariela Mota Ana Luiza Bierrenbach Renata Fiuza Damasceno Lea Campos de Oliveira Alexandre Dias Porto Chiavegatto Filho Ester Sabino |
| author_sort | Fabio De Rose Ghilardi |
| collection | DOAJ |
| description | <h4>Introduction</h4>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.<h4>Methods</h4>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.<h4>Results</h4>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.<h4>Conclusion</h4>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. |
| format | Article |
| id | doaj-art-b05f0dc1094b45c0a378dfd7f912d332 |
| institution | Kabale University |
| issn | 1935-2727 1935-2735 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Neglected Tropical Diseases |
| spelling | doaj-art-b05f0dc1094b45c0a378dfd7f912d3322025-01-18T05:31:42ZengPublic Library of Science (PLoS)PLoS Neglected Tropical Diseases1935-27271935-27352024-04-01184e001202610.1371/journal.pntd.0012026Machine learning for predicting Chagas disease infection in rural areas of Brazil.Fabio De Rose GhilardiGabriel SilvaThallyta Maria VieiraAriela MotaAna Luiza BierrenbachRenata Fiuza DamascenoLea Campos de OliveiraAlexandre Dias Porto Chiavegatto FilhoEster Sabino<h4>Introduction</h4>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.<h4>Methods</h4>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.<h4>Results</h4>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.<h4>Conclusion</h4>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.https://journals.plos.org/plosntds/article/file?id=10.1371/journal.pntd.0012026&type=printable |
| spellingShingle | Fabio De Rose Ghilardi Gabriel Silva Thallyta Maria Vieira Ariela Mota Ana Luiza Bierrenbach Renata Fiuza Damasceno Lea Campos de Oliveira Alexandre Dias Porto Chiavegatto Filho Ester Sabino Machine learning for predicting Chagas disease infection in rural areas of Brazil. PLoS Neglected Tropical Diseases |
| title | Machine learning for predicting Chagas disease infection in rural areas of Brazil. |
| title_full | Machine learning for predicting Chagas disease infection in rural areas of Brazil. |
| title_fullStr | Machine learning for predicting Chagas disease infection in rural areas of Brazil. |
| title_full_unstemmed | Machine learning for predicting Chagas disease infection in rural areas of Brazil. |
| title_short | Machine learning for predicting Chagas disease infection in rural areas of Brazil. |
| title_sort | machine learning for predicting chagas disease infection in rural areas of brazil |
| url | https://journals.plos.org/plosntds/article/file?id=10.1371/journal.pntd.0012026&type=printable |
| work_keys_str_mv | AT fabioderoseghilardi machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT gabrielsilva machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT thallytamariavieira machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT arielamota machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT analuizabierrenbach machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT renatafiuzadamasceno machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT leacamposdeoliveira machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT alexandrediasportochiavegattofilho machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil AT estersabino machinelearningforpredictingchagasdiseaseinfectioninruralareasofbrazil |