| Author | Delpino, Felipe Mendes | |
| Author | Chiavegatto Filho, Alexandre Dias Porto | |
| Author | Torres, Juliana Lustosa | |
| Author | Andrade, Fabíola Bof de | |
| Author | Costa, Maria Fernanda Furtado Lima | |
| Author | Nunes, Bruno Pereira | |
| Access date | 2025-04-30T18:51:11Z | |
| Available date | 2025-04-30T18:51:11Z | |
| Document date | 2025 | |
| Citation | DELPINO, Felipe Mendes et al. Predicting all-cause mortality with machine learning among Brazilians aged 50 and over: results from The Brazilian Longitudinal Study of Ageing (ELSI-Brazil). NPJ Aging, v. 11, n. 1, 22, 2025. | en_US |
| ISSN | 2731-6068 | en_US |
| URI | https://www.arca.fiocruz.br/handle/icict/70057 | |
| Language | eng | en_US |
| Publisher | Nature | en_US |
| Rights | restricted access | en_US |
| Subject in Portuguese | Cuidados em saude | en_US |
| Subject in Portuguese | Fatores de risco | en_US |
| Title | Predicting all-cause mortality with machine learning among Brazilians aged 50 and over: results from The Brazilian Longitudinal Study of Ageing (ELSI-Brazil). | en_US |
| Type | Article | en_US |
| DOI | 10.1038/s41514-025-00210-7 | |
| Abstract | We aimed to develop a machine-learning model to predict all-cause mortality among Brazilians aged 50 and over, incorporating demographic, health, and lifestyle characteristics as predictors. We analyzed data from the Brazilian Longitudinal Study of Aging (ELSI-Brazil), waves 1 and 2 (2015-2021), a nationally representative sample from 70 municipalities across Brazil's five regions. Nine algorithms, including Random Forest, Gradient Boosting, XGBOOST, and Logistic Regression, were tested on 9412 participants (54.6% female), with 970 deaths recorded over approximately five years. Using 59 predictor variables, we assessed performance with metrics like AUC, accuracy, precision, and F1-Score. Random Forest excelled with an AUC of 0.92 (95% CI: 0.90-0.94). SHAP analysis highlighted age, sex, BMI, medication use, and physical activity as top predictors. Integrating these models into healthcare systems can improve policy planning and enable targeted interventions, ultimately fostering better health outcomes for aging populations. | en_US |
| Affilliation | Universidade Federal de Pelotas. Programa de Pós-graduação em Enfermagem. Pelotas, RS, Brasil. | en_US |
| Affilliation | Universidade de São Paulo. Escola de Saúde Pública. São Paulo, SP, Brasil. | en_US |
| Affilliation | Universidade Federal de Minas Gerais. Departamento de Medicina Preventiva e Social. Belo Horizonte, MG, Brasil. / Universidade Federal de Minas Gerais. Programa de Pós-graduação em Saúde Pública. Belo Horizonte, MG, Brasil. | en_US |
| Affilliation | Fundação Oswaldo Cruz. Instituto Rene Rachou. Programa de Pós-graduação. Belo Horizonte, MG, Brasil. | en_US |
| Affilliation | Fundação Oswaldo Cruz. Instituto Rene Rachou. Centro de Estudos em Saúde Pública e Envelhecimento Envelhecimento. Belo Horizonte, MG, Brasil. / Universidade Federal de Minas Gerais. Centro de Estudos em Saúde Pública e Envelhecimento. Belo Horizonte, MG, Brasil. | en_US |
| Affilliation | Universidade Federal de Pelotas. Programa de Pós-graduação em Enfermagem. Pelotas, RS, Brasil. / Department of Health and Kinesiology. University of Illinois Urbana-Champaign. Urbana, IL, USA. | en_US |
| Subject | Health care | en_US |
| Subject | Risk factors | en_US |
| Embargo date | 2030-12-31 | |
