| dc.creator | Paula, Daniela Polessa | |
| dc.creator | Aguiar, Odaleia Barbosa | |
| dc.creator | Marques, Larissa Pruner | |
| dc.creator | Bensenor, Isabela | |
| dc.creator | Suemoto, Claudia Kimie | |
| dc.creator | Fonseca, Maria de Jesus Mendes da | |
| dc.creator | Griep, Rosane Härter | |
| dc.date | 2022-12-20T19:08:25Z | |
| dc.date | 2022-12-20T19:08:25Z | |
| dc.date | 2022 | |
| dc.date.accessioned | 2023-09-26T22:44:25Z | |
| dc.date.available | 2023-09-26T22:44:25Z | |
| dc.identifier | PAULA, Daniela Polessa et al. Comparing machine learning algorithms for multimorbidity prediction: An example from the Elsa-Brasil study. Plos One, v. 17, n. 10, e0275619, p. 1 - 14, Oct. 2022. | |
| dc.identifier | 1932-6203 | |
| dc.identifier | https://www.arca.fiocruz.br/handle/icict/56097 | |
| dc.identifier | 10.1371/journal.pone.0275619 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8882599 | |
| dc.description | Multimorbidity is a worldwide concern related to greater disability, worse quality of life, and
mortality. The early prediction is crucial for preventive strategies design and integrative
medical practice. However, knowledge about how to predict multimorbidity is limited, possibly
due to the complexity involved in predicting multiple chronic diseases.
Methods
In this study, we present the use of a machine learning approach to build cost-effective multimorbidity
prediction models. Based on predictors easily obtainable in clinical practice (sociodemographic,
clinical, family disease history and lifestyle), we build and compared the
performance of seven multilabel classifiers (multivariate random forest, and classifier chain,
binary relevance and binary dependence, with random forest and support vector machine
as base classifiers), using a sample of 15105 participants from the Brazilian Longitudinal
Study of Adult Health (ELSA-Brasil). We developed a web application for the building and
use of prediction models.
Results
Classifier chain with random forest as base classifier performed better (accuracy = 0.34,
subset accuracy = 0.15, and Hamming Loss = 0.16). For different feature sets, random forest
based classifiers outperformed those based on support vector machine. BMI, blood
pressure, sex, and age were the features most relevant to multimorbidity prediction.
Our results support the choice of random forest based classifiers for multimorbidity
prediction. | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.publisher | Public Library of Science | |
| dc.rights | open access | |
| dc.subject | Comparando algoritmos | |
| dc.subject | Aprendizado de máquina | |
| dc.subject | Predição de multimorbidade: | |
| dc.subject | Exemplo de o estudo Elsa-Brasil | |
| dc.subject | Comparing machine | |
| dc.subject | Learning algorithms | |
| dc.subject | Multimorbidity prediction | |
| dc.subject | Elsa-Brasil study | |
| dc.title | Comparing machine learning algorithms for multimorbidity prediction: An example from the Elsa-Brasil study | |
| dc.type | Article | |
