Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters
Background: Vitamin D deficiency affects the general population and is very common among elderly Europeans. This study compared different supervised learning algorithms in a cohort of Spanish individuals aged 35–75 years to predict which anthropometric parameter was most strongly associated with vit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/4/616 |
| _version_ | 1797478323093241856 |
|---|---|
| author | Carmen Patino-Alonso Marta Gómez-Sánchez Leticia Gómez-Sánchez Benigna Sánchez Salgado Emiliano Rodríguez-Sánchez Luis García-Ortiz Manuel A. Gómez-Marcos |
| author_facet | Carmen Patino-Alonso Marta Gómez-Sánchez Leticia Gómez-Sánchez Benigna Sánchez Salgado Emiliano Rodríguez-Sánchez Luis García-Ortiz Manuel A. Gómez-Marcos |
| author_sort | Carmen Patino-Alonso |
| collection | DOAJ |
| description | Background: Vitamin D deficiency affects the general population and is very common among elderly Europeans. This study compared different supervised learning algorithms in a cohort of Spanish individuals aged 35–75 years to predict which anthropometric parameter was most strongly associated with vitamin D deficiency. Methods: A total of 501 participants were recruited by simple random sampling with replacement (reference population: 43,946). The analyzed anthropometric parameters were waist circumference (WC), body mass index (BMI), waist-to-height ratio (WHtR), body roundness index (BRI), visceral adiposity index (VAI), and the Clinical University of Navarra body adiposity estimator (CUN-BAE) for body fat percentage. Results: All the anthropometric indices were associated, in males, with vitamin D deficiency (<i>p</i> < 0.01 for the entire sample) after controlling for possible confounding factors, except for CUN-BAE, which was the only parameter that showed a correlation in females. Conclusions: The capacity of anthropometric parameters to predict vitamin D deficiency differed according to sex; thus, WC, BMI, WHtR, VAI, and BRI were most useful for prediction in males, while CUN-BAE was more useful in females. The naïve Bayes approach for machine learning showed the best area under the curve with WC, BMI, WHtR, and BRI, while the logistic regression model did so in VAI and CUN-BAE. |
| first_indexed | 2024-03-09T21:30:21Z |
| format | Article |
| id | doaj.art-48d7f6b9d9f54026a423ba8dbc27a1c4 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T21:30:21Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-48d7f6b9d9f54026a423ba8dbc27a1c42023-11-23T20:57:31ZengMDPI AGMathematics2227-73902022-02-0110461610.3390/math10040616Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric ParametersCarmen Patino-Alonso0Marta Gómez-Sánchez1Leticia Gómez-Sánchez2Benigna Sánchez Salgado3Emiliano Rodríguez-Sánchez4Luis García-Ortiz5Manuel A. Gómez-Marcos6Department of Statistics, University of Salamanca, 37007 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainPrimary Care Research Unit of Salamanca (APISAL), Biomedical Research Institute of Salamanca (IBSAL), 37005 Salamanca, SpainBackground: Vitamin D deficiency affects the general population and is very common among elderly Europeans. This study compared different supervised learning algorithms in a cohort of Spanish individuals aged 35–75 years to predict which anthropometric parameter was most strongly associated with vitamin D deficiency. Methods: A total of 501 participants were recruited by simple random sampling with replacement (reference population: 43,946). The analyzed anthropometric parameters were waist circumference (WC), body mass index (BMI), waist-to-height ratio (WHtR), body roundness index (BRI), visceral adiposity index (VAI), and the Clinical University of Navarra body adiposity estimator (CUN-BAE) for body fat percentage. Results: All the anthropometric indices were associated, in males, with vitamin D deficiency (<i>p</i> < 0.01 for the entire sample) after controlling for possible confounding factors, except for CUN-BAE, which was the only parameter that showed a correlation in females. Conclusions: The capacity of anthropometric parameters to predict vitamin D deficiency differed according to sex; thus, WC, BMI, WHtR, VAI, and BRI were most useful for prediction in males, while CUN-BAE was more useful in females. The naïve Bayes approach for machine learning showed the best area under the curve with WC, BMI, WHtR, and BRI, while the logistic regression model did so in VAI and CUN-BAE.https://www.mdpi.com/2227-7390/10/4/616vitamin Dmachine learningdecision makinganthropometric parameters |
| spellingShingle | Carmen Patino-Alonso Marta Gómez-Sánchez Leticia Gómez-Sánchez Benigna Sánchez Salgado Emiliano Rodríguez-Sánchez Luis García-Ortiz Manuel A. Gómez-Marcos Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters Mathematics vitamin D machine learning decision making anthropometric parameters |
| title | Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters |
| title_full | Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters |
| title_fullStr | Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters |
| title_full_unstemmed | Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters |
| title_short | Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters |
| title_sort | predictive ability of machine learning methods for vitamin d deficiency prediction by anthropometric parameters |
| topic | vitamin D machine learning decision making anthropometric parameters |
| url | https://www.mdpi.com/2227-7390/10/4/616 |
| work_keys_str_mv | AT carmenpatinoalonso predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT martagomezsanchez predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT leticiagomezsanchez predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT benignasanchezsalgado predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT emilianorodriguezsanchez predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT luisgarciaortiz predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters AT manuelagomezmarcos predictiveabilityofmachinelearningmethodsforvitaminddeficiencypredictionbyanthropometricparameters |