Predictive Ability of Machine-Learning Methods for Vitamin D Deficiency Prediction by Anthropometric Parameters

Abstract

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 (p < 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.

Using Machine Learning to Identify the Relationships between Demographic, Biochemical, and Lifestyle Parameters and Plasma Vitamin D Concentration in Healthy Premenopausal Chinese Women

“…In fact, many of these studies were more closely related to the engineering and mathematics fields. In contrast, our study focuses on predicting vitamin D levels using Mach-L and identifying significant factors in a healthy population of Chinese women within a specific age range [44,45]. Our study is the first to use Mach-L methods to set PVDC as a continuous variable.…”

Machine learning approach for the detection of vitamin D level: a comparative study

“…Thus, another notable point is an attempt to draw attention to the multicollinearity problem in the self-collected dataset in the current study. In contrast, previous studies did not consider it [ 30 – 33 ].…”

“…Supervised classification techniques [ 29 ] are modern ML approaches to analyze the response variable in terms of the explanatory variables. According to the literature review, different classification or prediction models using various ML methods have been studied to determine Vitamin D status [ 30 – 33 ]. These comparative studies addressed the binary classification models to classify Vitamin D status [ 30 – 33 ].…”

“…According to the literature review, different classification or prediction models using various ML methods have been studied to determine Vitamin D status [ 30 – 33 ]. These comparative studies addressed the binary classification models to classify Vitamin D status [ 30 – 33 ]. However, categorizing the status of Vitamin D as only "Deficient" and "Not Deficient" may cause a loss of information and poor performance due to overgeneralization.…”

Advances in Artificial Intelligence and Statistical Techniques with Applications to Health and Education

“…Topics addressed in this Special Issue include data mining, machine learning, learning analytics, prediction methods, pattern recognition, decision analysis, probabilistic reasoning, fuzzy systems, student or patient modelling, adaptive systems, collaborative systems, recommendation systems, experimental design, and empirical study cases. Specifically, there are twenty rigorously reviewed papers included in this Special Issue, with eleven specializing in the field of medicine and health [1][2][3][4][5][6][7][8][9][10][11] and nine specializing in the field of education [12][13][14][15][16][17][18][19][20]. In total, fifteen papers (43% of the received) were rejected for publication.…”