Prediction of low Vitamin D not helped by improperly used Machine Learning – Sept 2022


Prediction of Vitamin D Deficiency in Older Adults: The Role of Machine Learning Models

J Clin Endocrinol Metab. 2022 Sep 28;107(10):2737-2747. doi: 10.1210/clinem/dgac432.   PDF rented at DeepDyve
John D Sluyter 1 , Yoshihiko Raita 2 , Kohei Hasegawa 2 , Ian R Reid 3 , Robert Scragg 1 , Carlos A Camargo 2

Context: Conventional prediction models for vitamin D deficiency have limited accuracy.

Background: Using cross-sectional data, we developed models based on machine learning (ML) and compared their performance with those based on a conventional approach.

Methods: Participants were 5106 community-resident adults (50-84 years; 58% male). In the randomly sampled training set (65%), we constructed 5 ML models:

  • lasso regression,
  • elastic net regression,
  • random forest,
  • gradient boosted decision tree, and
  • dense neural network.

The reference model was a logistic regression model. Outcomes were deseasonalized serum 25-hydroxyvitamin D (25(OH)D) <50 nmol/L (yes/no) and <25 nmol/L (yes/no). In the test set (the remaining 35%), we evaluated predictive performance of each model, including area under the receiver operating characteristic curve (AUC) and net benefit (decision curves).

Results: Overall, 1270 (25%) and 91 (2%) had 25(OH)D <50 and <25 nmol/L, respectively. Compared with the reference model, the ML models predicted 25(OH)D <50 nmol/L with similar accuracy. However, for prediction of 25(OH)D <25 nmol/L, all ML models had higher AUC point estimates than the reference model by up to 0.14. AUC was highest for elastic net regression (0.93; 95% CI 0.90-0.96), compared with 0.81 (95% CI 0.71-0.91) for the reference model. In the decision curve analysis, ML models mostly achieved a greater net benefit across a range of thresholds.

Conclusion: Compared with conventional models, ML models predicted 25(OH)D <50 nmol/L with similar accuracy but they predicted 25(OH)D <25 nmol/L with greater accuracy. The latter finding suggests a role for ML models in participant selection for vitamin D supplement trials.


Claimed to be better for <10 ng, but there was too little data to make such accurate predictions

Based on only 91 people they claimed the likeihood of being wrong (p) of 0.0001
This type of Machine Learing error is known as "overfitting"


VitaminDWiki - Predict Vitamin D category contains

It is very difficult to predict the response to supplementation of Vitamin D, or additional sun/UV
There are a huge number of factors involved.
 
This page also has studies predicting deficiency without Vitamin D tests

Examples of 82 studies that Predict Vitamin D levels

Image Image

811 visitors, last modified 30 Sep, 2022,
Printer Friendly Follow this page for updates