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
- Predicted Vitamin D levels for health young women had 95% accuracy using neural network (paywall) – July 2024
- Vitamin D deficiency predicted with 91% accuracy ( AI, age, paywall) - April 2024
- Predictors of low vitamin D: race, age, and BMI (confirmed now by Machine Learning) – Feb 2024
- Low Vitamin D screening with just 5 questions (for less than 12 ng) – June 2022
- Top 10 signs of Vitamin D Deficiency (9 minute Video) - Oct 2021
- Estimate Vitamin D levels based on questionnaires (12 studies) – July 2020
- Is a senior Vitamin D insufficient - a 2 minute questionnaire is 85 percent accurate – Nov 2019
- Simple Vitamin D deficiency scoring system – Feb 2016
- Toward predicting vitamin D levels without a blood test. by VitaminDWiki
- Excellent prediction of very low vitamin D in elderly from just 16 questions (analyzed by ML) – June 2017
- Quick, free, self test of vitamin D deficiency 90% chance <20 ng
| 813 visitors, last modified 30 Sep, 2022, |