Loading...
 
Toggle Health Problems and D

96% prediction of Vitamin D less than 20ng (not general nor cost-effective) - May 2024


Vitamin D Deficiency Detection: A Novel Ensemble Approach with Interpretability Insights

IEEE Xplore: 23 May 2024 DOI: 10.1109/ICEEICT62016.2024.10534371 PDF cost VitaminDWiki $36
Published in: 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT)
Date of Conference: 02-04 May 2024. Bangaldesh
Md.Fahim Ul Islam; Mehedi Hasan; Md.Tahmid Rahman; Amitabha Chakrabarty

Vitamin D deficiency is becoming a global public health concern, particularly in medical centers, with serious consequences for disease severity, mortality, and morbidity. Traditional diagnostic methodologies struggle with cost and are time-consuming. This drives a paradigm change toward the use of automated process for improved predicted accuracy and cost-effectiveness in diagnosing Vitamin D deficiency. In addressing the global challenge of Vitamin D deficiency, this study introduces an ensemble model that synergistically combines LightGBM and CatBoost algorithms, marking a significant leap in diagnostic methodologies. By leveraging the strengths of these advanced machine learning techniques, our approach achieves an impressive 96% accuracy on the Vitamin D Deficiency (VDD) Dataset, demonstrating substantial improvement over traditional diagnostic methods. The integration of SnAP (Shapley Additive explanations) for interpretability further enhances the utility of our model, providing clear insights into the impact of individual features on the severity predictions of Vitamin D deficiency. This revised abstract concisely encapsulates the research objectives, innovative methodology, and critical findings, underscoring the potential to revolutionize diagnostic efficiency and accuracy in the medical domain.

Variables for 3,000 college students
Weight (61-91 kgs),
Height (1.48-1.73m),
BMI (25.94-34.81 kg/m2),
Waist Circumference (58-92 cm),
Body Fat (21.60-41.20%),
Bone Mass (2.00-3.60),
Exercise (yes/no),
Sunlight Exposure/Day (5.0-30 hours), >24 hours ??
Milk Consumption (0-500).

Used a combination of 5 machine learning techniques
Decision Tree
Support Vector Classifier (SVC),
Naive Bayes (NB) model
Multilayer Perceptron (MLP)
Logistic Regression

Does not mention which expensive Body Fat measurement was used

1. Hydrostatic Weighing (Underwater Weighing)
2. Air Displacement Plethysmography (ADP)
3. Bioelectrical Impedance Analysis (BIA)
4. Skinfold Measurements
5. Dual-Energy X-ray Absorptiometry (DEXA)
6. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) Scans

Does not mention which expensive Bone Mass measurement was used

Dual-Energy X-Ray Absorptiometry (DEXA or DXA)
Quantitative Computed Tomography (QCT)
Quantitative Ultrasound (QUS)
Peripheral Dual-Energy X-Ray Absorptiometry (pDXA)
Single-Energy X-Ray Absorptiometry (SEXA)
Radiographic Absorptiometry
Fracture Risk Assessment Tool (FRAX)


Ignores: latitude, season, skin color, seafood, supplementation, concealing clothing, high-risk job, health problems that consume Vitamin D, etc.

A $50 Vitamin D home test is less expensive AND provides exact level, not just < 20 ng

A $12 instant Vitamin D test provides Y/N 30 ng results

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 80 studies that Predict Vitamin D levels

Image Image