Researchcatboostehealth literacyshapolder adults
Machine Learning Predicts Older Adults' Digital Health Literacy
8.2
In 2026, Korean researchers developed and validated an explainable machine learning approach to predict digital health literacy (DHL) in older adults, using a pilot performance cohort (n=30) and a survey cohort (n=1000). Categorical boosting achieved 0.785 accuracy and 0.835 AUC; SHAP analysis showed self-care confidence, health-app interest, device use, and exercise positively, while age, alcohol, and smoking negatively influenced DHL.
Key Points
- 1Finds device use and education increase comprehension; alcohol intake decreases performance (pilot n=30).
- 2Shows self-reported factors (interest in health apps, self-care confidence, age, lifestyle) correlate with DHL (n=1000).
- 3Demonstrates categorical boosting predicts KeHEALS levels (accuracy 0.785, AUC 0.835); enables explainable DHL targeting.
Scoring Rationale
Integrated explainable ML with extensive survey and pilot data; limited novelty beyond applied methodology and single-country sample.
Sources
Public references used for this report.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
Active Search Campaigns by BudgetEasyHigh CPC Clicks & Poor Landing PagesMediumCampaign ROAS by Attribution ModelHard
250 free problems · No credit card
See all Ad Tech problems