Researchelasticnetalzheimersshapclinical assessments
Researchers Predict 12-Month Cognitive and Functional Decline
8.6
In Communications Medicine (2026), researchers developed and validated ElasticNet models predicting 12-month MMSE and BADL scores using routine clinical assessments from the UK Minder study and external ADNI data. The cognitive model achieved MAE 1.84 (R² 0.74) and validated on 741 ADNI trajectories with MAE 2.19; the functional model achieved MAE 3.88 (R² 0.77). A clinician tool, Theia, provides SHAP explanations for deployment.
Key Points
- 1Predict 12-month MMSE and BADL outcomes from routine clinical assessments and demographics
- 2Demonstrate high accuracy for MMSE (MAE 1.84, R² 0.74) with ADNI external validation (MAE 2.19)
- 3Enable clinicians to generate personalized 12-month forecasts via Theia decision-support with SHAP explanations
Scoring Rationale
Strong external validation and interpretable tool drive high impact, limited by modest development sample and need for broader validation.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
250 free problems · No credit card
See all Health & Insurance problems
