Optimizing scalable approaches for early detection of cognitive impairment in primary care

Unrecognized cognitive impairment remains common in primary care, delaying access to care.

We conducted a prospective cross-sectional study to evaluate a multimodal screening approach combining a passive digital marker (PDM) from electronic health records with the Quick Dementia Rating System (QDRS).

Individually, each method showed limited discrimination (area under the curve [AUC] 0.61-0.62). The combined model, incorporating PDM, QDRS, and comorbidity context, improved performance (AUC 0.79; sensitivity 0.75; specificity 0.71). Decision curve analysis showed a net benefit of 0.5 at a 50% risk threshold, corresponding to a modest increase in correctly identified cases relative to alternative screening strategies.

This low-burden, scalable multimodal approach improves detection of cognitive impairment, including mild cognitive impairment and Alzheimer's disease and related dementias, and may support improved risk stratification and referral prioritization in primary care.