Early detection of cognitive impairment in primary care: a mixed-methods protocol integrating data from multiple sources (DENDRITE study)

Abstract

Globally, over half of cognitive impairment cases identified in population-based studies remain undetected, and up to 90% of mild cases go undiagnosed. This represents a major public health challenge with significant implications for ageing populations and health systems. The present protocol outlines the integration of clinical, multiomic, healthcare, social, environmental, voice, and behavioral data, using artificial intelligence and advance statistical modeling, to develop a predictive risk model for the preclinical detection of cognitive impairment in adults aged 55–70 years. This is an observational, multicenter, non-interventional study employing a convergent mixed-methods approach. The design combines a prospective quantitative phase with a qualitative one based on discussion groups. The study will be conducted across six Spanish regions and seven primary healthcare centers located in different geographic areas. Each center will recruit 150 cognitively unimpaired participants, resulting in a total sample of 1050 participants. In addition, a calibration group of 100 participants diagnosed with mild cognitive impairment will be included. This protocol has been developed in accordance with the STROBE guidelines to ensure methodological rigor, transparency, and reproducibility. This research aims to develop a simple, cost-effective, and actionable tool for early preclinical detection of individuals at risk of cognitive impairment, enabling its integration into primary care and supporting timely, targeted interventions. This approach has the potential to reduce diagnostic delays, optimize healthcare resources, and promote equitable access to timely interventions, ultimately improving population health and quality of life.