About Us
Research Watch
•स्क्रिनमा देखिने चुरोट: सुर्तीजन्य हानि न्यूनीकरण नीतिमा दक्षिण एसियाले अझै के छुटाइरहेको छ•नेपालमा पिसाब नलीको संक्रमण र एन्टिबायोटिक प्रतिरोधको बढ्दो संकट•Frontline Perspectives on Nursing Leadership in Nepal•Protecting the Smallest Lungs from the Hidden Grip of RSV in Kathmandu•The Heavy Burden of Bullying on Student Wellbeing in Nepal•The Emerging Landscape of Thyroid Health in Central Nepal•How a Recent Western Nepal Study is Redefining Anemia Diagnosis•How H. Pylori is Impacting the Health of Karnali’s High-Altitude Communities•Sweet Poison, Bitter Reality: The Unseen Diabetes Epidemic Among Nepal’s Youth•How Missing Checklists and Protocols are Costing Lives in Nepal’s ERs•स्क्रिनमा देखिने चुरोट: सुर्तीजन्य हानि न्यूनीकरण नीतिमा दक्षिण एसियाले अझै के छुटाइरहेको छ•नेपालमा पिसाब नलीको संक्रमण र एन्टिबायोटिक प्रतिरोधको बढ्दो संकट•Frontline Perspectives on Nursing Leadership in Nepal•Protecting the Smallest Lungs from the Hidden Grip of RSV in Kathmandu•The Heavy Burden of Bullying on Student Wellbeing in Nepal•The Emerging Landscape of Thyroid Health in Central Nepal•How a Recent Western Nepal Study is Redefining Anemia Diagnosis•How H. Pylori is Impacting the Health of Karnali’s High-Altitude Communities•Sweet Poison, Bitter Reality: The Unseen Diabetes Epidemic Among Nepal’s Youth•How Missing Checklists and Protocols are Costing Lives in Nepal’s ERs

Characterizing cognitive concerns in subjective cognitive decline using large language models and electronic health record notes.

Researchers

Taiyang Chen, Justin Wang, Sheril Varghese, Jiazi Tian, Rebecca E Amariglio, Li Zhou, Gad A Marshall, Liqin Wang

Abstract

Subjective cognitive decline (SCD) refers to self- or informant-reported cognitive concerns despite normal objective testing. These concerns are often documented as free text in electronic health records (EHRs), limiting systematic analysis. We characterized cognitive concern domains and assessed differences across demographic subgroups. We studied 2175 individuals aged ≥65 years with an EHR-derived SCD phenotype. Using large language models with expert review, we derived a taxonomy of concern themes and sub-themes and assigned themes to note excerpts. We examined theme frequencies and compared distribution across demographic groups. We identified 13 themes and 40 sub-themes. Theme-level classification showed strong performance (micro-F1 = 84.8%). Memory Issues was the most common theme (68.5%), with concerns spanning multiple cognitive domains. Theme distribution varied by age, sex, marital status, and education. EHR notes captured heterogeneous, multi-domain cognitive concerns among adults with an EHR-derived SCD phenotype. This approach enables scalable, clinically interpretable profiling of concerns that may support early risk stratification.
Source: PubMed (PMID: 42973460)View Original on PubMed