Abstract Details

Title A Transformer-based Model for Dementia Classification Using a Limited EHR Feature Set from Annual Wellness Visits

Topic Aging, Dementia, and Behavioral Neurology

Presentation(s) P8 - Poster Session 8 (11:45 AM-12:45 PM)

Poster/Presentation
Number 12-003

Objective

To develop and validate a transformer-based AI model that accurately screens for dementia and mild cognitive impairment (MCI) using a targeted feature set from routine Medicare Annual Wellness Visit (AWV) electronic health records.

Background Dementia diagnosis is often delayed in primary care, leading to poor outcomes. While complex AI models achieve high accuracy, they require hundreds of features from specialist workups, making them impractical for frontline screening. The Medicare AWV, conducted over 9 million times annually, represents a unique opportunity for scalable, early detection by leveraging its limited, routinely collected data.

Design/Methods We developed an AI model to operate on a streamlined set of approximately 50 features consistently documented during AWVs, including demographics, medical history, and cognitive screening results. The model was validated on a publicly available dataset of 5,000 patient records (ages 50-89) from the National Alzheimer’s Coordinating Center (NACC). This large, multi-center dataset served as a robust proxy for real-world clinical data.

Results Despite the constrained feature set, the model performed well. For dementia (DE) classification, it achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.98 and 0.92 accuracy. Furthermore, it demonstrated a high sensitivity of 0.92 and specificity of 0.93 for dementia classification, balancing case identification with a low false-positive rate. For normal cognition (NC), it achieved an AUROC of 0.95. Performance for identifying MCI was moderate (AUROC: 0.86), reflecting the clinical difficulty of this transitional state.

Conclusions This AI framework demonstrates excellent screening accuracy using only limited AWV data, offering a practical and scalable tool to enhance early dementia detection in primary care. By helping to reduce diagnostic delays and facilitate timely specialist referrals, this approach can significantly improve patient care pathways. Ongoing prospective validation on local clinical data is underway to confirm these findings and move towards clinical implementation for identifying at-risk individuals sooner.

Authors/Disclosures
Avery Buehler PRESENTER	Mr. Buehler has nothing to disclose.
Vatsal Mitesh Tailor	Mr. Tailor has nothing to disclose.
Tamanna Dhore	Ms. Dhore has nothing to disclose.
Laya Krishnan, BS	Ms. Krishnan has nothing to disclose.
Sung Joon Won	Mr. Won has nothing to disclose.
Vijaya B. Kolachalama, PhD, FAHA (Boston University)	Vijaya B. Kolachalama, PhD, FAHA has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for The American Journal of Managed Care. Vijaya B. Kolachalama, PhD, FAHA has or had stock in Cognimark, Inc..Vijaya B. Kolachalama, PhD, FAHA has or had stock in deepPath Inc..
Suguna Pappu, MD, PhD	Dr. Pappu has nothing to disclose.
Aimee Yu-Ballard, MD	Dr. Yu-Ballard has nothing to disclose.
Sridhar o. Seshadri, PhD	Prof. Seshadri has received personal compensation for serving as an employee of University of Illinois. Prof. Seshadri has stock in Many companies.

��ɫ��

��ɫ��