🤖 AI Summary
Early detection of Alzheimer’s disease (AD) remains challenging, particularly for ultra-early prediction more than a decade before clinical diagnosis. Method: Leveraging longitudinal free-text symptom descriptions from U.S. Veterans Affairs electronic health records (2004–2021), we systematically extracted and modeled temporal dynamics of ICD-10-CM–coded AD cases versus controls—focusing on symptom keywords such as “attention” and “speech.” Using a case–control design, we constructed symptom-term frequency panels and integrated four machine learning models, including XGBoost; model robustness was assessed via Hosmer–Lemeshow calibration tests and multi-subgroup analyses. Contribution/Results: The optimal model achieved a 10-year pre-diagnosis ROC-AUC of 0.997 with excellent calibration (p = 0.99) and consistent performance across age, sex, and racial subgroups. Symptom term frequencies rose significantly in cases starting 3–5 years pre-diagnosis (from ~10 to ≥40 terms/year), while remaining stable in controls (~10 terms/year). This work establishes a novel paradigm for ultra-early AD risk stratification based on EHR-derived symptom trajectory patterns.
📝 Abstract
Early prediction of Alzheimer's disease (AD) is crucial for timely intervention and treatment. This study aims to use machine learning approaches to analyze longitudinal electronic health records (EHRs) of patients with AD and identify signs and symptoms that can predict AD onset earlier. We used a case-control design with longitudinal EHRs from the U.S. Department of Veterans Affairs Veterans Health Administration (VHA) from 2004 to 2021. Cases were VHA patients with AD diagnosed after 1/1/2016 based on ICD-10-CM codes, matched 1:9 with controls by age, sex and clinical utilization with replacement. We used a panel of AD-related keywords and their occurrences over time in a patient's longitudinal EHRs as predictors for AD prediction with four machine learning models. We performed subgroup analyses by age, sex, and race/ethnicity, and validated the model in a hold-out and"unseen"VHA stations group. Model discrimination, calibration, and other relevant metrics were reported for predictions up to ten years before ICD-based diagnosis. The study population included 16,701 cases and 39,097 matched controls. The average number of AD-related keywords (e.g.,"concentration","speaking") per year increased rapidly for cases as diagnosis approached, from around 10 to over 40, while remaining flat at 10 for controls. The best model achieved high discriminative accuracy (ROCAUC 0.997) for predictions using data from at least ten years before ICD-based diagnoses. The model was well-calibrated (Hosmer-Lemeshow goodness-of-fit p-value = 0.99) and consistent across subgroups of age, sex and race/ethnicity, except for patients younger than 65 (ROCAUC 0.746). Machine learning models using AD-related keywords identified from EHR notes can predict future AD diagnoses, suggesting its potential use for identifying AD risk using EHR notes, offering an affordable way for early screening on large population.
