Natural language processing to identify social determinants of health in Alzheimer's disease and related dementia from electronic health records.

OBJECTIVE: To develop a natural language processing (NLP) algorithm that identifies social determinants of health (SDoH), including housing, transportation, food, and medication insecurities, social isolation, abuse, neglect, or exploitation, and financial difficulties for patients with Alzheimer's disease and related dementias (ADRD) from unstructured electronic health records (EHRs). DATA SOURCES AND STUDY SETTING: We leveraged 1000 medical notes randomly selected from 7401 emergency department and inpatient social worker notes generated between 2015 and 2019 for 231 unique patients diagnosed with ADRD at Michigan Medicine. STUDY DESIGN: We developed a rule-based NLP algorithm for the identification of seven domains of SDoH noted above. We also compared the rule-based algorithm with deep learning and regularized logistic regression approaches. These models were compared using accuracy, sensitivity, specificity, F1 score, and the area under the receiver operating characteristic curve (AUC). All notes were split into 700 notes for training NLP algorithms, and 300 notes for validation. DATA COLLECTION/EXTRACTION METHODS: Social worker notes used in this study were extracted from the Michigan Medicine EHR database. PRINCIPAL FINDINGS: Of the 700 notes for training, F1 and AUC for the rule-based algorithm were at least 0.94 and 0.95, respectively, for all SDoH categories. Of the 300 notes for validation, F1 and AUC were at least 0.80 and 0.97, respectively, for all SDoH except housing and medication insecurities. The deep learning and regularized logistic regression algorithms had unsatisfactory performance. CONCLUSIONS: The rule-based algorithm can accurately extract SDoH information in all seven domains of SDoH except housing and medication insecurities. Findings from the algorithm can be used by clinicians and social workers to proactively address social needs of patients with ADRD and other vulnerable patient populations.

Validation of EpiTRAQ, a transition readiness assessment tool for adolescents and young adults with epilepsy.

OBJECTIVE: To design and validate a transition readiness assessment tool for adolescents and young adults with epilepsy and without intellectual disability. METHODS: We adapted a general transition readiness assessment tool (TRAQ) to add epilepsy-relevant items based on concepts in current epilepsy quality measures. The adapted tool, EpiTRAQ, maintained the original structure and scoring system. Concurrent with clinical implementation in pediatric and adult epilepsy clinics at an academic medical center, we assessed the validity and reliability of this adapted tool for patients 16-26 years of age. This process included initial validation with 302 patients who completed EpiTRAQ between October 2017 and May 2018; repeat validation with 381 patients who completed EpiTRAQ between June 2018 and September 2019; and retest reliability among 153 patients with more than one completed EpiTRAQ. RESULTS: Mean scores were comparable between initial and repeat validation populations (absolute value differences between 0.05 and 0.1); internal consistency ranged from good to high. For both the initial and repeat validation, mean scores and internal consistency demonstrated high comparability to the original TRAQ validation results. Upon retest, few patients rated themselves with a lower score, while the majority rated themselves with higher scores. SIGNIFICANCE: EpiTRAQ is a valid and reliable tool for assessing transition readiness in adolescents and young adults with epilepsy and without intellectual disability.