Search

BACKGROUND Electronic Health Records (EHR) with large sample sizes and rich information offer great potential for dementia research but current methods of phenotyping cognitive status are not scalable. OBJECTIVE To evaluate whether Natural Language Processing (NLP)-powered semi-automated annotation can improve the speed and interrater reliability of chart reviews for phenotyping cognitive status METHODS In this diagnostic study, we developed and evaluated a semi-automated NLP-powered annotation tool (NAT) to facilitate phenotyping of cognitive status. Clinical experts adjudicated the cognitive status of 627 patients at Mass General Brigham (MGB) Healthcare using NAT or traditional chart reviews. Patient charts contained EHR data from two datasets: (1) Records from January 1, 2017 to December 31, 2018 for 100 Medicare beneficiaries from the MGB Accountable Care Organization (ACO), and (2) Records from 2-years pre-COVID diagnosis to the date of COVID diagnosis for 527 MGB patients. All EHR data from the relevant period were extracted; diagnosis codes, medications, and laboratory test values were processed and summarized; clinical notes were processed through an NLP pipeline; and a web tool was developed to present an integrated view of all data. Cognitive status was rated as cognitively normal, cognitively impaired, or undetermined. Assessment time and interrater agreement of NAT compared to manual chart reviews for cognitive status phenotyping was evaluated. RESULTS NAT adjudication provided higher interrater agreement (Cohen k=0.89 vs. k=0.80) and significant speed up (time difference mean [SD]: 1.4 [1.3] minutes, P < 0.001; ratio median [min, max]: 2.2 [0.4, 20]) over manual chart reviews. There was moderate agreement with manual chart reviews (Cohen k=0.67). In the cases that exhibited disagreement with manual chart review, NAT adjudication was able to produce assessments that had broader clinical consensus due to its integrated view of highlighted relevant information and semi-automated NLP features. CONCLUSIONS NAT adjudication improves the speed and interrater reliability for phenotyping cognitive status compared to manual chart reviews. This study underscores the potential of an NLP-based clinically adjudicated method to build large-scale dementia research cohorts from EHR.

Objective. To create an IPE course that improved knowledge related to HIV history, prevention, and therapy, in health professions students and improved their interest and confidence in becoming interprofessional collaborative clinicians, specifically involved in the care of people living with HIV. Methods. A motivational design framework was used to create an interprofessional course that incorporated whole-task complex scenarios, team-based application, and experiential components. Multiple sources of quantitative and qualitative data, including the AIDS Education and Training Center evaluation tool and Interprofessional Collaborative Competency Attainment Scale instrument, as well as assignments and course evaluations, were collected and analyzed. Results. Fifteen students from medicine, nursing, and pharmacy participated in 2017, and 21 students from medicine, nursing, pharmacy, and social work participated in 2018. In both offerings, students rated the course experience positively and self-reported increases in confidence related to interprofessional competencies. Ninety-three percent and 68% of the students in 2017 and 2018, respectively, stated they planned to be involved in HIV care to some degree in the future. Students demonstrated high levels of knowledge of the AIDS Training & Education Center National HIV Curriculum at the end of the 2018 course offering. Conclusion. This educational course design provided an effective interprofessional learning experience and establishes a sustainable interprofessional format for teaching health professions students about HIV.