Search

ObjectiveWe aimed to discover computationally-derived phenotypes of opioid-related patient presentations to the ED via clinical notes and structured electronic health record (EHR) data.MethodsThis was a retrospective study of ED visits from 2013-2020 across ten sites within a regional healthcare network. We derived phenotypes from visits for patients ≥18 years of age with at least one prior or current documentation of an opioid-related diagnosis. Natural language processing was used to extract clinical entities from notes, which were combined with structured data within the EHR to create a set of features. We performed latent dirichlet allocation to identify topics within these features. Groups of patient presentations with similar attributes were identified by cluster analysis.ResultsIn total 82,577 ED visits met inclusion criteria. The 30 topics were discovered ranging from those related to substance use disorder, chronic conditions, mental health, and medical management. Clustering on these topics identified nine unique cohorts with one-year survivals ranging from 84.2-96.8%, rates of one-year ED returns from 9-34%, rates of one-year opioid event 10-17%, rates of medications for opioid use disorder from 17-43%, and a median Carlson comorbidity index of 2-8. Two cohorts of phenotypes were identified related to chronic substance use disorder, or acute overdose.ConclusionsOur results indicate distinct phenotypic clusters with varying patient-oriented outcomes which provide future targets better allocation of resources and therapeutics. This highlights the heterogeneity of the overall population, and the need to develop targeted interventions for each population.

OBJECTIVES/SPECIFIC AIMS: 1. To assess the acceptability and feasibility and of an online self-assessment version of the Community REsearch Activity Assessment Tool (CREAT), an instrument to measure research capacity of CBOs. 2. To elicit CBO perspectives on their research and knowledge generation activities. METHODS/STUDY POPULATION: Thirteen CBOs who had previously partnered with an academic course on practice-based community health research were contacted and asked to participate in the field testing of the CREAT and provide feedback on areas of strength and areas for potential improvement. Eleven organizations completed the field testing, which began and ended with an in-person semi-structured interview with the online self-administration of the CREAT in the middle. The semi-structured interviews were audio-recorded with questions pertaining to topics such as: strengths and challenges of previous academic research partnerships, perceptions around the importance of research within the organization, thoughts and reactions to the CREAT, and general feedback about the CREAT. Results from the self-administered CREAT were used to test a scoring algorithm. Semi-structured interviews are being transcribed, pre-post responses to questions of strengths and challenges in engaging in research partnerships will be compared, and overall qualitative transcripts will be coded using grounded theory. RESULTS/ANTICIPATED RESULTS: Anticipated Results: The CREAT was acceptable and self-administration was feasible. Average time for completion of the online CREAT was 41 ± 13 min, and respondents did not need assistance from the interviewer to complete the online instrument. Suggestions for improvements focused on word choices and scale options. Respondents were aware of the importance of research activities for their CBOs, particularly for optimizing programmatic quality and services. Access to staff and financial resources were key barriers to strengthening research capacity, and respondents noted that engaging in research partnerships can also bring in additional resources. Interview transcription is still in progress along with the refinement of the codebook for the qualitative data collected. In alignment with objectives/goals outlined above, the results will be separated into the following four sections: CBO Research and Knowledge Generation Activities, Acceptability of the Tool, Feasibility of the Tool, and Refinement of the Tool. DISCUSSION/SIGNIFICANCE OF IMPACT: The online, self-administered CREAT instrument is acceptable and feasible for CBO respondents. Availability of a validated tool to assess research capacity of CBOs, developed and refined with input from community researchers, will support targeted research capacity building for CTSAs, community organizations and partners, thus strengthening collaborations. Translational scientists, public health systems and community health improvement depend on CBOs as partners in community-engaged research (CEnR). The CREAT will allow community members to more fully contribute their expertise to the development, implementation and evaluation of interventions, and to develop more equitable partnerships with researchers.