OBJECTIVE: Artificial intelligence (AI) is revolutionizing healthcare, but less is known about how it may facilitate methodological innovations in research settings. In this manuscript, we describe a novel use of AI in summarizing and reporting qualitative data generated from an expert panel discussion about the role of electronic health records (EHRs) in implementation science. MATERIALS AND METHODS: 15 implementation scientists participated in an hour-long expert panel discussion addressing how EHRs can support implementation strategies, measure implementation outcomes, and influence implementation science. Notes from the discussion were synthesized by ChatGPT (a large language model-LLM) to generate a manuscript summarizing the discussion, which was later revised by participants. We also surveyed participants on their experience with the process. RESULTS: Panelists identified implementation strategies and outcome measures that can be readily supported by EHRs and noted that implementation science will need to evolve to assess future EHR advancements. The ChatGPT-generated summary of the panel discussion was generally regarded as an efficient means to offer a high-level overview of the discussion, although participants felt it lacked nuance and context. Extensive editing was required to contextualize the LLM-generated text and situate it in relevant literature. DISCUSSION AND CONCLUSIONS: Our qualitative findings highlight the central role EHRs can play in supporting implementation science, which may require additional informatics and implementation expertise and a different way to think about the combined fields. Our experience using ChatGPT as a research methods innovation was mixed and underscores the need for close supervision and attentive human involvement.

Gulf War Illness (GWI), a chronic multisymptom illness with a complex and uncertain etiology and pathophysiology, is highly prevalent among veterans deployed to the 1990-1991 GW. We examined how GWI phenotypes varied by demographic and military characteristics among GW-era veterans. Data were from the VA's Cooperative Studies Program 2006/Million Veteran Program (MVP) 029 cohort, Genomics of GWI. From June 2018 to March 2019, 109,976 MVP enrollees (out of a total of over 676,000) were contacted to participate in the 1990-1991 GW-era Survey. Of 109,976 eligible participants, 45,169 (41.1%) responded to the 2018-2019 survey, 35,902 respondents met study inclusion criteria, 13,107 deployed to the GW theater. GWI phenotypes were derived from Kansas (KS) and Centers for Disease Control and Prevention (CDC) GWI definitions: (a) KS Symptoms (KS Sym+), (b) KS GWI (met symptom criteria and without exclusionary health conditions) [KS GWI: Sym+/Dx-], (c) CDC GWI and (d) CDC GWI Severe. The prevalence of each phenotype was 67.1% KS Sym+, 21.5% KS Sym+/Dx-, 81.1% CDC GWI, and 18.6% CDC GWI severe. These findings affirm the persistent presence of GWI among GW veterans providing a foundation for further exploration of biological and environmental underpinnings of this condition.