The utility of ChatGPT in the assessment of literature on the prevention of migraine: an observational, qualitative study.

Background: It is not known how large language models, such as ChatGPT, can be applied toward the assessment of the efficacy of medications, including in the prevention of migraine, and how it might support those claims with existing medical evidence. Methods: We queried ChatGPT-3.5 on the efficacy of 47 medications for the prevention of migraine and then asked it to give citations in support of its assessment. ChatGPT's evaluations were then compared to their FDA approval status for this indication as well as the American Academy of Neurology 2012 evidence-based guidelines for the prevention of migraine. The citations ChatGPT generated for these evaluations were then assessed to see if they were real papers and if they were relevant to the query. Results: ChatGPT affirmed that the 14 medications that have either received FDA approval for prevention of migraine or AAN Grade A/B evidence were effective for migraine. Its assessments of the other 33 medications were unreliable including suggesting possible efficacy for four medications that have never been used for the prevention of migraine. Critically, only 33/115 (29%) of the papers ChatGPT cited were real, while 76/115 (66%) were "hallucinated" not real papers and 6/115 (5%) shared the names of real papers but had not real citations. Conclusion: While ChatGPT produced tailored answers on the efficacy of the queried medications, the results were unreliable and inaccurate because of the overwhelming volume of "hallucinated" articles it generated and cited.

Reimagining Headache Fellowships.

In March of 2020, the COVID-19 pandemic led to drastic changes in clinical practice and teaching methods. This article relates the experience of developing an almost virtual headache fellowship in response to the pandemic.

Introducing the National Headache Fellowship Opportunities Website.

OBJECTIVE: To build a national Headache Medicine fellowship opportunities website that promotes a unified application timeline and a more transparent application process. BACKGROUND: In July 2019, the Consortium of Academic Headache Program Directors unanimously accepted the recommendations of the American Academy of Neurology Fellowship Application Timing Position Statement. To implement the unified application timeline, the American Headache Society agreed to host a fellowship opportunities website with information on the application process and resources for each fellowship program. METHODS: We designed a main landing page that features the unified timeline for applications and offers. The page also features icons for all participating US fellowship programs (identified using the United Council for Neurologic Subspecialties certification database). The icons serve as links to each fellowship program's individual webpage. We sent an electronic form to each fellowship program director, asking them to submit program information to be included on each fellowship program's individual webpage. Key contents on each program webpage include an image of the program, brief program description, names of applicants who have filled positions, and open positions. Each institution webpage also includes an electronic form that allows applicants to directly send their name, contact, and a brief message to the program director. RESULTS: We launched the website on May 15, 2020. As of June 19, 2020, the website featured 24 participating headache fellowship programs, including 5 pediatric programs and 19 adult training programs, from all regions of the US. CONCLUSION: The website serves as a central resource for Headache Medicine fellowship applicants and promotes a unified application timeline and a more transparent application process.

The state of the headache fellowship application process and attitudes toward the match.

OBJECTIVE: To examine the current headache medicine fellowship application process and to propose recommendations for a more unified, systematic, and transparent process. METHODS: We identified 42 headache fellowship programs using the United Council for Neurologic Subspecialties certification database. After an initial contact via e-mail, we conducted individual telephone interviews with program directors. Qualitative data coding allowed identification of emerging themes. Quantitative data were summarized with descriptive statistics. RESULTS: Forty (95%) program directors (34 adult, 6 pediatric) responded. Emerging themes included the following. (1) There are benefits and disadvantages to having a match. (2) If the match were reinstated, programs would participate only if all programs participated. (3) There should be consequences for programs that do not participate. If the match were reinstated, 37.5% of program directors responded that their program would participate without conditions; 37.5% would participate only if every program were required to participate. Fifteen percent would not participate, and 10% were not sure if they would participate. Forty percent supported sanctions against programs that did not participate in the match. CONCLUSION: The fellowship match potentially makes the process more systematic for both programs and applicants; however, it does not currently appear to be a feasible option for the field of headache medicine. Until the number of applicants exceeds the number of programs, we recommend instituting a universal timeline for applications and offers.