Kim KM, et al. Korean J Radiol. 2022 Nov;23:e72. https://doi.org/10.3348/kjr.2022.0539

The application of artificial intelligence (AI) in the field of headache disorders, particularly migraine, is rapidly expanding, and AI has demonstrated significant potential for diagnosis, treatment, and research. This review examines the current role of AI in migraine management, categorizing AI applications into diagnosis and classification, assessment of treatment response, prediction of migraine attacks, and research. A systematic search of literature published between 2000 and 2024 was conducted, following PRISMA guidelines and utilizing the snowball technique. Of the 398 articles identified, along with five additional articles, 61 were finally reviewed. The results highlight promising AI applications, including the use of patient questionnaires, natural language processing, and imaging for migraine diagnosis, as well as predicting treatment responses and forecasting migraine attacks. Nonetheless, challenges remain in improving the accuracy, generalizability, validation, and clinical relevance of AI applications. Despite the substantial promise of AI for improving migraine management, it does not always guarantee better results than traditional methods. Careful consideration of the study design and method selection is crucial. Additionally, the interpretation of AI-generated results, particularly those from generative models, requires caution to avoid potential pitfalls.

Background: Clear guidelines for a patient with suspected COVID-19 infection are unavailable. Many countries rely on assessments through a national hotline or telecommunications, but this only adds to the burden of an already overwhelmed health care system. In this study, we developed an algorithm and a web application to help patients get screened. Objective: This study aims to aid the general public by developing a web-based application that helps patients decide when to seek medical care during a novel disease outbreak. Methods: The algorithm was developed via consultations with 6 physicians who directly screened, diagnosed, and/or treated patients with COVID-19. The algorithm mainly focused on when to test a patient in order to allocate limited resources more efficiently. The application was designed to be mobile-friendly and deployed on the web. We collected the application usage pattern data from March 1 to March 27, 2020. We evaluated the association between the usage pattern and the numbers of COVID-19 confirmed, screened, and mortality cases by access location and digital literacy by age group. Results: The algorithm used epidemiological factors, presence of fever, and other symptoms. In total, 83,460 users accessed the application 105,508 times. Despite the lack of advertisement, almost half of the users accessed the application from outside of Korea. Even though the digital literacy of the 60+ years age group is half of that of individuals in their 50s, the number of users in both groups was similar for our application. Conclusions: We developed an expert-opinion–based algorithm and web-based application for screening patients. This innovation can be helpful in circumstances where information on a novel disease is insufficient and may facilitate efficient medical resource allocation.

Background: The term ‘precision medicine’ encompasses strategies to optimize diagnosis and outcome prediction and to tailor treatment for individual patients, in consideration of their unique characteristics. The greater availability of multifaceted datasets and strategies to model such data have made precision medicine increasingly possible in recent years. Precision medicine is especially needed in the migraine field since the response to migraine treatments is not universal amongst all individuals with migraine. Objective: To provide a narrative review describing contributions to achieving precision medicine for migraine treatment. Methods: A search of PubMed for English language articles of human participants published from 2005 to January 2024 was conducted to identify articles that reported research contributing to precision medicine for migraine treatment. The published literature was categorized and summarized according to the type of data that were included: clinical phenotypes, genomics, proteomics, physiologic measures, and brain imaging. Results: Published studies have investigated characteristics associated with acute and preventive treatment responses, such as nonsteroidal anti-inflammatory drugs, triptans, onabotulinumtoxinA, and anti-calcitonin gene-related peptide monoclonal antibodies, in patients with episodic or chronic migraine. There is evidence that clinical, genetic, epigenetic, proteomic, physiologic, and brain imaging features might associate with migraine treatment outcomes, although inconsistencies for such findings clearly exist. Conclusions: The published literature suggests that there are clinical and biological features which associate with, and might be useful for predicting, migraine treatment responses. To achieve precision medicine for migraine treatment, further research is needed that validates and expands on existing findings and tests the accuracy and value of migraine treatment prediction models in clinical settings.