Computerized migraine diagnostic tools: a systematic review

Abstract

Background: Computerized migraine diagnostic tools have been developed and validated since 1960. We conducted a systematic review to summarize and critically appraise the quality of all published studies involving computerized migraine diagnostic tools. Methods: We performed a systematic literature search using PubMed, Web of Science, Scopus, snowballing, and citation searching. Cutoff date for search was 1 June 2021. Published articles in English that evaluated a computerized/automated migraine diagnostic tool were included. The following summarized each study: publication year, digital tool name, development basis, sample size, sensitivity, specificity, reference diagnosis, strength, and limitations. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool was applied to evaluate the quality of included studies in terms of risk of bias and concern of applicability. Results: A total of 41 studies (median sample size: 288 participants, median age = 43 years; 77% women) were included. Most (60%) tools were developed based on International Classification of Headache Disorders criteria, half were self-administered, and 82% were evaluated using face-to-face interviews as reference diagnosis. Some of the automated algorithms and machine learning programs involved case-based reasoning, deep learning, classifier ensemble, ant-colony, artificial immune, random forest, white and black box combinations, and hybrid fuzzy expert systems. The median diagnostic accuracy was concordance = 89% [interquartile range (IQR) = 76–93%; range = 45–100%], sensitivity = 87% (IQR = 80–95%; range = 14–100%), and specificity = 90% (IQR = 77–96%; range = 65–100%). Lack of random patient sampling was observed in 95% of studies. Case–control designs were avoided in all studies. Most (76%) reference tests exhibited low risk of bias and low concern of applicability. Patient flow and timing showed low risk of bias in 83%. Conclusion: Different computerized and automated migraine diagnostic tools are available with varying accuracies. Random patient sampling, head-to-head comparison among tools, and generalizability to other headache diagnoses may improve their utility.

Diagnostic accuracy of an artificial intelligence online engine in migraine: A multi‐center study

“…An accurate computer‐based diagnostic tool can reduce inefficiencies in headache care and enable remote provision of headache management, leading to reduction in health‐care–related cost, shortening diagnostic delay, and improving access to care 79–83 . Accurate computer‐based migraine diagnosis can decrease rate of misdiagnosis (false positive/negative cases or over/underdiagnoses) and improve effectiveness of triage systems for headache consultations 25,79–81 . Reduction in false negative cases will be crucial for an early migraine diagnosis, avoiding diagnostic delay thereby minimizing the risk for progression to chronic migraine and medication overuse headache, which require more aggressive and expensive treatment 25,80,81 .…”

“…[79][80][81][82][83] Accurate computer-based migraine diagnosis can decrease rate of misdiagnosis (false positive/negative cases or over/underdiagnoses) and improve effectiveness of triage systems for headache consultations. 25,[79][80][81] Reduction in false negative cases will be crucial for an early migraine diagnosis, avoiding diagnostic delay thereby minimizing the risk for progression to chronic migraine and medication overuse headache, which require more aggressive and expensive treatment. 25,80,81 Additionally, it will help avoid anxiety of patients and their families about a missed migraine diagnosis.…”

“…25,[79][80][81] Reduction in false negative cases will be crucial for an early migraine diagnosis, avoiding diagnostic delay thereby minimizing the risk for progression to chronic migraine and medication overuse headache, which require more aggressive and expensive treatment. 25,80,81 Additionally, it will help avoid anxiety of patients and their families about a missed migraine diagnosis. 84 On the other hand, reduction in false positive cases will lessen the financial burden associated with unnecessary referral and costly medications, 79,81 lower the health-care resource waste, [79][80][81] as well as alleviate unnecessary cyberchondria (anxiety from misdiagnosis by digital tools) from patients and their families.…”

“…We conducted a systematic review of all published studies that evaluated computerized migraine diagnostic tools (41 studies since 1960). 25 In 1991, the first computer diagnosis based on the 1988 International Classification of Headache Disorders (ICHD-1) 26 and the 1962 Ad Hoc criteria 27 was compared to interview-based diagnosis by headache physicians and psychologists. 28 A 95.9% concordance rate was found between the interviewers and the computerized diagnosis 28 —both using the Ad Hoc criteria.…”

Artificial Intelligence and Migraine: Insights and Applications

“…High risk for chronification and increased treatment complexity are causes of delay in headache diagnosis, simply more than a decade. To reduce the inaccuracies and diagnostic delays, facilitate access, and continue care and remote management, some digital health applications are practical, such as health information technology, computerized expert systems or software, Internet of Medical Things, mobile health, telehealth and telemedicine, wearables, and robotic surgery (4,5). According to computing power improvement, availability of big data (derived from wearable health monitors and medical history), learning algorithms, and Artificial Intelligence (AI) can play a prominent role in healthcare and medicine (6).…”