Artificial intelligence in headache medicine: between automation and the doctor-patient relationship. A systematic review
Bibliographic record
Abstract
BACKGROUND: Headache disorders, particularly migraine, are highly prevalent, but often remain underdiagnosed and undertreated. Artificial intelligence (AI) offers promising applications in diagnosis, prediction of attacks, analysis of neuroimaging and neurophysiology data, and treatment selection. Its use in headache medicine raises ethical, regulatory, and clinical questions, including its impact on the doctor-patient relationship. METHODS: A systematic literature search was conducted on April 10, 2025, across PubMed, Cochrane Library, Scopus, Web of Science, and DOAJ, following PRISMA guidelines. Two reviewers independently applied strict inclusion criteria to select studies published from 2000 to 2025 in either English or Spanish. Risk of bias was assessed using validated tools tailored to study design, including the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), Prediction Model Risk of Bias Assessment Tool (PROBAST), Newcastle-Ottawa Scale (NOS), and Appraisal Tool for Cross-Sectional Studies (AXIS). RESULTS: A total of 76 studies were included in the qualitative synthesis. The analysis covered AI methodologies, clinical applications, patient perspectives, and ethical implications. AI tools have shown potential to improve diagnostic accuracy, headache subtype classification, and prediction of treatment response, and may help reduce the administrative burden in clinical practice. Emerging technologies such as digital twins, wearable biomarker monitoring, and synthetic data generation support personalized approaches and may reshape clinical research. However, significant challenges remain. These include data quality, model interpretability, algorithmic bias, privacy concerns, and regulatory gaps. Moreover, the evidence base is still developing, with expectations often exceeding the strength of available clinical data. Many studies present methodological limitations due to small sample sizes, selection bias, and lack of external validation, which limit their generalizability to real-world settings. Finally, concerns about depersonalization and transparency affect patient trust in AI, reinforcing the need for both human oversight and a patient-centered approach. CONCLUSIONS: AI holds promise for improving headache care, but evidence supporting its clinical utility is still limited. Integration into practice must be rigorously validated, ethically guided, and carefully designed to prevent depersonalization. Human oversight remains essential as AI should complement, not replace, clinical judgment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.109 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.006 |
| Bibliometrics | 0.010 | 0.010 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".