{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T17:55:07Z","timestamp":1794246907577,"version":"4.9.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NTNU Norwegian University of Science and Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Headache Pain"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Machine learning provides a powerful framework to model the complex patterns underlying migraine attack onset from real-world high dimensional datasets. In this study, we used machine learning to forecast headache days using mobile health (mHealth) data from a migraine biofeedback treatment app.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>This was a machine learning analysis of data from the BioCer clinical trial (NCT05616741) evaluating app-based biofeedback for preventive treatment of episodic migraine. Participants completed three months of daily biofeedback sessions with wearables measuring trapezius muscle tension, heart rate variability, and peripheral skin temperature. Input data for the models included summary metrics from the biofeedback sessions and daily headache diary entries. The outcome of interest was the presence of a moderate-to-severe headache (defined as an intensity of 4 or higher on an 11-point scale of 0\u201310) on the next calendar day and the next three calendar days. The dataset was randomly split into training, validation, and test sets. Multiple standard machine learning architectures, foundation models, and time-series models were trained and optimized using the area under the receiver operating characteristics curve (AUC) as the primary scoring metric. Among these three classes of machine learning models, the best optimized model in each class identified during training was applied on the unseen test set. Permutation feature importance (PFI) was created for model explainability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>146 individuals, with a total of 21,550 headache days, were included in the forecasting models. For the next calendar day predictions, the top performing standard machine learning approach (decision tree) and foundation model achieved a test set AUC of 0.59 (95% CI 0.56 to 0.61) and 0.55 (95% CI 0.55 to 0.56), respectively. The best time-series model achieved a test set AUC of 0.84 (95% CI 0.82 to 0.85). For the three-calendar day forecasting window, the test set performances were 0.55 (95% CI 0.53 to 0.56), 0.55 (95% CI 0.54 to 0.57), and 0.76 (95% CI 0.74 to 0.77), respectively. The most important features were headache intensity, duration of the headache, and heart rate scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Time-series machine learning models using a relatively large dataset could forecast moderate-to-severe headaches with good accuracy in patients with episodic migraine.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s10194-026-02346-7","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T16:25:10Z","timestamp":1774887910000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Forecasting migraine with time-series machine learning from mobile health data"],"prefix":"10.1186","volume":"27","author":[{"given":"Fahim","family":"Faisal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amalie C.","family":"Poole","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonios","family":"Danelakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tore","family":"Wergeland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marte","family":"Bj\u00f8rk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrej N.","family":"Khanevski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Espen Saxhaug","family":"Kristoffersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tja\u0161a","family":"Kumelj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iben C. K.","family":"Larsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oda V.","family":"Lunder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjit","family":"Matharu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parashkev","family":"Nachev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melanie R.","family":"Simpson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erling","family":"Tronvik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kjersti G.","family":"Vetvik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bendik S.","family":"Winsvold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lise R.","family":"\u00d8ie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ane B.","family":"\u00d8vrevik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anker","family":"Stubberud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"2346_CR1","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1111\/j.1526-4610.2007.01004.x","volume":"48","author":"JL Brandes","year":"2008","unstructured":"Brandes JL (2008) The Migraine Cycle: Patient Burden of Migraine During and Between Migraine Attacks. Headache 48:430\u2013441","journal-title":"Headache"},{"key":"2346_CR2","doi-asserted-by":"publisher","first-page":"1032103","DOI":"10.3389\/fneur.2022.1032103","volume":"13","author":"M Vincent","year":"2022","unstructured":"Vincent M, Viktrup L, Nicholson RA, Ossipov MH, Vargas BB (2022) The not so hidden impact of interictal burden in migraine: A narrative review. Front Neurol 13:1032103","journal-title":"Front Neurol"},{"key":"2346_CR3","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1136\/jnnp-2015-312233","volume":"87","author":"MT Minen","year":"2016","unstructured":"Minen MT et al (2016) Migraine and its psychiatric comorbidities. J Neurol Neurosurg Psychiatry 87:741\u2013749","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"2346_CR4","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1046\/j.1468-2982.2003.00546.x","volume":"23","author":"R Lipton","year":"2003","unstructured":"Lipton R et al (2003) Migraine Headache Disability and Health-Related Quality-of-life: A Population-Based Case-Control Study from England. Cephalalgia 23:441\u2013450","journal-title":"Cephalalgia"},{"key":"2346_CR5","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1177\/0333102418789072","volume":"38","author":"DC Buse","year":"2018","unstructured":"Buse DC et al (2018) Migraine-related disability, impact, and health-related quality of life among patients with episodic migraine receiving preventive treatment with erenumab. Cephalalgia 38:1622\u20131631","journal-title":"Cephalalgia"},{"key":"2346_CR6","doi-asserted-by":"publisher","first-page":"033310242412682","DOI":"10.1177\/03331024241268290","volume":"44","author":"A Stubberud","year":"2024","unstructured":"Stubberud A, Langseth H, Nachev P, Matharu MS, Tronvik E (2024) Artificial intelligence and headache. Cephalalgia 44:03331024241268290","journal-title":"Cephalalgia"},{"key":"2346_CR7","doi-asserted-by":"publisher","first-page":"033310242513912","DOI":"10.1177\/03331024251391207","volume":"45","author":"G Dumkrieger","year":"2025","unstructured":"Dumkrieger G (2025) The promise of machine learning in predicting migraine attacks. Cephalalgia 45:03331024251391207","journal-title":"Cephalalgia"},{"key":"2346_CR8","doi-asserted-by":"publisher","first-page":"033310242311692","DOI":"10.1177\/03331024231169244","volume":"43","author":"A Stubberud","year":"2023","unstructured":"Stubberud A et al (2023) Forecasting migraine with machine learning based on mobile phone diary and wearable data. Cephalalgia 43:033310242311692","journal-title":"Cephalalgia"},{"key":"2346_CR9","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1111\/head.14482","volume":"63","author":"M Katsuki","year":"2023","unstructured":"Katsuki M et al (2023) Investigating the effects of weather on headache occurrence using a smartphone application and artificial intelligence: A retrospective observational cross-sectional study. Headache 63:585\u2013600","journal-title":"Headache"},{"key":"2346_CR10","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1038\/s41582-018-0098-4","volume":"14","author":"N Karsan","year":"2018","unstructured":"Karsan N, Goadsby PJ (2018) Biological insights from the premonitory symptoms of migraine. Nat Rev Neurol 14:699\u2013710","journal-title":"Nat Rev Neurol"},{"key":"2346_CR11","doi-asserted-by":"crossref","unstructured":"Chrisitine Poole A et al (2025) Biofeedback therapy using Cerebri for the prevention of migraine attacks in adults with episodic migraine (BioCer): a randomized, wait-list controlled trial \u2013 the study protocol. F1000Res. 13, PMID: 40909914; PMCID: PMC12405843","DOI":"10.12688\/f1000research.149807.2"},{"key":"2346_CR12","doi-asserted-by":"crossref","unstructured":"Buuren SV, Groothuis-Oudshoorn K (2011) Mice: multivariate imputation by chained equations in R. J Stat Soft 45","DOI":"10.18637\/jss.v045.i03"},{"key":"2346_CR13","doi-asserted-by":"publisher","first-page":"48","DOI":"10.62087\/hpr.2024.0024","volume":"26","author":"W Lee","year":"2025","unstructured":"Lee W, Chu MK (2025) The Current Role of Artificial Intelligence in the Field of Headache Disorders, with a Focus on Migraine: A Systemic Review. Headache Pain Res 26:48\u201365","journal-title":"Headache Pain Res"},{"key":"2346_CR14","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.3390\/s18051374","volume":"18","author":"P Siirtola","year":"2018","unstructured":"Siirtola P, Koskim\u00e4ki H, M\u00f6nttinen H, R\u00f6ning J (2018) Using Sleep Time Data from Wearable Sensors for Early Detection of Migraine Attacks. Sensors 18:1374","journal-title":"Sensors"},{"key":"2346_CR15","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1111\/head.13137","volume":"57","author":"TT Houle","year":"2017","unstructured":"Houle TT et al (2017) Forecasting Individual Headache Attacks Using Perceived Stress: Development of a Multivariable Prediction Model for Persons With Episodic Migraine. Headache 57:1041\u20131050","journal-title":"Headache"},{"key":"2346_CR16","doi-asserted-by":"publisher","unstructured":"Hestness J et al (2017) Deep learning scaling is predictable, empirically. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.1712.00409","DOI":"10.48550\/ARXIV.1712.00409"},{"key":"2346_CR17","doi-asserted-by":"publisher","unstructured":"Kaplan J et al (2020) Scaling laws for neural language models. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2001.08361","DOI":"10.48550\/ARXIV.2001.08361"},{"key":"2346_CR18","doi-asserted-by":"publisher","unstructured":"Bahri Y, Dyer E, Kaplan J, Lee J, Sharma U (2021) Explaining neural scaling laws. https:\/\/doi.org\/10.48550\/ARXIV.2102.06701","DOI":"10.48550\/ARXIV.2102.06701"},{"key":"2346_CR19","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","volume":"37","author":"B Lim","year":"2021","unstructured":"Lim B, Ar\u0131k S\u00d6, Loeff N, Pfister T (2021) Temporal Fusion Transformers for interpretable multi-horizon time series forecasting. Int J Forecast 37:1748\u20131764","journal-title":"Int J Forecast"},{"key":"2346_CR20","doi-asserted-by":"publisher","unstructured":"Wen Q et al (2022) Transformers in time series: a survey. https:\/\/doi.org\/10.48550\/ARXIV.2202.07125","DOI":"10.48550\/ARXIV.2202.07125"},{"key":"2346_CR21","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1177\/0333102419898868","volume":"40","author":"K-P Peng","year":"2020","unstructured":"Peng K-P, May A (2020) Redefining migraine phases \u2013 a suggestion based on clinical, physiological, and functional imaging evidence. Cephalalgia 40:866\u2013870","journal-title":"Cephalalgia"},{"key":"2346_CR22","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1152\/physrev.00034.2015","volume":"97","author":"PJ Goadsby","year":"2017","unstructured":"Goadsby PJ et al (2017) Pathophysiology of Migraine: A Disorder of Sensory Processing. Physiol Rev 97:553\u2013622","journal-title":"Physiol Rev"},{"key":"2346_CR23","doi-asserted-by":"publisher","first-page":"033310242412872","DOI":"10.1177\/03331024241287224","volume":"44","author":"G Sebastianelli","year":"2024","unstructured":"Sebastianelli G et al (2024) Insights from triggers and prodromal symptoms on how migraine attacks start: The threshold hypothesis. Cephalalgia 44:03331024241287224","journal-title":"Cephalalgia"},{"key":"2346_CR24","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s10194-022-01510-z","volume":"23","author":"AK Eigenbrodt","year":"2022","unstructured":"Eigenbrodt AK et al (2022) Premonitory symptoms in migraine: a systematic review and meta-analysis of observational studies reporting prevalence or relative frequency. J Headache Pain 23:140","journal-title":"J Headache Pain"},{"key":"2346_CR25","doi-asserted-by":"publisher","first-page":"1036798","DOI":"10.3389\/fneur.2022.1036798","volume":"13","author":"JC Ray","year":"2022","unstructured":"Ray JC et al (2022) Autonomic symptoms in migraine: Results of a prospective longitudinal study. Front Neurol 13:1036798","journal-title":"Front Neurol"},{"key":"2346_CR26","doi-asserted-by":"publisher","first-page":"128","DOI":"10.31083\/j.jin2307128","volume":"23","author":"D D\u2019Agnano","year":"2024","unstructured":"D\u2019Agnano D et al (2024) The role of the autonomic nervous system in epilepsy and migraine: a narrative review. J Integr Neurosci 23:128","journal-title":"J Integr Neurosci"},{"key":"2346_CR27","doi-asserted-by":"publisher","first-page":"033310242513486","DOI":"10.1177\/03331024251348651","volume":"45","author":"A Stubberud","year":"2025","unstructured":"Stubberud A, Linde M, Tronvik E (2025) A narrative review of app- and internet-delivered headache interventions: From ideation to implementation and the future. Cephalalgia 45:03331024251348651","journal-title":"Cephalalgia"},{"key":"2346_CR28","doi-asserted-by":"publisher","first-page":"e15182","DOI":"10.2196\/15182","volume":"8","author":"MP Sendak","year":"2020","unstructured":"Sendak MP, Ratliff W, Sarro D, Alderton E (2020) Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study. JMIR Med Inf 8:e15182","journal-title":"JMIR Med Inf"},{"key":"2346_CR29","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-020-0253-3","volume":"3","author":"MP Sendak","year":"2020","unstructured":"Sendak MP, Gao M, Brajer N, Balu S (2020) Presenting machine learning model information to clinical end users with model facts labels. npj Digit Med 3:41","journal-title":"npj Digit Med"},{"key":"2346_CR30","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1186\/s12911-025-03107-3","volume":"25","author":"H Van Dung","year":"2025","unstructured":"Van Dung H et al (2025) Development and external validation of a machine learning model for predicting drug-induced immune thrombocytopenia in a real-world hospital cohort. BMC Med Inf Decis Mak 25:265","journal-title":"BMC Med Inf Decis Mak"}],"container-title":["The Journal of Headache and Pain"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s10194-026-02346-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s10194-026-02346-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s10194-026-02346-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:45:38Z","timestamp":1774943138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s10194-026-02346-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2346"],"URL":"https:\/\/doi.org\/10.1186\/s10194-026-02346-7","relation":{},"ISSN":["1129-2377"],"issn-type":[{"value":"1129-2377","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"17 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Regional Committee for Medical and Health Research (REK 502734 and REK 574937) and the Norwegian Medical Product Agency (NOMA) (ref 22\/17254-5).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"FF, AD, ANK, ESK, TK, ICL, OVL, MRS, BSW, LR\u00d8 and AB\u00d8 declare no conflict of interest related to this work. ACP has received travel grants from TEVA, AbbVie and Pfizer, and is a clinical study investigator in a trial sponsored by AbbVie (not related to present study). TW reports research grants from The Liaison Committee for Education, Research and Innovation in Central Norway (Samarbeidsorganet) and The DAM Foundation. He has received lecture honoraria from TEVA, Roche, LUNDBECK and Lilly, and is a shareholder in two medical device start-up companies (Vilje Bionics AS and Keimon Medical AS). MHB reports advisory board participation and\/or speaking honoraria from Pfizer, Jazz Pharmaceuticals, Angelini Pharma, AbbVie, Lundbeck, Organon, Teva, and Eisai. Her institution and research group have received funding from valproate marketing authorisation holders for post-marketing safety studies, and from Lundbeck for a phase IV eptinezumab study. She is supported by the Research Council of Norway (grant 328615) and the Trond Mohn Foundation (grant TMF2024TMT03). MSM has served on advisory boards for AbbVie, Eli Lilly, Pfizer, Salvia and TEVA; has received payment for educational presentations from AbbVie, Eli Lilly, Organon and TEVA; has received grants from Abbott and Ehlers Danlos Society; stocks in Keilon Medical; and has a patent on system and method for diagnosing and treating headaches (WO2018051103A1, issued). PN is a shareholder in Hologen. ET has received personal fees for lectures\/advisory boards: Novartis, Eli Lilly, Abbvie, TEVA, Roche, Lundbeck, Pfizer, Biogen. Consultant for and owner of stocks and IP in Man & Science. Stocks and IP in Nordic Brain Tech and Keimon Medical. Non-personal research grants from several sources, including EU, Norwegian Research Council, Dam foundation, KlinBeForsk. Commissioned research (non-personal): Lundbeck, Eli-Lilly. KGV reports advisory board participation and\/or speaking honoraria from Pfizer, AbbVie, Lundbeck, Organon, Teva and Novartis. AS has received lecture honoraria from TEVA. AS is share-holder and patent holder of Nordic Brain Tech AS and the Cerebri app.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"91"}}