[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117916-en":3,"doc-seo-117916-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117916,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",7,"Healthcare","Forecasting migraine with machine learning based on mobile phone diary and wearable data","Migraine involves unpredictable onset and functional impairment, motivating methods that can forecast attacks before symptoms fully develop. This study evaluates machine learning for predicting next-day migraine using preictal headache diary entries and simple physiology collected via a mobile health app and wearable biofeedback. In a prospective development and usability study, participants generated hundreds of diary records alongside wireless measurements of heart rate, peripheral skin temperature, and muscle tension. The best-performing random forest model reached moderate predictive performance in a hold-out dataset.","Original Article  \nForecasting migraine with machine learning based on mobile phone diary and wearable data  \nAnker Stubberud 1,2 , Sigrid Hegna Ingvaldsen 1,3,  \nEiliv Brenner4, Ingunn Winnberg4, Alexander Olsen2,3,5, Gøril Bruvik Gravdahl 1,2,4 , Manjit Singh Matharu 1,2,6 , Parashkev Nachev6 and Erling Tronvik 1,2,4  \nCephalalgia  \n2023, Vol. 43(5) 1–10  \n! International Headache Society 2023 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/03331024231169244](DOI: 10.1177/03331024231169244)[ ](DOI: 10.1177/03331024231169244)[journals.sagepub.com/home/cep](journals.sagepub.com/home/cep)  \nAbstract  \nIntroduction: Triggers, premonitory symptoms and physiological changes occur in the preictal migraine phase and maybe used in models for forecasting attacks. Machine learning is a promising option for such predictive analytics. The objective of this study was to explore the utility of machine learning to forecast migraine attacks based on preictal headache diary entries and simple physiological measurements.  \nMethods: In a prospective development and usability study 18 patients with migraine completed 388 headache diary entries and self-administered app-based biofeedback sessions wirelessly measuring heart rate, peripheral skin temperature and muscle tension. Several standard machine learning architectures were constructed to forecast headache the subsequent day. Models were scored with area under the receiver operating characteristics curve.  \nResults: Two-hundred-and-ninety-five days were included in the predictive modelling. The top performing model, based on random forest classification, achieved an area under the receiver operating characteristics curve of 0.62 in a hold-out partition of the dataset.  \nDiscussion: In this study we demonstrate the utility of using mobile health apps and wearables combined with machine learning to forecast headache. We argue that high-dimensional modelling may greatly improve forecasting and discuss important considerations for future design of forecasting models using machine learning and mobile health data.  \nKeywords  \nArtificial intelligence, random forest, boosting, prediction, headache, biofeedback  \nDate received: 2 December 2022; revised: 18 March 2023; accepted: 27 March 2023  \nIntroduction  \nMigraine is the leading cause for disability in the age range of 15–55 (1) and almost all sufferers experience functional impairment during the attack (2) . The disorder is for many unpredictive and the uncertainty of when a new attack occurs is associated with anxiety and further functional impairment (3) . The usual treatment strategy for migraines is to abort attacks after their occurrence or commence preventative treatmentsin order to reduce the frequency of attacks (4) . In addition, so-called preemptive treatment—in which drugs are administered specifically on days with increased risk of headache—is a promising option (5) . The notion of  \n1 Department of Neuromedicine and Movement Science, NTNU Norwegian University of Science and Technology, Trondheim, Norway 2NorHEAD, Norwegian Headache Research Centre, Norway 3Department of Psychology, NTNU Norwegian University of Science and Technology, Trondheim, Norway  \n4National Advisory Unit on Headaches, Department of Neurology and Clinical Neurophysiology, St. Olavs Hospital, Trondheim, Norway 5Department of Physical Medicine and Rehabilitation, St. Olavs Hospital, Trondheim, Norway  \n6UCL Queen Square Institute of Neurology, London, United Kingdom  \nCorresponding author:  \nAnker Stubberud, Department of Neuromedicine and Movement Science, NTNU Norwegian University of Science and Technology, Edvard Griegs gt 8, 7030, Trondheim, Norway.  \nEmail: [anker.stubberud@ntnu.no](anker.stubberud@ntnu.no)  \nCreative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License ([https://](https://)  \n[creativecommons.","cbCailgsvUCyoOHx","https://ap.wps.com/l/cbCailgsvUCyoOHx","pdf",840070,1,10,"English","en",105,"# Introduction\n## Migraine unpredictability and need for prediction\n## Triggers, premonitory symptoms, and physiological changes\n## Role of mHealth apps and wearables\n# Methods\n## Prospective development and usability study\n## Mobile app diary and wireless biofeedback measurements\n## Machine learning architectures and evaluation metric\n# Results\n## Dataset size for modelling\n## Best-performing model performance\n# Discussion\n## Utility of combining mobile health and wearables with machine learning\n## Considerations for future forecasting model design","[{\"question\":\"What data sources were used to forecast migraine attacks?\",\"answer\":\"The study used preictal headache diary entries plus physiological measurements collected with a mobile health app and wearables. Measurements included heart rate, peripheral skin temperature, and muscle tension.\"},{\"question\":\"How was the machine learning model evaluated?\",\"answer\":\"Models were scored using the area under the receiver operating characteristics curve (AUC-ROC). Performance was reported on a hold-out partition of the dataset.\"},{\"question\":\"Which model performed best and with what result?\",\"answer\":\"A random forest classification model produced the top performance. It achieved an AUC-ROC of 0.62 on the hold-out dataset.\"}]","Forecasting migraine with machine learning based on mobile phone diary and wearable data | PDF",1785680365,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"forecasting-migraine-with-machine-learning-based-on-mobile-phone-diary-and-wearable-data","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/forecasting-migraine-with-machine-learning-based-on-mobile-phone-diary-and-wearable-data/117916/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data sources were used to forecast migraine attacks?","Question",{"text":75,"@type":76},"The study used preictal headache diary entries plus physiological measurements collected with a mobile health app and wearables. Measurements included heart rate, peripheral skin temperature, and muscle tension.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the machine learning model evaluated?",{"text":80,"@type":76},"Models were scored using the area under the receiver operating characteristics curve (AUC-ROC). Performance was reported on a hold-out partition of the dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performed best and with what result?",{"text":84,"@type":76},"A random forest classification model produced the top performance. It achieved an AUC-ROC of 0.62 on the hold-out dataset.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]