{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-signature-based-machine-learning-model-for","title":"A signature-based machine learning model for bipolar disorder and borderline personality disorder","arxiv_id":"1707.07124","date":"2017-07-22","proceeding":null,"authors":["Imanol Perez Arribas","Kate Saunders","Guy Goodwin","Terry Lyons"],"abstract":"Mobile technologies offer opportunities for higher resolution monitoring of\nhealth conditions. This opportunity seems of particular promise in psychiatry\nwhere diagnoses often rely on retrospective and subjective recall of mood\nstates. However, getting actionable information from these rather complex time\nseries is challenging, and at present the implications for clinical care are\nlargely hypothetical. This research demonstrates that, with well chosen cohorts\n(of bipolar disorder, borderline personality disorder, and control) and modern\nmethods, it is possible to objectively learn to identify distinctive behaviour\nover short periods (20 reports) that effectively separate the cohorts.\nParticipants with bipolar disorder or borderline personality disorder and\nhealthy volunteers completed daily mood ratings using a bespoke smartphone app\nfor up to a year. A signature-based machine learning model was used to classify\nparticipants on the basis of the interrelationship between the different mood\nitems assessed and to predict subsequent mood. The signature methodology was\nsignificantly superior to earlier statistical approaches applied to this data\nin distinguishing the participant three groups, clearly placing 75% into their\noriginal groups on the basis of their reports. Subsequent mood ratings were\ncorrectly predicted with greater than 70% accuracy in all groups. Prediction of\nmood was most accurate in healthy volunteers (89-98%) compared to bipolar\ndisorder (82-90%) and borderline personality disorder (70-78%).","url_abs":"http://arxiv.org/abs/1707.07124v2","url_pdf":"http://arxiv.org/pdf/1707.07124v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-signature-based-machine-learning-model-for","repo_url":"https://github.com/alan-turing-institute/signatures-psychiatry","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.07124","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}