[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117253-en":3,"doc-seo-117253-105":29,"detail-sidebar-cat-0-en-105":94},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},117253,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Machine learning and big data for personalized epilepsy treatment - Dissertation","Finding an effective anti-seizure medication (ASM) with minimal side effects is a major challenge in epilepsy care. Patient characteristics can guide selection, yet about half of people do not achieve seizure freedom with the first ASM. Randomized controlled trials are the benchmark for efficacy, but may be limited for rare conditions. This research evaluates national Swedish register data and develops machine learning methods to support personalized medicine by modeling ASM use and retention as an aggregated indicator of efficacy and tolerability.","Machine learning and big data for personalized epilepsy treatment  \nSamuel Håkansson  \nDepartment of Clinical Neuroscience Institute of Neuroscience and Physiology Sahlgrenska Academy, University of Gothenburg  \nGothenburg 2023  \nCover illustration by DALL·E 2  \nMachine learning and big data for personalized epilepsy treatment © Samuel Håkansson 2023  \n[samuel.hakansson@gu.se](samuel.hakansson@gu.se)  \nISBN 978-91-8069-313-4 (PRINT)  \nISBN 978-91-8069-314-1 (PDF)  \nPrinted in Borås, Sweden 2023 Printed by Stema Specialtryck AB  \nTrycksak 3041 0234  \n- But what is a girl addicted to fun supposed to do Maddy Bishop  \nABSTRACT  \nFinding an effective anti-seizure medication (ASM) with minimal side effects is a challenge. Patient characteristics are used to guide treatment selection, but about half of the patients with epilepsy do not achieve seizure freedom with their first ASM. While randomized controlled trials are the gold standard for estimating treatment efficacy, they may not always be clinically relevant, especially for rare conditions. Registers are valuable sources of data because they can contain many patients, are accessible, and are updated regularly. The aim of the present research is to evaluate registers and develop machine learning algorithms for personalized medicine in epilepsy.  \nWe used prescriptions, in-and outpatient data, and mortality data from national Swedish registers to model ASM use of patients. As a bundled estimation of efficacy and tolerability, retention rate was used as the measure of outcome.  \nThe results indicate that using register data to estimate retention of ASMs is feasible and personalized ASM selection can potentially improve patient outcomes. Retention rates from registers are similar to that of RCTs and meta-analyses of RCTs. In an analysis of patients with epilepsy and comorbidities, there was a potential improvement of 14-21% of the 5-year retention rate for the initial ASM (Paper I). Ranking of ASMs for patient cases based on retention rates from register data is similar to suggestions based on expert advice (Paper II) . We also studied ASM use in children, a group with limited evidence (Paper III) . Specialized machine learning algorithms can potentially be a useful source of information for doctors for selecting ASMs (Paper IV) .  \nIn conclusion, this research highlights the potential of registers as a data source for personalized medicine. Machine learning trained on register data can be used to predict the efficacy of ASMs, but the methodology needs further development and clinical verification.  \nKeywords: anti-seizure medication, personalized treatment, machine learning  \nSAMMANFATTNING PÅ SVENSKA  \nEpilepsi behandlas oftast med antiepileptika. Men att hitta rätt medicin som minskar risken för anfall och samtidigt ger så få biverkningar som möjligt ärsvårt. Val av antiepileptikum grundas på bland annat ålder, kön, typ avepilepsi och samjuklighet, men trots det blir hälften av alla patienter inteanfallsfria av första testade antiepileptikum. Randomiserade kontrolleradestudier (RCT) anses vara det bästa underlaget för att bedömma effekt av mediciner, men det är inte alltid de är kliniskt relevanta, speciellt förovanliga tillstånd eller syndrom. Register är värdefulla datakällor eftersomatt de har information om många patienter, är tillgängliga, och uppdateras regelbundet. Målet med denna forskning är att utvärdera register som datakälla och utveckla maskininlärningsalgoritmer för precisionsmedicininom epilepsi.  \nVi har använt svenska nationella registerdata av recept, sluten-och öppenvård samt död för att modellera patienters användning avantiepileptika. Som ett aggregerat mått av effekt och tolerabilitet har vianvänt retention som måttet på utfall av antiepileptika.  \nResultaten i denna avhandling indikerar att det är möjligt att använda registerdata för att uppskatta retention och att patientanpassat val avantiepileptika kan öka retentionen. Retentionsgrader uppskattade genom","cbCaimqisiYtruXM","https://ap.wps.com/l/cbCaimqisiYtruXM","pdf",5404449,1,66,"English","en",105,"# Abstract\n## Aim and background\n## Methods and outcome measure\n## Key findings\n## Conclusion\n# Keywords\n# List of Papers\n## Paper I\n## Paper II\n## Paper III\n## Paper IV","[{\"question\":\"Why is personalized ASM selection difficult in epilepsy treatment?\",\"answer\":\"About half of patients do not achieve seizure freedom with the first tested ASM, despite treatment being guided by patient characteristics. Trials can also be less clinically relevant for rare conditions.\"},{\"question\":\"What data and outcome measure were used in the study?\",\"answer\":\"The research used prescriptions, inpatient/outpatient data, and mortality data from national Swedish registers. Retention rate was used as a bundled measure of efficacy and tolerability.\"},{\"question\":\"What do the results suggest about using register data for personalization?\",\"answer\":\"Estimating ASM retention from register data is feasible, and personalized ASM selection may improve patient outcomes. Retention estimates were similar to RCT and meta-analysis results, and comorbidity analyses indicated potential 14–21% improvement over five years.\"},{\"question\":\"How do the machine learning approaches support clinicians?\",\"answer\":\"Specialized machine learning algorithms trained on register data can provide decision support for selecting ASMs. However, the methodology requires further development and clinical verification.\"}]",1785674715,166,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":89,"head_meta":91,"extra_data":93,"updated_unix":27},"machine-learning-and-big-data-for-personalized-epilepsy-treatment-dissertation","",{"@graph":35,"@context":88},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-and-big-data-for-personalized-epilepsy-treatment-dissertation/117253/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80,84],{"name":71,"@type":72,"acceptedAnswer":73},"Why is personalized ASM selection difficult in epilepsy treatment?","Question",{"text":74,"@type":75},"About half of patients do not achieve seizure freedom with the first tested ASM, despite treatment being guided by patient characteristics. Trials can also be less clinically relevant for rare conditions.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What data and outcome measure were used in the study?",{"text":79,"@type":75},"The research used prescriptions, inpatient/outpatient data, and mortality data from national Swedish registers. Retention rate was used as a bundled measure of efficacy and tolerability.",{"name":81,"@type":72,"acceptedAnswer":82},"What do the results suggest about using register data for personalization?",{"text":83,"@type":75},"Estimating ASM retention from register data is feasible, and personalized ASM selection may improve patient outcomes. Retention estimates were similar to RCT and meta-analysis results, and comorbidity analyses indicated potential 14–21% improvement over five years.",{"name":85,"@type":72,"acceptedAnswer":86},"How do the machine learning approaches support clinicians?",{"text":87,"@type":75},"Specialized machine learning algorithms trained on register data can provide decision support for selecting ASMs. However, the methodology requires further development and clinical verification.","https://schema.org",{"og:url":51,"og:type":90,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":92,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":95},[96,100,104,108,113,118,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Exam",70,"exam",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},5,"Comic",60,"comic",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},6,"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":45,"category_name":140,"show_sort_weight":109,"slug":141},19,"General","general"]