[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123998-en":3,"doc-seo-123998-105":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},123998,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Evaluation of machine learning methods for the retrospective detection of ovarian cancer recurrences from chemotherapy data","Cancer recurrences are inconsistently documented in electronic health records, making retrospective research into treatment effectiveness difficult. The current process of manually reviewing clinical records is costly, time-consuming, and inefficient, motivating automated methods. This study evaluates four machine learning models to identify proxy recurrence/progression dates from structured chemotherapy data in 531 epithelial ovarian cancer patients, and assesses event detection quality and alignment with chart-reviewed treatment timelines.","ORIGINAL ARTICLE  \nEvaluation of machine learning methods for the retrospective detection of ovarian cancer recurrences from chemotherapy data  \nA. D. Coles1􀀁, C. D. McInerney2, K. Zucker3, 4, S. Cheeseman4, O. A. Johnson1 & G. Hall3, 4  \n1School of Computing, University of Leeds, Leeds; 2School of Medicine & Population Health, University of Sheffield, Sheffield; 3School of Medicine, University of Leeds, Leeds; 4Leeds Cancer Center, Leeds Teaching Hospitals NHS Trust, Leeds, UK  \nAvailable online 1 May 2024  \nBackground: Cancer recurrences are poorly recorded within electronic health records around the world. This hinders research into the efficacy of cancer treatments. Currently, the retrospective identification of recurrence/progression diagnosis dates is achieved by staff who manually review patients’ health records. This is expensive, timeconsuming, and inefficient. Machine Learning models may expedite the review of health records and facilitate the assessment of alternative cancer therapies.  \nMaterials and methods: This paper evaluates the use of four machine learning models (random forests, conditional inference trees, decision trees, and logistic regression) in identifying proxy dates of epithelial ovarian cancer recurrence/progression from chemotherapy data, in 531 patients at Leeds Teaching Hospital Trust.  \nResults: The random forest achieved the highest F1 score of 0 .941 (95% confidence interval 0 .916-0.968) when identifying recurrence events. Both the random forest and decision tree models’ classifications closely conform to chart-reviewed time to next treatment, serving as a surrogate for recurrence-free survival. Additionally, all models reached an F1 score >0.940 when identifying patients whose cancer recurred/progressed.  \nConclusions: Our models proficiently identify both proxy dates for recurrence/progression diagnoses and patients whose cancer recurred/progressed. Considering the similar performance of the random forest and decision tree, model preference should be determined by the interpretability required to assist chart review and the ease of implementation into existing architecture.  \nKey words: cancer recurrence, chemotherapy, electronic health record, machine learning, artificial intelligence  \nINTRODUCTION  \nThe recurrence of a patient’s cancer is a clinically significant event, enabling the measurement of various clinical endpoints, including recurrence-free survival, progression-free survival, and time to next treatment (TTNT), which are used to assess the efficacy of cancer therapies.1-3 These endpoints rely on the accurate documentation of recurrence/progression diagnoses in health care records. However, recurrence data is inconsistently recorded in large databases.4 Where the recurrence date is not recorded in a structured format, it is retrospectively inferred through manual chart review.5  \nThe burden of chart review has encouraged the automated identification of recurrence diagnosis dates from structured administrative and electronic health record  \n*Correspondence to: Mr Alexander D. Coles, School of Computing, University of Leeds, Leeds LS2 9JT, UK.  \nE-mail: [scadc@leeds.ac.uk](scadc@leeds.ac.uk) (A. D. Coles).  \n2949-8201/© 2024 The Authors. Published by Elsevier Ltd on behalf of European Society for Medical Oncology. This is an open access article under the CC BY license ([http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/)).  \n(EHR) data.6 Methods used in previous studies to identify the date of first recurrence, range from simple rules-based methods,7-13 to machine learning (ML) models, like decision trees,14-16 and logistic regression.17, 18 Random forests,19 and conditional inference trees20 have also been used to identify patients whose cancer recurred. While the act of identifying patients who have had a recurrence alone does not enable survival analysis, this alternative output can be used for measuring population prevalence and identifying study cohor","cbCaikwi7fp9G8kg","https://ap.wps.com/l/cbCaikwi7fp9G8kg","pdf",1224613,1,9,"English","en",105,"# Introduction\n## Clinical endpoints and documentation challenges\n## Related automated methods and evaluation metrics\n## Study ambition and scope\n# Materials and Methods\n## Dataset description\n## Modeling approaches and outcome definitions\n# Results\n## Event detection performance\n## Agreement with time to next treatment\n# Conclusions\n## Model choice, interpretability, and implementation","[{\"question\":\"Why is retrospective detection of ovarian cancer recurrence difficult in electronic health records?\",\"answer\":\"Recurrence/progression diagnoses are inconsistently recorded in structured formats, so dates are often inferred via manual chart review, which is resource intensive.\"},{\"question\":\"Which machine learning models are evaluated for detecting recurrence-related proxy dates?\",\"answer\":\"The study evaluates random forests, conditional inference trees, decision trees, and logistic regression using structured chemotherapy data.\"},{\"question\":\"How do the model performances compare for identifying recurrence events and recurrent/progressed patients?\",\"answer\":\"The random forest achieves the highest F1 score for recurrence events, and random forest and decision tree outputs closely match chart-reviewed time to next treatment; all models reach high F1 scores for identifying patients whose cancer recurred/progressed.\"}]","Evaluation of machine learning methods for the retrospective detection of ovarian cancer recurrences from chemotherapy data | PDF",1785819740,23,{"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},"evaluation-of-machine-learning-methods-for-the-retrospective-detection-of-ovarian-cancer-recurrences-from-chemotherapy-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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluation-of-machine-learning-methods-for-the-retrospective-detection-of-ovarian-cancer-recurrences-from-chemotherapy-data/123998/",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","2026-08-04",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},"Why is retrospective detection of ovarian cancer recurrence difficult in electronic health records?","Question",{"text":75,"@type":76},"Recurrence/progression diagnoses are inconsistently recorded in structured formats, so dates are often inferred via manual chart review, which is resource intensive.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are evaluated for detecting recurrence-related proxy dates?",{"text":80,"@type":76},"The study evaluates random forests, conditional inference trees, decision trees, and logistic regression using structured chemotherapy data.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the model performances compare for identifying recurrence events and recurrent/progressed patients?",{"text":84,"@type":76},"The random forest achieves the highest F1 score for recurrence events, and random forest and decision tree outputs closely match chart-reviewed time to next treatment; all models reach high F1 scores for identifying patients whose cancer recurred/progressed.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]