[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-337841-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-337841-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","mathematical-model-driven-deep-learning-enables-personalized-adaptive-therapy-abstract","Mathematical Model-Driven Deep Learning Enables Personalized Adaptive Therapy - Abstract","","Standard-of-care regimens are often built for maximal tumor cell killing, but they frequently fail in metastatic disease because drug resistance emerges and evolves during therapy. Adaptive treatment adjusts dosing over time to suppress treatment-resistant populations and delay or prevent progression. Deep reinforcement learning is used to optimize adaptive drug scheduling in a prostate cancer-calibrated model, more than doubling time to progression and remaining robust to patient variability. The approach yields interpretable, threshold-based schedules and includes a five-step path integrating mechanistic modeling to support clinical translation.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/mathematical-model-driven-deep-learning-enables-personalized-adaptive-therapy-abstract/337841/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/mathematical-model-driven-deep-learning-enables-personalized-adaptive-therapy-abstract/337841.png","ImageObject",300,407,{"name":42,"@type":43},"Hazel","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-04","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why do standard-of-care regimens often fail in metastatic cancers?","Question",{"text":63,"@type":64},"They are designed for maximal cell killing, but metastatic tumors frequently develop treatment resistance, causing these strategies to become ineffective over time.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is adaptive therapy in this work?",{"text":68,"@type":64},"Adaptive therapy dynamically adjusts treatment to suppress growth of treatment-resistant populations by maintaining competition with drug-sensitive cells, aiming to control progression rather than eliminate the tumor outright.",{"name":70,"@type":61,"acceptedAnswer":71},"How does deep reinforcement learning improve adaptive drug scheduling here?",{"text":72,"@type":64},"Deep reinforcement learning guides dosing schedules and, in a prostate cancer-calibrated mathematical model, outperforms current adaptive protocols by more than doubling the time to progression while remaining robust to patient variability.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},337841,1791225482,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},137441390410,"https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984","Mathematical Model-Driven Deep Learning Enables Personalized Adaptive Therapy  \nKit Gallagher1,2, Maximilian A. R. Strobl2, Derek S. Park2, Fabian C. Spoendlin1, Robert A. Gatenby2, Philip K. Maini1, and Alexander R.A. Anderson2  \nABSTRACT  \n◥  \nStandard-of-care treatment regimens have long been designed for maximal cell killing, yet these strategies often fail when applied to metastatic cancers due to the emergence of drug resistance. Adaptive treatment strategies have been developed as an alternative approach, dynamically adjusting treatment to suppress the growth of treatment-resistant populations and thereby delay, or even prevent, tumor progression. Promising clinical results in prostate cancer indicate the potential to optimize adaptive treatment protocols. Here, we applied deep reinforcement learning (DRL) to guide adaptive drug scheduling and demonstrated that these treatment schedules can outperform the current adaptive protocols in a mathematical model calibrated to prostate cancer dynamics, more than doubling the time to progression. The DRL strategies were robust to patient variability, including both tumor dynamics and clinical monitoring schedules. The DRL framework could produce interpretable, adaptive strategies based on a single tumor burden threshold, replicating and informing optimal treatment strategies. The DRL framework had no knowledge of the underlying mathematical tumor model, demonstrating the capability of DRL to help develop treatment strategies in novel or complex settings. Finally, a proposed ﬁve-step pathway, which combined mechanistic modeling with the DRL framework and integrated conventional tools to improve interpretability compared with traditional “black-box”DRL models, could allow translation of this approach to the clinic. Overall, the proposed framework generated personalized treatment  \nschedules that consistently outperformed clinical standard-of-care protocols.  \nSigniﬁcance: Generation of interpretable and personalized adaptive treatment schedules using a deep reinforcement framework that interacts with a virtual patient model overcomes the limitations of standardized strategies caused by heterogeneous treatment responses.  \nIntroduction  \nDrug resistance is responsible for up to 90% of cancer-related deaths (1) . It can be present before treatment (intrinsic) or emerge during therapy (acquired) and is driven by a combination of genetic, epigenetic, and environmental processes (2) . Much modern cancer  \n1Wolfson Centre for Mathematical Biology, Mathematical Institute, Oxford, United Kingdom. 2Integrated Mathematical Oncology, Mofﬁtt Cancer Center, Tampa, Florida.  \nCorrected online December 11, 2024.  \nK. Gallagher and M.A. R. Strobl share the ﬁrst authorship of this article.  \nP. K. Maini and A. R.A. Anderson share the senior authorship of this article. Corresponding Authors: Alexander R. Anderson, Mofﬁtt Cancer Center, SRB 4th Floor, 12902 Magnolia Drive, Tampa, FL 33612 . E-mail:  \nalexander. anderson@mofﬁ[tt.org](tt.org); Kit Gallagher, Mathematical Institute, University of Oxford, Andrew Wiles Building, Radcliffe Observatory Quarter, Woodstock Road, Oxford OX2 6GG, United Kingdom. E-mail:  \n[gallagher@maths.ox.ac.uk](gallagher@maths.ox.ac.uk)[ ](gallagher@maths.ox.ac.uk)[Cancer Res 2024](Cancer Res 2024);[84:1929](84:1929)–[41](41)  \ndoi: 10.1158/0008-5472 . CAN-23-2040  \nThis open access article is distributed under the Creative Commons AttributionNonCommercial-NoDerivatives 4 . 0 International (CC BY-NC-ND 4 . 0) license.  \n􀀁2024The Authors;Published by the American Association for Cancer Research  \nresearch has focused on developing novel therapies to overcome resistance but, especially in the metastatic setting, cure rates remain low and beneﬁts are all too often short-lived (3, 4) .  \nConventional, standard-of-care treatment schedules for systemic cancer therapies are based on the maximum tolerated dose (MTD) principle. This argues for the administration of treatment at as ","cbCaiqb2P1pbsaNQ","https://ap.wps.com/l/cbCaiqb2P1pbsaNQ","pdf",31166648,13,"English","# Abstract\n# Significance\n# Introduction","[{\"question\":\"Why do standard-of-care regimens often fail in metastatic cancers?\",\"answer\":\"They are designed for maximal cell killing, but metastatic tumors frequently develop treatment resistance, causing these strategies to become ineffective over time.\"},{\"question\":\"What is adaptive therapy in this work?\",\"answer\":\"Adaptive therapy dynamically adjusts treatment to suppress growth of treatment-resistant populations by maintaining competition with drug-sensitive cells, aiming to control progression rather than eliminate the tumor outright.\"},{\"question\":\"How does deep reinforcement learning improve adaptive drug scheduling here?\",\"answer\":\"Deep reinforcement learning guides dosing schedules and, in a prostate cancer-calibrated mathematical model, outperforms current adaptive protocols by more than doubling the time to progression while remaining robust to patient variability.\"}]","Mathematical Model-Driven Deep Learning Enables Personalized Adaptive Therapy - Abstract | PDF",1790020861,33,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1336ae6fc60d966d14eac1d3eaf21622.webp",983,1286,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3d632f4fe47f85069f36e5b16273b062.webp",982,1285,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0f25820371301db90d87435fff7b3921.webp",981,1283,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d26d0156fb7c64b86a0cb5b8c7e67528.webp",980,1282]