{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T17:19:56Z","timestamp":1763572796375,"version":"3.37.3"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010414","name":"Health Research Board","doi-asserted-by":"publisher","award":["SS-2023-054"],"award-info":[{"award-number":["SS-2023-054"]}],"id":[{"id":"10.13039\/100010414","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>There is ongoing uncertainty about the effectiveness of various adjuvant treatments for low-grade gliomas (LGGs). Machine learning (ML) models that predict individual treatment effects (ITE) and provide treatment recommendations could help tailor treatments to each patient\u2019s needs.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Objective<\/jats:title>\n<jats:p>We sought to discern the individual suitability of radiotherapy (RT) or chemoradiotherapy (CRT) in LGG patients using ML models.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Ten ML models, trained to infer ITE in 4,042 LGG patients, were assessed. We compared patients who followed treatment recommendations provided by the models with those who did not. To mitigate the risk of treatment selection bias, we employed inverse probability treatment weighting (IPTW).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Results<\/jats:title>\n<jats:p>The Balanced Survival Lasso-Network (BSL) model showed the most significant protective effect among all the models we tested (hazard ratio (HR): 0.52, 95% CI, 0.41\u20130.64; IPTW-adjusted HR: 0.58, 95% CI, 0.45\u20130.74; the difference in restricted mean survival time (DRMST): 9.11, 95% CI, 6.19\u201312.03; IPTW-adjusted DRMST: 9.17, 95% CI, 6.30\u201311.83). CRT presented a protective effect in the \u2018recommend for CRT\u2019 group (IPTW-adjusted HR: 0.60, 95% CI, 0.39\u20130.93) yet presented an adverse effect in the \u2018recommend for RT\u2019 group (IPTW-adjusted HR: 1.64, 95% CI, 1.19\u20132.25). Moreover, the models predict that younger patients and patients with overlapping lesions or tumors crossing the midline are better suited for CRT (HR: 0.62, 95% CI, 0.42\u20130.91; IPTW-adjusted HR: 0.59, 95% CI, 0.36\u20130.97).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Our findings underscore the potential of the BSL model in guiding the choice of adjuvant treatment for LGGs patients, potentially improving survival time. This study emphasizes the importance of ML in customizing patient care, understanding the nuances of treatment selection, and advancing personalized medicine.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0306711","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T18:00:35Z","timestamp":1724176835000},"page":"e0306711","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Utilizing machine learning to tailor radiotherapy and chemoradiotherapy for low-grade glioma patients"],"prefix":"10.1371","volume":"19","author":[{"given":"Enzhao","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhong","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linlin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2762-6770","authenticated-orcid":true,"given":"Dan","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,8,20]]},"reference":[{"issue":"10145","key":"pone.0306711.ref001","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/S0140-6736(18)30990-5","article-title":"Primary brain tumours in adults","volume":"392","author":"S Lapointe","year":"2018","journal-title":"Lancet"},{"issue":"8","key":"pone.0306711.ref002","first-page":"Cd013047","article-title":"Long-term neurocognitive and other side effects of radiotherapy, with or without chemotherapy, for glioma.","volume":"8","author":"TA Lawrie","year":"2019","journal-title":"Cochrane Database Syst Rev."},{"key":"pone.0306711.ref003","doi-asserted-by":"crossref","first-page":"15017","DOI":"10.1038\/nrdp.2015.17","article-title":"Glioma","volume":"1","author":"M Weller","year":"2015","journal-title":"Nat Rev Dis Primers"},{"issue":"4","key":"pone.0306711.ref004","doi-asserted-by":"crossref","first-page":"299","DOI":"10.3322\/caac.21613","article-title":"Management of glioblastoma: State of the art and future directions.","volume":"70","author":"AC Tan","year":"2020","journal-title":"CA Cancer J Clin"},{"issue":"29","key":"pone.0306711.ref005","doi-asserted-by":"crossref","first-page":"3407","DOI":"10.1200\/JCO.19.02983","article-title":"Comprehensive Genomic Analysis in NRG Oncology\/RTOG 9802: A Phase III Trial of Radiation Versus Radiation Plus Procarbazine, Lomustine (CCNU), and Vincristine in High-Risk Low-Grade Glioma.","volume":"38","author":"EH Bell","year":"2020","journal-title":"J Clin Oncol."},{"issue":"6","key":"pone.0306711.ref006","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1097\/WCO.0000000000000257","article-title":"Chemotherapy for low-grade glioma: when, for whom, which regimen?","volume":"28","author":"MJ van den Bent","year":"2015","journal-title":"Curr Opin Neurol."},{"issue":"3","key":"pone.0306711.ref007","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1200\/JCO.2012.43.2229","article-title":"Adjuvant procarbazine, lomustine, and vincristine chemotherapy in newly diagnosed anaplastic oligodendroglioma: long-term follow-up of EORTC brain tumor group study 26951.","volume":"31","author":"MJ van den Bent","year":"2013","journal-title":"J Clin Oncol."},{"issue":"9343","key":"pone.0306711.ref008","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1016\/S0140-6736(02)11398-5","article-title":"Effect of radiotherapy and other treatment-related factors on mid-term to long-term cognitive sequelae in low-grade gliomas: a comparative study","volume":"360","author":"M Klein","year":"2002","journal-title":"Lancet. Nov 2"},{"issue":"3","key":"pone.0306711.ref009","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1200\/JCO.2012.43.2674","article-title":"Phase III trial of chemoradiotherapy for anaplastic oligodendroglioma: long-term results of RTOG 9402.","volume":"31","author":"G Cairncross","year":"2013","journal-title":"J Clin Oncol"},{"issue":"25","key":"pone.0306711.ref010","doi-asserted-by":"crossref","first-page":"3065","DOI":"10.1200\/JCO.2011.35.8598","article-title":"Randomized trial of radiation therapy plus procarbazine, lomustine, and vincristine chemotherapy for supratentorial adult low-grade glioma: initial results of RTOG 9802.","volume":"30","author":"EG Shaw","year":"2012","journal-title":"J Clin Oncol"},{"issue":"2","key":"pone.0306711.ref011","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1159\/000012087","article-title":"Analysis of prognostic and survival factors related to treatment of low-grade astrocytomas in adults","volume":"58","author":"M Nakamura","year":"2000","journal-title":"Oncology"},{"issue":"3","key":"pone.0306711.ref012","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1158\/2159-8290.CD-20-1474","article-title":"Diffuse Glioma Heterogeneity and Its Therapeutic Implications.","volume":"11","author":"JG Nicholson","year":"2021","journal-title":"Cancer Discov"},{"issue":"11","key":"pone.0306711.ref013","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1016\/S1470-2045(16)30305-9","article-title":"Health-related quality of life in patients with high-risk low-grade glioma (EORTC 22033\u201326033): a randomised, open-label, phase 3 intergroup study.","volume":"17","author":"JC Reijneveld","year":"2016","journal-title":"Lancet Oncol"},{"issue":"3","key":"pone.0306711.ref014","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s11060-010-0340-4","article-title":"Favorable long-term outcome of low-grade oligodendrogliomas irrespective of 1p\/19q status when treated without radiotherapy","volume":"102","author":"Y Iwadate","year":"2011","journal-title":"J Neurooncol. May"},{"issue":"4","key":"pone.0306711.ref015","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.3892\/ijo.2012.1564","article-title":"IDH1\/2 mutation is a prognostic marker for survival and predicts response to chemotherapy for grade II gliomas concomitantly treated with radiation therapy","volume":"41","author":"Y Okita","year":"2012","journal-title":"Int J Oncol"},{"issue":"3","key":"pone.0306711.ref016","doi-asserted-by":"crossref","first-page":"e119","DOI":"10.1002\/cai2.119","article-title":"Personalized surgical recommendations and quantitative therapeutic insights for patients with metastatic breast cancer: Insights from deep learning","volume":"3","author":"E Zhu","year":"2024","journal-title":"Cancer Innovation"},{"key":"pone.0306711.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3444944","article-title":"A Survey on Causal Inference.","volume":"15","author":"L Yao","year":"2020","journal-title":"ACM Transactions on Knowledge Discovery from Data (TKDD)."},{"volume-title":"Data-Driven Estimation of Heterogeneous Treatment Effects.","year":"2023","author":"C Tran","key":"pone.0306711.ref018"},{"key":"pone.0306711.ref019","doi-asserted-by":"crossref","first-page":"1330907","DOI":"10.3389\/fmed.2024.1330907","article-title":"Individualized survival prediction and surgery recommendation for patients with glioblastoma","volume":"11","author":"E Zhu","year":"2024","journal-title":"Front Med (Lausanne)."},{"issue":"12","key":"pone.0306711.ref020","first-page":"1117","article-title":"The surveillance, epidemiology, and end results program: a national resource","volume":"8","author":"BF Hankey","year":"1999","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"issue":"9596","key":"pone.0306711.ref021","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1016\/S0140-6736(07)61602-X","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies.","volume":"370","author":"E von Elm","year":"2007","journal-title":"Lancet"},{"key":"pone.0306711.ref022","doi-asserted-by":"crossref","first-page":"4156","DOI":"10.1073\/pnas.1804597116","article-title":"Metalearners for estimating heterogeneous treatment effects using machine learning","volume":"116","author":"SR K\u00fcnzel","year":"2017","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"volume-title":"A Robust Method for Estimating Individualized Treatment Effect","year":"2020","author":"H Meng","key":"pone.0306711.ref023"},{"key":"pone.0306711.ref024","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and Inference of Heterogeneous Treatment Effects using Random Forests","volume":"113","author":"S Wager","year":"2015","journal-title":"Journal of the American Statistical Association"},{"key":"pone.0306711.ref025","doi-asserted-by":"crossref","first-page":"i60","DOI":"10.1093\/bioinformatics\/btac221","article-title":"BITES: balanced individual treatment effect for survival data","volume":"38","author":"S Schrod","year":"2022","journal-title":"Bioinformatics"},{"key":"pone.0306711.ref026","doi-asserted-by":"crossref","DOI":"10.1145\/3534678.3539110","volume-title":"Counterfactual Phenotyping with Censored Time-to-Events.","author":"C Nagpal","year":"2022"},{"journal-title":"Reconsidering Generative Objectives For Counterfactual Reasoning","year":"2020","author":"D Lu","key":"pone.0306711.ref027"},{"key":"pone.0306711.ref028","first-page":"127:1","article-title":"LassoNet: A Neural Network with Feature Sparsity.","volume":"22","author":"I Lemhadri","year":"2019","journal-title":"J Mach Learn Res."},{"journal-title":"Interpolating between Optimal Transport and MMD using Sinkhorn Divergences","year":"2018","author":"J Feydy","key":"pone.0306711.ref029"},{"key":"pone.0306711.ref030","first-page":"abs\/1606.00931","volume-title":"Deep Survival: A Deep Cox Proportional Hazards Network","author":"J Katzman","year":"2016"},{"issue":"6","key":"pone.0306711.ref031","doi-asserted-by":"crossref","first-page":"e205842","DOI":"10.1001\/jamanetworkopen.2020.5842","article-title":"Development and Validation of a Deep Learning Model for Non-Small Cell Lung Cancer Survival.","volume":"3","author":"Y She","year":"2020","journal-title":"JAMA Netw Open. Jun 1"},{"key":"pone.0306711.ref032","first-page":"abs\/2208.11080","volume-title":"Time-dependent explanations of machine learning survival models","author":"M Krzyzi\u2019nski","year":"2022"},{"issue":"1","key":"pone.0306711.ref033","doi-asserted-by":"crossref","first-page":"6968","DOI":"10.1038\/s41598-021-86327-7","article-title":"Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival","volume":"11","author":"A Moncada-Torres","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0306711.ref034","doi-asserted-by":"crossref","first-page":"k4817","DOI":"10.1136\/bmj.k4817","article-title":"When continuous outcomes are measured using different scales: guide for meta-analysis and interpretation","volume":"364","author":"MH Murad","year":"2019","journal-title":"Bmj"},{"issue":"14","key":"pone.0306711.ref035","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1056\/NEJMoa1500925","article-title":"Radiation plus Procarbazine, CCNU, and Vincristine in Low-Grade Glioma.","volume":"374","author":"JC Buckner","year":"2016","journal-title":"New England Journal of Medicine"},{"issue":"suppl 2","key":"pone.0306711.ref036","first-page":"ii31","article-title":"The dilemma of low grade glioma","volume":"75","author":"IR Whittle","year":"2004","journal-title":"Journal of Neurology, Neurosurgery &amp; Psychiatry"},{"issue":"11","key":"pone.0306711.ref037","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1016\/S1470-2045(16)30313-8","article-title":"Temozolomide chemotherapy versus radiotherapy in high-risk low-grade glioma (EORTC 22033\u201326033): a randomised, open-label, phase 3 intergroup study.","volume":"17","author":"BG Baumert","year":"2016","journal-title":"The Lancet Oncology"},{"issue":"3","key":"pone.0306711.ref038","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1007\/s11060-015-1931-x","article-title":"The role of initial chemotherapy for the treatment of adults with diffuse low grade glioma","volume":"125","author":"M Ziu","year":"2015","journal-title":"Journal of Neuro-Oncology"},{"issue":"2","key":"pone.0306711.ref039","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1002\/cncr.31834","article-title":"On high-risk, low-grade glioma: What distinguishes high from low?","volume":"125","author":"M Geurts","year":"2019","journal-title":"Cancer"},{"key":"pone.0306711.ref040","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/1471-2288-13-88","article-title":"Testing the proportional hazards assumption in case-cohort analysis.","volume":"13","author":"X Xue","year":"2013","journal-title":"BMC Med Res Methodol"},{"key":"pone.0306711.ref041","article-title":"Reasoning and causal inference regarding surgical options for patients with low-grade gliomas using machine learning: A SEER-based study","author":"E Zhu","year":"2023","journal-title":"Cancer Med. Nov"},{"issue":"2","key":"pone.0306711.ref042","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s00432-023-05602-4","article-title":"Quantified treatment effect at the individual level is more indicative for personalized radical prostatectomy recommendation: implications for prostate cancer treatment using deep learning","volume":"150","author":"H Pan","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"issue":"4","key":"pone.0306711.ref043","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1093\/nop\/npy034","article-title":"Management of low-grade glioma: a systematic review and meta-analysis","volume":"6","author":"TJ Brown","year":"2019","journal-title":"Neuro-Oncology Practice"},{"issue":"4","key":"pone.0306711.ref044","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1016\/j.urology.2010.09.062","article-title":"Young age as favorable prognostic factor for cancer-specific survival in localized renal cell carcinoma","volume":"77","author":"Y Komai","year":"2011","journal-title":"Urology. Apr"},{"issue":"5","key":"pone.0306711.ref045","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.3171\/2019.6.JNS19409","article-title":"Impact of facility type and volume in low-grade glioma outcomes","volume":"133","author":"P Zhu","year":"2020","journal-title":"Journal of Neurosurgery JNS"},{"issue":"12","key":"pone.0306711.ref046","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1634\/theoncologist.2014-0170","article-title":"Management of Elderly Patients With Gliomas.","volume":"19","author":"J G\u00e1llego P\u00e9rez-Larraya","year":"2014","journal-title":"The Oncologist."},{"issue":"1","key":"pone.0306711.ref047","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/pro6.1190","article-title":"Definitive chemoradiotherapy in elderly patients with esophageal cancer: Safety and outcome.","volume":"7","author":"I Kiladze","year":"2023","journal-title":"Precision Radiation Oncology."},{"issue":"1","key":"pone.0306711.ref048","first-page":"224","article-title":"Radiolucent Jaw Lesions: Imaging Approach.","volume":"31","author":"J Kumar","year":"2021","journal-title":"Indian J Radiol Imaging"},{"issue":"1","key":"pone.0306711.ref049","doi-asserted-by":"crossref","first-page":"1","DOI":"10.21873\/anticanres.14746","article-title":"Chemoradiotherapy in Cancer Treatment: Rationale and Clinical Applications","volume":"41","author":"R Kathrine S","year":"2021","journal-title":"Anticancer Research"},{"key":"pone.0306711.ref050","first-page":"12","article-title":"Reducing the Cognitive Footprint of Brain Tumor Surgery.","volume":"2021","author":"NB Dadario","year":"2021","journal-title":"Review. Frontiers in Neurology"},{"key":"pone.0306711.ref051","first-page":"69","volume-title":"Handbook of Clinical Neurology","author":"T Walbert","year":"2023"},{"issue":"3","key":"pone.0306711.ref052","first-page":"54","article-title":"Concurrent therapy to enhance radiotherapeutic outcomes in glioblastoma","volume":"4","author":"D. Khosla","year":"2016","journal-title":"Ann Transl Med"},{"issue":"11","key":"pone.0306711.ref053","doi-asserted-by":"crossref","first-page":"e2025881","DOI":"10.1001\/jamanetworkopen.2020.25881","article-title":"Machine Learning-Guided Adjuvant Treatment of Head and Neck Cancer.","volume":"3","author":"FM Howard","year":"2020","journal-title":"JAMA Netw Open"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0306711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T18:01:08Z","timestamp":1724176868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0306711"}},"subtitle":[],"editor":[{"given":"Gayle E.","family":"Woloschak","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,8,20]]},"references-count":53,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0306711","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2024,8,20]]}}}