{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:52:17Z","timestamp":1753883537647,"version":"3.41.2"},"reference-count":45,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"6","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clinical Cancer Informatics"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:sec><jats:title>PURPOSE<\/jats:title><jats:p> To stratify patients and aid clinical decision making, we developed machine learning models to predict treatment failure and radiation-induced toxicities after radiotherapy (RT) in patients with hepatocellular carcinoma across institutions. <\/jats:p><\/jats:sec><jats:sec><jats:title>MATERIALS AND METHODS<\/jats:title><jats:p> The models were developed using linear and nonlinear algorithms, predicting survival, nonlocal failure, radiation-induced liver disease, and lymphopenia from baseline patient and treatment parameters. The models were trained on 207 patients from Massachusetts General Hospital. Performance was quantified using Harrell's c-index, area under the curve (AUC), and accuracy in high-risk populations. Models' structures were optimized in a nested cross-validation approach to prevent overfitting. A study analysis plan was registered before external validation using 143 patients from MD Anderson Cancer Center. Clinical utility was assessed using net-benefit analysis. <\/jats:p><\/jats:sec><jats:sec><jats:title>RESULTS<\/jats:title><jats:p> The survival model stratified high-risk versus low-risk patients well in the external validation cohort (c-index = 0.75), better than existing risk scores. Predictions of 1-year survival and nonlocal failure were excellent (external AUC = 0.74 and 0.80, respectively), especially in the high-risk group (accuracy &gt; 90%). Cause-of-death analysis showed differential modes of treatment failure in these cohorts and indicated that these models could be used to stratify RT patients for liver-sparing treatment regimen or combination approaches with systemic agents. Predictions of liver disease and lymphopenia were good but less robust (external AUC = 0.68 and 0.7, respectively), suggesting the need for more comprehensive consideration of dosimetry and better predictive biomarkers. The liver disease model showed excellent accuracy in the high-risk group (92%) and revealed possible interactions of platelet count with initial liver function. <\/jats:p><\/jats:sec><jats:sec><jats:title>CONCLUSION<\/jats:title><jats:p> Machine learning approaches can provide reliable outcome predictions in patients with hepatocellular carcinoma after RT in diverse cohorts across institutions. The excellent performance, particularly in high-risk patients, suggests novel strategies for patient stratification and treatment selection. <\/jats:p><\/jats:sec>","DOI":"10.1200\/cci.21.00169","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:59:34Z","timestamp":1645563574000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":6,"title":["Predictive Modeling of Survival and Toxicity in Patients With Hepatocellular Carcinoma After Radiotherapy"],"prefix":"10.1200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7005-8692","authenticated-orcid":false,"given":"Ibrahim","family":"Chamseddine","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-1502","authenticated-orcid":false,"given":"Yejin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"},{"name":"Korean Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3468-3359","authenticated-orcid":false,"given":"Brian","family":"De","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University of Texas, MD Anderson Cancer Center, Houston, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6023-1132","authenticated-orcid":false,"given":"Issam","family":"El Naqa","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7065-8797","authenticated-orcid":false,"given":"Dan G.","family":"Duda","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Wolfgang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0531-6798","authenticated-orcid":false,"given":"Jennifer","family":"Pursley","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harald","family":"Paganetti","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer","family":"Wo","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8481-6581","authenticated-orcid":false,"given":"Theodore","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7675-3461","authenticated-orcid":false,"given":"Eugene J.","family":"Koay","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University of Texas, MD Anderson Cancer Center, Houston, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4425-4489","authenticated-orcid":false,"given":"Clemens","family":"Grassberger","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"233","reference":[{"key":"b1","doi-asserted-by":"publisher","DOI":"10.1002\/jso.21593"},{"key":"b2","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.04.006"},{"key":"b3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2017.02.022"},{"key":"b4","doi-asserted-by":"publisher","DOI":"10.2217\/hep.15.7"},{"key":"b5","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2007.14.3529"},{"key":"b6","doi-asserted-by":"publisher","DOI":"10.1159\/000367764"},{"key":"b7","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-010-0492-x"},{"key":"b8","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.27533"},{"key":"b9","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2012.44.1659"},{"key":"b10","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.12.005"},{"key":"b11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.05.056"},{"key":"b12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.01.076"},{"key":"b13","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-019-0238-9"},{"key":"b14","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2019.12.003"},{"key":"b15","doi-asserted-by":"publisher","DOI":"10.2147\/JHC.S282062"},{"key":"b16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab63b6"},{"key":"b17","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.07.025"},{"key":"b18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.04.027"},{"key":"b19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0077472"},{"key":"b20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0177793"},{"key":"b22","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMe048225"},{"key":"b23","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.00978"},{"key":"b24","doi-asserted-by":"publisher","DOI":"10.1111\/eci.12376"},{"key":"b25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.06.092"},{"key":"b26","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2018.2832609"},{"key":"b27","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91"},{"key":"b28","first-page":"1","volume":"45","author":"van Buuren S","year":"2011","journal-title":"J Stat Softw"},{"key":"b29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00043-X"},{"key":"b30","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-25"},{"key":"b31","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOAS148"},{"key":"b32","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4"},{"key":"b33","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7"},{"key":"b34","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i6"},{"key":"b35","doi-asserted-by":"publisher","DOI":"10.1016\/j.meddos.2019.03.004"},{"key":"b36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhepr.2019.05.004"},{"key":"b37","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v26.i4.393"},{"key":"b38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2015.10.004"},{"key":"b39","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-018-0065-y"},{"key":"b40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.10.005"},{"key":"b41","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-020-0124-z"},{"key":"b42","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-61298-3"},{"key":"b43","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2019.2904078"},{"key":"b44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.02.013"},{"key":"b45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.08.029"},{"key":"b46","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-4296(99)80052-6"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI.21.00169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,29]],"date-time":"2022-05-29T10:58:56Z","timestamp":1653821936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI.21.00169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10.1200\/CCI.21.00169"],"URL":"https:\/\/doi.org\/10.1200\/cci.21.00169","relation":{},"ISSN":["2473-4276"],"issn-type":[{"type":"electronic","value":"2473-4276"}],"subject":[],"published":{"date-parts":[[2022,5]]},"assertion":[{"value":"2021-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-20","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2100169"}}