{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T12:16:14Z","timestamp":1778588174100,"version":"3.51.4"},"reference-count":20,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T00:00:00Z","timestamp":1545955200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2019,2]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>The purpose of this study was to compare the effectiveness of ensemble methods (e.g., random forests) and single\u2010model methods (e.g., logistic regression and decision trees) in predictive modeling of post\u2010<jats:styled-content style=\"fixed-case\">RT<\/jats:styled-content> treatment failure and adverse events (<jats:styled-content style=\"fixed-case\">AE<\/jats:styled-content>s) for breast cancer patients using automatically extracted <jats:styled-content style=\"fixed-case\">EMR<\/jats:styled-content> data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Data from 1967 consecutive breast radiotherapy (<jats:styled-content style=\"fixed-case\">RT<\/jats:styled-content>) courses at one institution between 2008 and 2015 were automatically extracted from <jats:styled-content style=\"fixed-case\">EMR<\/jats:styled-content>s and oncology information systems using extraction software. Over 230 variables were extracted spanning the following variable segments: patient demographics, medical\/surgical history, tumor characteristics, <jats:styled-content style=\"fixed-case\">RT<\/jats:styled-content> treatment history, and <jats:styled-content style=\"fixed-case\">AE<\/jats:styled-content>s tracked using <jats:styled-content style=\"fixed-case\">CTCAE<\/jats:styled-content>v4.0. Treatment failure was extracted algorithmically by searching posttreatment encounters for evidence of local, nodal, or distant failure. Individual models were trained using decision trees, logistic regression, random forests, and boosted decision trees to predict treatment failures and <jats:styled-content style=\"fixed-case\">AE<\/jats:styled-content>s. Models were fit on 75% of the data and evaluated for probability calibration and area under the <jats:styled-content style=\"fixed-case\">ROC<\/jats:styled-content> curve (<jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content>) on the remaining test set. The impact of each variable segment was assessed by retraining without the segment and measuring change in <jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content> (\u0394<jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content>).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All <jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content> values were statistically significant (<jats:italic>P\u00a0<\/jats:italic>&lt;\u00a00.05). Ensemble methods outperformed single\u2010model methods across all outcomes. The best ensemble method outperformed decision trees and logistic regression by an average <jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content> of 0.053 and 0.034, respectively. Model probabilities were well calibrated as evidenced by calibration curves. Excluding the patient medical history variable segment led to the largest <jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content> reduction in all models (Average \u0394<jats:styled-content style=\"fixed-case\">AUC<\/jats:styled-content>\u00a0=\u00a0\u22120.025), followed by <jats:styled-content style=\"fixed-case\">RT<\/jats:styled-content> treatment history (\u22120.021) and tumor information (\u22120.015).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>In this largest such study in breast cancer performed to date, automatically extracted <jats:styled-content style=\"fixed-case\">EMR<\/jats:styled-content> data provided a basis for reliable outcome predictions across multiple statistical methods. Ensemble methods provided substantial advantages over single\u2010model methods. Patient medical history contributed the most to prediction quality.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.13314","type":"journal-article","created":{"date-parts":[[2018,11,30]],"date-time":"2018-11-30T12:39:23Z","timestamp":1543581563000},"page":"1054-1063","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Automated data extraction and ensemble methods for predictive modeling of breast cancer outcomes after radiation therapy"],"prefix":"10.1002","volume":"46","author":[{"given":"William D.","family":"Lindsay","sequence":"first","affiliation":[{"name":"Oncora Medical Philadelphia PA 19103 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher A.","family":"Ahern","sequence":"additional","affiliation":[{"name":"Oncora Medical Philadelphia PA 19103 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob S.","family":"Tobias","sequence":"additional","affiliation":[{"name":"Oncora Medical Philadelphia PA 19103 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher G.","family":"Berlind","sequence":"additional","affiliation":[{"name":"Oncora Medical Philadelphia PA 19103 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chidambaram","family":"Chinniah","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hospital of the University of Pennsylvania Philadelphia PA 19104 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter E.","family":"Gabriel","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hospital of the University of Pennsylvania Philadelphia PA 19104 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James C.","family":"Gee","sequence":"additional","affiliation":[{"name":"Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA 19104 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"2nd","given":"Charles B.","family":"Simone","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Maryland School of Medicine Baltimore MD 21201 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2018,12,28]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21395"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-15-0578"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM198503143121101"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2002.11.101"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2005.04.1665"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2016.09.012"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1200\/JOP.2014.001434"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2014.112"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature15819"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.298.10.1209"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2014.04.012"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.8755"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/16\/6105"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1072-7515(99)00056-3"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/npjbcancer.2016.11"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2000.18.4.743"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0142(20000515)88:10<2260::AID-CNCR9>3.0.CO;2-M"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(05)67887-7"},{"key":"e_1_2_7_20_1","volume-title":"Classification and Regression Trees","author":"Breiman L","year":"1984"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0936-6555(05)80657-0"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmp.13314","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13314","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.13314","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T15:38:59Z","timestamp":1693928339000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.13314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,28]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["10.1002\/mp.13314"],"URL":"https:\/\/doi.org\/10.1002\/mp.13314","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,28]]},"assertion":[{"value":"2018-02-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-11-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-12-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}