{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T15:13:36Z","timestamp":1788016416195,"version":"build-2784847793"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Introduction<\/jats:title>\n<jats:p>Primary refractory disease affects 30\u201340% of patients diagnosed with DLBCL and is a significant challenge in disease management due to its poor prognosis. Predicting refractory status could greatly inform treatment strategies, enabling early intervention. Various options are now available based on patient and disease characteristics. Supervised machine-learning techniques, which can predict outcomes in a medical context, appear highly suitable for this purpose.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Design<\/jats:title>\n<jats:p>Retrospective monocentric cohort study.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Patient population<\/jats:title>\n<jats:p>Adult patients with a first diagnosis of DLBCL admitted to the hematology unit from 2017 to 2022.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Aim<\/jats:title>\n<jats:p>We evaluated in our Center five supervised machine-learning (ML) models as a tool for the prediction of primary refractory DLBCL.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Main results<\/jats:title>\n<jats:p>One hundred and thirty patients with Diffuse Large B-cell lymphoma (DLBCL) were included in this study between January 2017 and December 2022. The variables used for analysis included demographic characteristics, clinical condition, disease characteristics, first-line therapy and PET-CT scan realization after 2 cycles of treatment. We compared five supervised ML models: support vector machine (SVM), Random Forest Classifier (RFC), Logistic Regression (LR), Na\u00efve Bayes (NB) Categorical classifier and eXtreme Gradient Boost (XGboost), to predict primary refractory disease. The performance of these models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, false positive rate, sensitivity, and F1-score to identify the best model. After a median follow-up of 19.5 months, the overall survival rate was 60% in the cohort. The Overall Survival at 3 years was 58.5% (95%CI, 51\u201368.5) and the 3-years Progression Free Survival was 63% (95%CI, 54\u201371) using Kaplan-Meier method. Of the 124 patients who received a first line treatment, primary refractory disease occurred in 42 patients (33.8%) and 2 patients (1.6%) experienced relapse within 6 months. The univariate analysis on refractory disease status shows age (p = 0.009), Ann Arbor stage (p = 0.013), CMV infection (p = 0.012), comorbidity (p = 0.019), IPI score (p&lt;0.001), first line of treatment (p&lt;0.001), EBV infection (p = 0.008) and socio-economics status (p = 0.02) as influencing factors. The NB Categorical classifier emerged as the top-performing model, boasting a ROC-AUC of 0.81 (95% CI, 0.64\u20130.96), an accuracy of 83%, a F1-score of 0.82, and a low false positive rate at 10% on the validation set. The eXtreme Gradient Boost (XGboost) model and the Random Forest Classifier (RFC) followed with a ROC-AUC of 0.74 (95%CI, 0.52\u20130.93) and 0.67 (95%CI, 0.46\u20130.88) respectively, an accuracy of 78% and 72% respectively, a F1-score of 0.75 and 0.67 respectively, and a false positive rate of 10% for both. The other two models performed worse with ROC-AUC of 0.65 (95%CI, 0.40\u20130.87) and 0.45 (95%CI, 0.29\u20130.64) for SVM and LR respectively, an accuracy of 67% and 50% respectively, a f1-score of 0.64 and 0.43 respectively, and a false positive rate of 28% and 37% respectively.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec006\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Machine learning algorithms, particularly the NB Categorical classifier, have the potential to improve the prediction of primary refractory disease in DLBCL patients, thereby providing a novel decision-making tool for managing this condition. To validate these results on a broader scale, multicenter studies are needed to confirm the results in larger cohorts.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0311261","type":"journal-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T17:22:53Z","timestamp":1727803373000},"page":"e0311261","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["A machine learning approach in a monocentric cohort for predicting primary refractory disease in Diffuse Large B-cell lymphoma patients"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9718-0789","authenticated-orcid":true,"given":"Marie Y.","family":"Detrait","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phanie","family":"Warnon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rapha\u00ebl","family":"Lagasse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Dumont","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phanie","family":"De Proph\u00e9tis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amandine","family":"Hansenne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juliette","family":"Raedemaeker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Val\u00e9rie","family":"Robin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00e9raldine","family":"Verstraete","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aline","family":"Gillain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Depasse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Jacmin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Delphine","family":"Pranger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"issue":"9","key":"pone.0311261.ref001","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1056\/NEJMra2027612","article-title":"Diffuse large B cell lymphoma","volume":"384","author":"LH Sehn","year":"2021","journal-title":"N Engl J Med"},{"issue":"3","key":"pone.0311261.ref002","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.beha.2018.07.014","article-title":"Management of relapsed\/refractory DLBCL","volume":"31","author":"C Sarkozy","year":"2018","journal-title":"Best Pract Res Clin Haematol"},{"issue":"22","key":"pone.0311261.ref003","doi-asserted-by":"crossref","first-page":"8553","DOI":"10.3390\/ijms21228553","article-title":"Novel Therapies for relapsed and Refractory DLBCL","volume":"21","author":"LJ Harris","year":"2020","journal-title":"Int J Mol Sci"},{"key":"pone.0311261.ref004","doi-asserted-by":"crossref","first-page":"v116","DOI":"10.1093\/annonc\/mdv304","article-title":"DLBCL: ESMO clinical practice guidelines for diagnosis, treatment and follow-up","volume":"26","author":"H Tilly","year":"2015","journal-title":"Ann Oncol"},{"issue":"5","key":"pone.0311261.ref005","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1002\/ajh.26149","article-title":"Relapsed\/Refractory International Prognostic Index: an international prognostic calculator for relapsed\/refractory diffuse large B-cell lymphoma","volume":"96","author":"MJ Maurer","year":"2021","journal-title":"AM J Haematol"},{"key":"pone.0311261.ref006","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"AL Beam","year":"2018","journal-title":"JAMA"},{"key":"pone.0311261.ref007","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"issue":"11","key":"pone.0311261.ref008","first-page":"31008","article-title":"Role of Artificial Intelligence and Machine Learning in Prediction, Diagnosis, and Prognosis of Cancer","volume":"14","author":"K Gaur","year":"2022","journal-title":"Cureus"},{"key":"pone.0311261.ref009","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.2147\/JMDH.S410301","article-title":"Machine Learning and AI in Cancer Prognosis, Prediction, and Treatment Selection: A Critical Approach","volume":"16","author":"B Zhang","year":"2023","journal-title":"J Multidiscip Healthc"},{"key":"pone.0311261.ref010","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1111\/bjh.16915","article-title":"Machine Learning and artificial intelligence in haematology","volume":"192","author":"R Shouval","year":"2021","journal-title":"BJH"},{"issue":"1","key":"pone.0311261.ref011","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1093\/jalm\/jfac108","article-title":"Hematology and Machine Learning","volume":"8","author":"AE Obstfeld","year":"2023","journal-title":"J Appl Lab Med"},{"issue":"10","key":"pone.0311261.ref012","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1016\/j.ccell.2021.08.011","article-title":"The landscape of tumor cell states and ecosystems in diffuse large B cell lymphoma","volume":"39","author":"CB Steen","year":"2021","journal-title":"Cancer Cell"},{"issue":"6","key":"pone.0311261.ref013","doi-asserted-by":"crossref","first-page":"847","DOI":"10.2174\/1573409920666230821102806","article-title":"Machine learning algorithms identify target genes and the molecular mechanism of matrine against diffuse large B-cell lymphoma","volume":"20","author":"Y Zhu","year":"2024","journal-title":"Curr Comput Aided Drug Des"},{"key":"pone.0311261.ref014","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric estimation from incomplete observation","volume":"53","author":"EL Kaplan","year":"1958","journal-title":"Journal of the American Statistical Association"},{"issue":"3","key":"pone.0311261.ref015","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"P Virtanen","year":"2020","journal-title":"Nature Methods"},{"issue":"31","key":"pone.0311261.ref016","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.21105\/joss.01026","article-title":"Pingouin: statistics in Python","volume":"3","author":"R. Vallat","year":"2018","journal-title":"Journal of Open Source Software"},{"issue":"60","key":"pone.0311261.ref017","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"Seaborn: statistical data visualization","volume":"6","author":"ML Waskom","year":"2021","journal-title":"Journal of Open Source Software"},{"issue":"40","key":"pone.0311261.ref018","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.21105\/joss.01317","article-title":"Lifelines: survival analysis in Python","volume":"4","author":"P. Davidson","year":"2019","journal-title":"Journal of Open Source Software"},{"key":"pone.0311261.ref019","first-page":"87","volume-title":"Jupyter Notebooks\u2014a publishing format for reproducible computational workflows","author":"T. Kluyver","year":"2016"},{"key":"pone.0311261.ref020","volume-title":"Information Computing and Applications","author":"Y. Liu","year":"2012"},{"key":"pone.0311261.ref021","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"T Chen","year":"2016"},{"issue":"1","key":"pone.0311261.ref022","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"JA Hanley","year":"1982","journal-title":"Radiology"},{"key":"pone.0311261.ref023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A review on evaluation metrics for data classification evaluations","volume":"5","author":"M Hossin","year":"2015","journal-title":"Int. J. Data Min. Knowl. Manag. Process"},{"issue":"4","key":"pone.0311261.ref024","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"M Sokolova","year":"2009","journal-title":"Inf. Process. Manage"},{"key":"pone.0311261.ref025","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"pone.0311261.ref026","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1007\/s00259-012-2320-8","article-title":"Interim FDG PET\/CT as a prognostic factor in diffuse large B-cell lymphoma","volume":"40","author":"S Fuertes","year":"2013","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"pone.0311261.ref027","doi-asserted-by":"crossref","first-page":"3144","DOI":"10.1200\/JCO.2014.59.1339","article-title":"Prediction of allogeneic hematopoietic stem-cell transplantation mortality 100 days after transplantation using a machine learning algorithm: a European group for blood and marrow transplantation acute leukemia working party retrospective data mining study","volume":"33","author":"R Shouval","year":"2015","journal-title":"J Clin Oncol"},{"issue":"8","key":"pone.0311261.ref028","doi-asserted-by":"crossref","first-page":"e0161401","DOI":"10.1371\/journal.pone.0161401","article-title":"Prediction of clinical deterioration in hospitalized adult patients with hematologic malignancies using a neural network model","volume":"11","author":"SB Hu","year":"2016","journal-title":"PLoS One"},{"issue":"4","key":"pone.0311261.ref029","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/j.jval.2019.01.006","article-title":"Bayesian networks for risk prediction using real-world data: a tool for precision medicine","volume":"22","author":"P Arora","year":"2019","journal-title":"Value Health"},{"key":"pone.0311261.ref030","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.artmed.2013.01.004","article-title":"Impact of precision of Bayesian network parameters on accuracy of medical diagnostic systems","volume":"57","author":"A Onisko","year":"2013","journal-title":"Artificial Intelligence in Medicine"},{"issue":"2\u20133","key":"pone.0311261.ref031","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1023\/A:1007413511361","article-title":"On the optimality of the simple Bayesian classifier under zero-one loss","volume":"29","author":"P Domingos","year":"1997","journal-title":"Machine Learning"},{"issue":"1","key":"pone.0311261.ref032","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1111\/j.1365-2753.2011.01762.x","article-title":"A na\u00efve Bayes classifier for planning transfusion requirements in heart surgery","volume":"19","author":"G Cevenini","year":"2013","journal-title":"Eval Clin Pract"},{"key":"pone.0311261.ref033","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1145\/2939672.2939778","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"MT Ribeiro","year":"2016"},{"key":"pone.0311261.ref034","doi-asserted-by":"crossref","first-page":"337","DOI":"10.3322\/caac.21150","article-title":"Electronic patient-reported outcome systems in oncology clinical practice","volume":"62","author":"AV Bennett","year":"2012","journal-title":"CA-Cancer J Clin"},{"issue":"Suppl 1","key":"pone.0311261.ref035","doi-asserted-by":"crossref","first-page":"S32","DOI":"10.1097\/MLR.0b013e3181db53a4","article-title":"Electronic patient-reported data capture as a foundation of rapid learning cancer care","volume":"48","author":"AP Abernethy","year":"2010","journal-title":"Med Care"},{"key":"pone.0311261.ref036","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1056\/NEJMoa2115304","article-title":"Polatuzumab vedotin in previously untreated diffuse large B-cell lymphoma","volume":"386","author":"H Tilly","year":"2022","journal-title":"NEJM"},{"issue":"5","key":"pone.0311261.ref037","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1007\/s00277-014-2271-1","article-title":"Prognosis of patients with diffuse large B cell lymphoma not reaching complete response or relapsing after frontline chemotherapy or immunochemotherapy","volume":"94","author":"J Rovira","year":"2015","journal-title":"Ann Hematol"},{"issue":"16","key":"pone.0311261.ref038","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1182\/blood-2017-03-769620","article-title":"Outcomes in refractory diffuse large B-cell lymphoma: results from the international SCHOLAR-1 study","volume":"130","author":"M Crump","year":"2017","journal-title":"Blood"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0311261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T17:23:05Z","timestamp":1727803385000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0311261"}},"subtitle":[],"editor":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0311261","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]}}}