{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:02:53Z","timestamp":1782846173318,"version":"3.54.5"},"reference-count":66,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Bioinform Biotech"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Risk group stratification based on the prediction of survival of patients with acute myeloid leukemia (AML) is complex. Despite common risk group categorization guidelines, the overall prognosis remains poor. Machine learning techniques have been shown to provide more accurate risk group stratification than conventional approaches using trial data. However, many time-to-event (TTE) models do not use training sets constrained to specific time windows, instead using aggregations of trial data.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to evaluate the performance of (1) random survival forest (RSF) and (2) Cox proportional hazard regression with elastic net regularization (CoxNet) for survival prediction of patients with AML within a censoring window trained with available data recorded at discrete time points during the United Kingdom National Cancer Research Institute Acute Myeloid Leukaemia 17 randomized controlled trial (AML17).<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n For each stage in the AML17 trial, separate models were trained for each exhaustive k-choice combination of available AML17 data subsets. Data combinations for each model were further constrained according to the respective trial stage to avoid data leakage. Preliminary Pearson correlation methods were used to remove directly correlating features with the TTE prediction (time-to-death\/5-y censoring point). Repeated k-fold stratified cross-validation was used on each dataset ablation to find candidate models. Permutation importance and elastic net regularization were used to monitor stability across validation folds and reduce the feature set of the highest performing stage RSF and Cox proportional hazard regression models, respectively. Finally, selected ablated models were re-evaluated using the nested, k-fold, stratified sampling cross-validation method with bootstrapping.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Concordance index ranked the best models for data constricted up to the end of induction (RSF=0.68, CoxNet=0.67), stages 1 (RSF=0.69, CoxNet=0.68), 2 (RSF=0.68, CoxNet=0.66), and 3 (RSF=0.69, CoxNet=0.63) of the trial.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study details the high prediction accuracy for time-to-survival-event predictions when training sets of CoxNet and RSF models, which are sequentially constricted to data measured up to the end of respective AML17 trial stages. The performance of these sequential TTE models is intended to justify their use as part of a wider digital twin system simulating multiple TTE outcomes for patients with AML.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/75678","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T22:05:07Z","timestamp":1767132307000},"page":"e75678-e75678","source":"Crossref","is-referenced-by-count":0,"title":["Random Survival Forest Versus Elastic-Net Regularized Cox Regression for Survival Prediction in Acute Myeloid Leukemia at Distinct Treatment Time Points: Model Performance Comparison Study"],"prefix":"10.2196","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2956-3206","authenticated-orcid":false,"given":"Ois\u00edn","family":"Brady","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4641-835X","authenticated-orcid":false,"given":"Sean","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3143-6854","authenticated-orcid":false,"given":"Peter","family":"Giles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4391-9802","authenticated-orcid":false,"given":"Caroline","family":"Alvares","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0951-3825","authenticated-orcid":false,"given":"Joanna","family":"Zabkiewicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0871-939X","authenticated-orcid":false,"given":"Carolina","family":"Fuentes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"R1","unstructured":"Cancers by body location\/system. National Cancer Institute. URL: https:\/\/www.cancer.gov\/types\/by-body-location [Accessed 25-03-2025]"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm5030033","article-title":"Acute myeloid leukemia: a concise review","volume":"5","author":"Saultz","journal-title":"J Clin Med"},{"issue":"5","key":"R3","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.21873\/anticanres.14269","article-title":"Characterization and prognosis of secondary acute myeloid leukemia in an Asian population: AML with antecedent hematological disease confers worst outcomes, irrespective of cytogenetic risk","volume":"40","author":"Kim","journal-title":"Anticancer Res"},{"issue":"10","key":"R4","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.3324\/haematol.2023.283225","article-title":"Down syndrome and leukemia: from basic mechanisms to clinical advances","volume":"108","author":"Baruchel","journal-title":"haematol"},{"issue":"3-4","key":"R5","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.beha.2014.10.002","article-title":"Fanconi anemia and the development of leukemia","volume":"27","author":"Alter","journal-title":"Best Pract Res Clin Haematol"},{"issue":"7","key":"R6","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1182\/blood-2007-06-098251","article-title":"Npm1 is a haploinsufficient suppressor of myeloid and lymphoid malignancies in the mouse","volume":"111","author":"Sportoletti","journal-title":"Blood"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1128\/JVI.41.2.489-500.1982","article-title":"McDonough feline sarcoma virus: characterization of the molecularly cloned provirus and its feline oncogene (v-fms)","volume":"41","author":"Donner","journal-title":"J Virol"},{"issue":"2","key":"R8","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1111\/cas.14274","article-title":"FLT3 mutations in acute myeloid leukemia: therapeutic paradigm beyond inhibitor development","volume":"111","author":"Kiyoi","journal-title":"Cancer Sci"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.blre.2020.100736","article-title":"A clandestine culprit with critical consequences: benzene and acute myeloid leukemia","volume":"47","author":"Shallis","journal-title":"Blood Rev"},{"issue":"8","key":"R10","doi-asserted-by":"publisher","first-page":"E125","DOI":"10.1002\/ajh.23744","article-title":"The relation between cigarette smoking and risk of acute myeloid leukemia: an updated meta-analysis of epidemiological studies","volume":"89","author":"Fircanis","journal-title":"Am J Hematol"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2022.103607","article-title":"Diagnosis and treatment of therapy-related acute myeloid leukemia","volume":"171","author":"Strickland","journal-title":"Crit Rev Oncol Hematol"},{"issue":"9","key":"R12","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14092182","article-title":"Dissecting the genetic and non-genetic heterogeneity of acute myeloid leukemia using next-generation sequencing and in vivo models","volume":"14","author":"Desai","journal-title":"Cancers (Basel)"},{"issue":"12","key":"R13","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1182\/blood.2022016867","article-title":"Diagnosis and management of AML in adults: 2022 recommendations from an international expert panel on behalf of the ELN","volume":"140","author":"D\u00f6hner","journal-title":"Blood"},{"issue":"20","key":"R14","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.1182\/blood-2016-03-643544","article-title":"The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia","volume":"127","author":"Arber","journal-title":"Blood"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.20892\/j.issn.2095-3941.2018.0055","article-title":"Next-generation sequencing and its clinical application","volume":"16","author":"Qin","journal-title":"Cancer Biol Med"},{"key":"R16","unstructured":"AML 17 protocol for patients aged under 60. Cardiff University Centre for Trials Research. URL: https:\/\/trials.cardiff.ac.uk\/aml\/17\/web\/files\/new3\/AML%2017%20Protocol%20June11%20v7.1%20.pdf [Accessed 12-10-2024]"},{"key":"R17","unstructured":"AML17. Cardiff University | Centre for Trials Research. URL: https:\/\/www.cardiff.ac.uk\/centre-for-trials-research\/research\/studies-and-trials\/view\/aml17 [Accessed 14-10-2024]"},{"issue":"25","key":"R18","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1182\/blood-2015-01-623447","article-title":"A randomized comparison of daunorubicin 90 mg\/m2 vs 60 mg\/m2 in AML induction: results from the UK NCRI AML17 trial in 1206 patients","volume":"125","author":"Burnett","journal-title":"Blood"},{"issue":"2","key":"R19","doi-asserted-by":"publisher","DOI":"10.1038\/s41408-021-00425-3","article-title":"Acute myeloid leukemia: current progress and future directions","volume":"11","author":"Kantarjian","journal-title":"Blood Cancer J"},{"key":"R20","unstructured":"Cancer stat facts: leukemia \u2014 acute myeloid leukemia (AML). National Cancer Institute \u2014 Surveillance, Epidemiology and End Results Program. URL: https:\/\/seer.cancer.gov\/statfacts\/html\/amyl.html [Accessed 22-10-2024]"},{"issue":"13","key":"R21","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15133512","article-title":"Modern risk stratification of acute myeloid leukemia in 2023: integrating established and emerging prognostic factors","volume":"15","author":"Boscaro","journal-title":"Cancers (Basel)"},{"key":"R22","unstructured":"Acute myeloid leukaemia (AML) statistics. Cancer Research UK. URL: https:\/\/www.cancerresearchuk.org\/health-professional\/cancer-statistics\/statistics-by-cancer-type\/leukaemia-aml [Accessed 12-05-2024]"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/s44230-023-00041-3","article-title":"Applications and techniques of machine learning in cancer classification: a systematic review","volume":"3","author":"Yaqoob","journal-title":"Hum-Cent Intell Syst"},{"issue":"Supplement 1","key":"R24","doi-asserted-by":"publisher","first-page":"6300","DOI":"10.1182\/blood-2022-163201","article-title":"Survival prediction optimization of acute myeloid leukemia based on T-cell function-related genes and plasma proteins","volume":"140","author":"Chen","journal-title":"Blood"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1177\/1176935119835544","article-title":"Predicting complete remission of acute myeloid leukemia: machine learning applied to gene expression","volume":"18","author":"Gal","journal-title":"Cancer Inform"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32103-8","article-title":"Unified classification and risk-stratification in acute myeloid leukemia","volume":"13","author":"Tazi","journal-title":"Nat Commun"},{"key":"R27","unstructured":"AML18. Cardiff University | Centre for Trials Research. URL: https:\/\/www.cardiff.ac.uk\/centre-for-trials-research\/research\/studies-and-trials\/view\/aml18 [Accessed 09-05-2024]"},{"issue":"34","key":"R28","doi-asserted-by":"publisher","first-page":"4084","DOI":"10.1200\/JCO.23.02631","article-title":"Risk stratification in older intensively treated patients with AML","volume":"42","author":"Versluis","journal-title":"JCO"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2016.03.009","article-title":"Adapting machine learning techniques to censored time-to-event health record data: a general-purpose approach using inverse probability of censoring weighting","volume":"61","author":"Vock","journal-title":"J Biomed Inform"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01679-6","article-title":"Survival prediction models: an introduction to discrete-time modeling","volume":"22","author":"Suresh","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","journal-title":"Ann Appl Stat"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1111\/j.1541-0420.2009.01287.x","article-title":"Statistical methods for analyzing right-censored length-biased data under Cox model","volume":"66","author":"Qin","journal-title":"Biometrics"},{"issue":"13","key":"R34","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.1093\/bioinformatics\/bti422","article-title":"Penalized Cox regression analysis in the high-dimensional and low-sample size settings, with applications to microarray gene expression data","volume":"21","author":"Gui","journal-title":"Bioinformatics"},{"issue":"2","key":"R35","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","journal-title":"Journal of the Royal Statistical Society Series B"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-13448-3","article-title":"A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling","volume":"7","author":"Leger","journal-title":"Sci Rep"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104635","article-title":"Comparison of time-to-event machine learning models in predicting oral cavity cancer prognosis","volume":"157","author":"Adeoye","journal-title":"Int J Med Inform"},{"issue":"4","key":"R38","doi-asserted-by":"publisher","first-page":"8582","DOI":"10.1016\/j.eswa.2008.10.023","article-title":"The comparisons of random survival forests and Cox regression analysis with simulation and an application related to breast cancer","volume":"36","author":"Kurt Omurlu","journal-title":"Expert Syst Appl"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-28393-7","article-title":"Comparing machine learning approaches to incorporate time-varying covariates in predicting cancer survival time","volume":"13","author":"Cygu","journal-title":"Sci Rep"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92944-z","article-title":"A comparison of time to event analysis methods, using weight status and breast cancer as a case study","volume":"11","author":"Aivaliotis","journal-title":"Sci Rep"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.551420","article-title":"A comparison study of machine learning (random survival forest) and classic statistic (Cox proportional hazards) for predicting progression in high-grade glioma after proton and carbon ion radiotherapy","volume":"10","author":"Qiu","journal-title":"Front Oncol"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-021-01375-x","article-title":"Random survival forests for dynamic predictions of a time-to-event outcome using a longitudinal biomarker","volume":"21","author":"Pickett","journal-title":"BMC Med Res Methodol"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2019.10.001","article-title":"Enabling technologies and tools for digital twin","volume":"58","author":"Qi","journal-title":"Journal of Manufacturing Systems"},{"key":"R44","doi-asserted-by":"publisher","DOI":"10.2147\/OTT.S236740","article-title":"FMS-like Tyrosine Kinase 3 inhibitors in the treatment of acute myeloid leukemia: an update on the emerging evidence and safety profile","volume":"16","author":"Garciaz","journal-title":"Onco Targets Ther"},{"key":"R45","unstructured":"Hawk Cardiff Research Datastore (RDS) access VM. Supercomputing Wales Portal. URL: https:\/\/portal.supercomputing.wales\/index.php\/hawk-cardiff-research-datastore-rds-access-vm\/ [Accessed 08-04-2025]"},{"issue":"4","key":"R46","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1111\/j.1365-2141.1976.tb03563.x","article-title":"Proposals for the classification of the acute leukaemias. French-American-British (FAB) co-operative group","volume":"33","author":"Bennett","journal-title":"Br J Haematol"},{"key":"R47","unstructured":"ECOG performance status scale. ECOG-ACRIN Cancer Research Group. URL: https:\/\/ecog-acrin.org\/resources\/ecog-performance-status\/ [Accessed 08-03-2025]"},{"key":"R48","unstructured":"Centre for Trials Research | Home. Cardiff University. URL: https:\/\/www.cardiff.ac.uk\/centre-for-trials-research [Accessed 12-10-2024]"},{"issue":"2","key":"R49","doi-asserted-by":"publisher","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An overview of overfitting and its solutions","volume":"1168","author":"Ying","journal-title":"J Phys: Conf Ser"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.103","article-title":"An introduction to deep learning in natural language processing: models, techniques, and tools","volume":"470","author":"Lauriola","journal-title":"Neurocomputing"},{"key":"R51","unstructured":"Pandas.DataFrame. pandas. URL: https:\/\/pandas.pydata.org\/docs\/reference\/api\/pandas.DataFrame.html [Accessed 14-10-2024]"},{"key":"R52","unstructured":"StandardScaler. scikit-learn. URL: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.preprocessing.StandardScaler.html [Accessed 12-10-2024]"},{"key":"R53","unstructured":"General concepts. The Open Group. URL: https:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/basedefs\/V1_chap04.html#tag_04_16 [Accessed 12-10-2024]"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109924","article-title":"The choice of scaling technique matters for classification performance","volume":"133","author":"de Amorim","journal-title":"Appl Soft Comput"},{"issue":"10","key":"R55","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","journal-title":"Bioinformatics"},{"key":"R56","unstructured":"Belle V Pelckmans K Suykens J Huffel S . Presented at: Survival SVM: a practical scalable algorithm; Apr 23-25, 2008; Bruges, Belgium. URL: https:\/\/www.esann.org\/sites\/default\/files\/proceedings\/legacy\/es2008-95.pdf"},{"key":"R57","unstructured":"Sksurv.svm.fastsurvivalsvm. scikit-survival 0271. URL: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.preprocessing.StandardScaler.html [Accessed 27-03-2025]"},{"issue":"22","key":"R58","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1182\/blood.V128.22.897.897","article-title":"Long term follow up from the NCRI AML17 trial of attenuated arsenic trioxide and ATRA therapy for newly diagnosed and relapsed acute promyelocytic leukaemia","volume":"128","author":"Russell","journal-title":"Blood"},{"key":"R59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2020.107095","article-title":"Estimation of incident dynamic AUC in practice","volume":"154","author":"van Geloven","journal-title":"Comput Stat Data Anal"},{"issue":"3","key":"R60","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s10844-015-0368-1","article-title":"Types of minority class examples and their influence on learning classifiers from imbalanced data","volume":"46","author":"Napierala","journal-title":"J Intell Inf Syst"},{"key":"R61","unstructured":"Datasets: imbalanced datasets. 'Machine Learning\u2019, Google for Developers. URL: https:\/\/developers.google.com\/machine-learning\/crash-course\/overfitting\/imbalanced-datasets [Accessed 14-01-2025]"},{"key":"R62","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","journal-title":"jair"},{"key":"R63","unstructured":"Sksurv.metrics.concordance_index_ipcw. scikit-survival 0270. URL: https:\/\/scikit-survival.readthedocs.io\/en\/stable\/api\/generated\/sksurv.metrics.concordance_index_ipcw.html [Accessed 11-03-2025]"},{"key":"R64","doi-asserted-by":"publisher","DOI":"10.2147\/CMAR.S225123","article-title":"Impact Of ELN risk stratification, induction chemotherapy regimens and hematopoietic stem cell transplantation on outcomes in hyperleukocytic acute myeloid leukemia with initial white blood cell count more than 100 \u00d7 10\/L","volume":"11","author":"Feng","journal-title":"Cancer Manag Res"},{"issue":"6","key":"R65","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1182\/bloodadvances.2019001335","article-title":"The prognostic impact of FLT3-ITD and NPM1 mutation in adult AML is age-dependent in the population-based setting","volume":"4","author":"Juliusson","journal-title":"Blood Adv"},{"key":"R66","unstructured":"Centre for trials research - data requests. Cardiff University. URL: https:\/\/www.cardiff.ac.uk\/centre-for-trials-research\/collaborate-with-us\/data-requests\/ [Accessed 06-04-2026]"}],"container-title":["JMIR Bioinformatics and Biotechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bioinform.jmir.org\/2026\/1\/e75678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:06:50Z","timestamp":1782842810000},"score":1,"resource":{"primary":{"URL":"https:\/\/bioinform.jmir.org\/2026\/1\/e75678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":66,"URL":"https:\/\/doi.org\/10.2196\/75678","relation":{},"ISSN":["2563-3570"],"issn-type":[{"value":"2563-3570","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"article-number":"v7i3e75678"}}