{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:06Z","timestamp":1785545046710,"version":"3.56.0"},"reference-count":41,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Limited data availability and privacy constraints hinder the development of robust survival prediction models for personalized treatment. Synthetic data offers a promising solution, preserving the statistical properties of real clinical data.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to quantitatively assess the feasibility of using synthetic data for survival prediction by evaluating model transfer performance to real-world hospital data, with a focus on model transfer strategies.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We developed and validated colorectal cancer survival prediction models using the National Cancer Data Center (NCDC) synthetic data (30,683 patients from 3 Korean institutions) for pretraining and real hospital data (2170 patients from Hwasun Jeonnam University Hospital) for external validation. We evaluated 3 model transfer strategies\u2014domain adaptation, zero-shot, and ensemble\u2014using extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM). In total, 48 model configurations were tested, defined by the combination of algorithms (LightGBM and XGBoost), sampling technique (no-sampling, random undersampling [RUS], and synthetic minority oversampling technique combined with edited nearest neighbors [SMOTEENN]), model type (baseline, domain adaptation, zero-shot, and ensemble), and optimization objective (area under the precision-recall curve [AUPRC] and\n F<\/jats:italic>\n 1<\/jats:sub>\n ). The outcome was 7-year overall survival, evaluated using the AUPRC and Brier scores. Performance was compared against a hospital-only baseline using absolute values and deltas (\u0394AUPRC and \u0394Brier). Differences and corresponding 95% CIs were estimated on the held-out test set using 2000 bootstrap samples.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Zero-shot application reduced the AUPRC in most settings, and any marginal improvements observed in the remaining settings were not statistically significant. In contrast, the domain adaptation model improved AUPRC in 8\/12 combinations, with 4 statistically significant gains; the best setting (XGBoost+RUS+\n F<\/jats:italic>\n 1<\/jats:sub>\n optimization) achieved AUPRC=0.5391 (\u0394+0.1474;\n P<\/jats:italic>\n <.001). The soft ensemble increased AUPRC in 7\/12 combinations, with 3 statistically significant gains; the best setting (XGBoost+RUS+AUPRC optimization) achieved AUPRC=0.5060 (\n \u0394<\/jats:italic>\n +0.1258,\n P<\/jats:italic>\n =.002). For calibration, Brier scores improved in most domain adaptation and ensemble combinations, with a substantial proportion reaching statistical significance.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n When domain adaptation using local hospital data was applied, the model pretrained on synthetic data exhibited similar performance to the hospital-only baseline across various settings. This study demonstrates the methodological utility of a model transfer approach using NCDC synthetic data in a setting with limited data sharing. At the same time, it clarifies that while synthetic data can serve as a complement to local clinical data, it is not a substitute for real-world clinical models.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/86087","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T18:12:57Z","timestamp":1783447977000},"page":"e86087-e86087","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of the Applicability of Synthetic Data in the Development of Colorectal Cancer Survival Prediction Models: External Validation of Advanced Machine Learning Models Based on National Cancer Data Center Data"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3284-0205","authenticated-orcid":false,"given":"Yujeong","family":"Jang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8727-1955","authenticated-orcid":false,"given":"Jae Hoon","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0375-2157","authenticated-orcid":false,"given":"Heeyong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5796-4035","authenticated-orcid":false,"given":"You-Jin","family":"Joung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5833-4822","authenticated-orcid":false,"given":"Junho","family":"\u200dNang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1954-189X","authenticated-orcid":false,"given":"Chang Hyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1111\/cts.12884","article-title":"Precision medicine, AI, and the future of personalized health care","volume":"14","author":"Johnson","journal-title":"Clin Transl Sci"},{"issue":"Suppl 2","key":"R2","doi-asserted-by":"publisher","first-page":"93","DOI":"10.4137\/CIN.S13780","article-title":"Combined benefit of prediction and treatment: a criterion for evaluating clinical prediction models","volume":"13","author":"Billheimer","journal-title":"Cancer Inform"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s41060-018-0127-9","article-title":"Personalised medicine challenges: quality of data","volume":"6","author":"Cruz-Correia","journal-title":"Int J Data Sci Anal"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92799-4","article-title":"Long-term cancer survival prediction using multimodal deep learning","volume":"11","author":"Vale-Silva","journal-title":"Sci Rep"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.36011\/cpp.2024.6.e1","article-title":"Using medical big data for clinical research and legal considerations for the protection of personal information: the double-edged sword","volume":"6","author":"Kim","journal-title":"CPP"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011099","article-title":"Secondary use of electronic health record: opportunities and challenges","volume":"8","author":"Shah","journal-title":"IEEE Access"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1428501","article-title":"Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases","volume":"7","author":"Abbasi","journal-title":"Front Artif Intell"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-02078-1","article-title":"Application of machine learning in predicting survival outcomes involving real-world data: a scoping review","volume":"23","author":"Huang","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00927-3","article-title":"Harnessing the power of synthetic data in healthcare: innovation, application, and privacy","volume":"6","author":"Giuffr\u00e8","journal-title":"NPJ Digit Med"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","first-page":"e157","DOI":"10.1016\/S2589-7500(24)00196-1","article-title":"The urgent need to accelerate synthetic data privacy frameworks for medical research","volume":"7","author":"Arora","journal-title":"Lancet Digit Health"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108571","article-title":"Preserving privacy in healthcare: a systematic review of deep learning approaches for synthetic data generation","volume":"260","author":"Liu","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0793-0","article-title":"The validity of synthetic clinical data: a validation study of a leading synthetic data generator (Synthea) using clinical quality measures","volume":"19","author":"Chen","journal-title":"BMC Med Inform Decis Mak"},{"issue":"7","key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/18910","article-title":"Reliability of supervised machine learning using synthetic data in health care: model to preserve privacy for data sharing","volume":"8","author":"Rankin","journal-title":"JMIR Med Inform"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-72894-y","article-title":"Synthetic data for privacy-preserving clinical risk prediction","volume":"14","author":"Qian","journal-title":"Sci Rep"},{"issue":"7981","key":"R15","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","journal-title":"Nature"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.07.005","article-title":"Synthetic data generation methods in healthcare: a review on open-source tools and methods","volume":"23","author":"Pezoulas","journal-title":"Comput Struct Biotechnol J"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000082","article-title":"Synthetic data in health care: a narrative review","volume":"2","author":"Gonzales","journal-title":"PLOS Digit Health"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00614-9","article-title":"Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening","volume":"5","author":"Yang","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","journal-title":"J Big Data"},{"key":"R20","unstructured":"National Cancer Data Center. URL: https:\/\/www.cancerdata.re.kr\/main\/publicData\/publicDataList [Accessed 26-05-2026]"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69812-7","article-title":"Synthesis and quality assessment of combined time-series and static medical data using a real-world time-series generative adversarial network","volume":"14","author":"Kim","journal-title":"Sci Rep"},{"issue":"1-2","key":"R22","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","volume":"79","author":"Ben-David","journal-title":"Mach Learn"},{"issue":"3","key":"R23","doi-asserted-by":"publisher","DOI":"10.12771\/emj.2025.00668","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods: a Korean translation","volume":"48","author":"Collins","journal-title":"Ewha Med J"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Zhang X Li S Cheng Z Callcut R Petzold L . Domain adaptation for trauma mortality prediction in EHRs with feature disparity. Presented at: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Dec 9-12, 2021; Houston, TX, USA. [doi: 10.1109\/BIBM52615.2021.9669798] [Medline: 33664987]","DOI":"10.1109\/BIBM52615.2021.9669798"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","journal-title":"Proc IEEE"},{"issue":"10","key":"R26","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"R27","unstructured":"Major cancer mortality rate. National Cancer Information Center. URL: https:\/\/www.cancer.go.kr\/lay1\/program\/S1T211C214\/cancer\/view.do?cancer_seq=3797&menu_seq=3816 [Accessed 26-05-2026]"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s40537-020-00390-x","article-title":"Resampling imbalanced data for network intrusion detection datasets","volume":"8","author":"Bagui","journal-title":"J Big Data"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2024.100597","article-title":"Enhancing SMOTE for imbalanced data with abnormal minority instances","volume":"18","author":"Matharaarachchi","journal-title":"Machine Learning with Applications"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.10.005","article-title":"Analysis of sampling techniques for imbalanced data: an n=648 ADNI study","volume":"87","author":"Dubey","journal-title":"Neuroimage"},{"key":"R31","unstructured":"Ke G Meng Q Finley T et al. LightGBM: a highly efficient gradient boosting decision tree. Presented at: NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017; Long Beach, California, United States. URL: https:\/\/dl.acm.org\/doi\/10.5555\/3294996.3295074 [Accessed 25-06-2026]"},{"key":"R32","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C . XGBoost: a scalable tree boosting system. Presented at: KDD \u201916: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Aug 13-17, 2016:785-794; San Francisco, California, United States. [doi: 10.1145\/2939672.2939785]","DOI":"10.1145\/2939672.2939785"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","journal-title":"PLoS ONE"},{"issue":"14","key":"R34","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1001\/jama.2017.12126","article-title":"Discrimination and calibration of clinical prediction models: users\u2019 guides to the medical literature","volume":"318","author":"Alba","journal-title":"JAMA"},{"issue":"2","key":"R35","doi-asserted-by":"publisher","first-page":"588","DOI":"10.3390\/app16020588","article-title":"Reproducibility and environmental efficiency of metabolomics cancer modeling","volume":"16","author":"Jean-Quartier","journal-title":"Applied Sciences"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-06484-1","article-title":"Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine","volume":"12","author":"Guo","journal-title":"Sci Rep"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.07.013","article-title":"Enhancing prediction of short linear protein motifs with Wregex 3.0","volume":"23","author":"Prieto","journal-title":"Comput Struct Biotechnol J"},{"issue":"7","key":"R38","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.118.005122","article-title":"Privacy-preserving generative deep neural networks support clinical data sharing","volume":"12","author":"Beaulieu-Jones","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"6","key":"R39","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41551-021-00751-8","article-title":"Synthetic data in machine learning for medicine and healthcare","volume":"5","author":"Chen","journal-title":"Nat Biomed Eng"},{"key":"R40","unstructured":"Colorectal cancer multi-institutional clinical library synthetic dataset. National Cancer Data Center. URL: https:\/\/www.cancerdata.re.kr\/main\/publicData\/publicDataView [Accessed 06-07-2026]"},{"key":"R41","unstructured":"Github. YujeongJang\/colorectal-survival-domain-adaptation. URL: https:\/\/github.com\/YujeongJang\/colorectal-survival-domain-adaptation [Accessed 26-05-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:37Z","timestamp":1785536737000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":41,"URL":"https:\/\/doi.org\/10.2196\/86087","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"article-number":"v28i1e86087"}}