{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:02:29Z","timestamp":1790197349254,"version":"4.1.0"},"reference-count":41,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Liposuction is widely performed to remove localized fat deposits and improve body contour, yet individualized prediction of postoperative outcomes remains challenging. Existing machine learning (ML) studies have largely focused on single-outcome prediction, with limited attention to the interdependence between postoperative body weight and circumferential size.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and validate a chained multioutput ML framework to jointly predict postoperative body weight and circumferential size after liposuction using a large multicenter cohort from the 365mc network.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We analyzed a multicenter cohort of 7804 individuals who underwent liposuction in 2024 at 20 obesity specialty clinics in the 365mc network across South Korea. Using 15 predictors, we compared 8 individual ML models, an automated ML approach, 2 ensemble approaches, and chained multioutput regression models for predicting postoperative body weight and circumferential size. Models were developed using 5-fold cross-validation and evaluated on an independent test set. Performance was assessed using the coefficient of determination (\n R<\/jats:italic>\n 2<\/jats:sup>\n ), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), and feature importance was evaluated using Shapley additive explanation (SHAP) values. The selected model was integrated into a web-based clinical decision support system (CDSS).\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 7804 individuals who underwent liposuction were included; of these, 7612 (97.54%) were female. The chained extra trees regressor model with a weight-to-size prediction order achieved an\n R<\/jats:italic>\n 2<\/jats:sup>\n of 0.98, an RMSE of 2.36, an MAE of 1.24, and a MAPE of 2.19. The SHAP analysis identified preoperative weight as the main predictor of postoperative body weight and preoperative size and liposuction-related factors as key predictors of postoperative circumferential size. The final model was integrated into a web-based CDSS (365mc AI platform).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n We developed and validated a chained multioutput regression model to predict postoperative body weight and circumferential size after liposuction. Integrated into a web-based CDSS, the model may support patient-specific preoperative counseling and surgical planning.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82145","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T20:22:11Z","timestamp":1790194931000},"page":"e82145-e82145","source":"Crossref","is-referenced-by-count":0,"title":["Multioutput Machine Learning Model for Predicting Postoperative Outcomes After Liposuction: Algorithm Development and Validation Study in a Multicenter Cohort"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4607-7240","authenticated-orcid":false,"given":"Chaewoo","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4115-2947","authenticated-orcid":false,"given":"Seoyoung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-374X","authenticated-orcid":false,"given":"Jiyoung","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7961-2074","authenticated-orcid":false,"given":"Selin","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9750-419X","authenticated-orcid":false,"given":"Youn Chan","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9126-6442","authenticated-orcid":false,"given":"Jae Won","family":"Seo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2001-1823","authenticated-orcid":false,"given":"Sun Ho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1693-5480","authenticated-orcid":false,"given":"Jae Hyun","family":"Ahn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1628-9948","authenticated-orcid":false,"given":"Dong Keon","family":"Yon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0119-5818","authenticated-orcid":false,"given":"Sang Youl","family":"Rhee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1177\/1090820X10362728","article-title":"Updates and advances in liposuction","volume":"30","author":"Stephan","journal-title":"Aesthet Surg J"},{"issue":"20","key":"R2","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1007\/s00266-024-04260-2","article-title":"Trends in surgical and nonsurgical aesthetic procedures: a 14-year analysis of the International Society of Aesthetic Plastic Surgery-ISAPS","volume":"48","author":"Triana","journal-title":"Aesthetic Plast Surg"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjps.2025.01.055","article-title":"The effect of massive liposuction surgery of the abdomen and flanks on insulin and some adipokines","volume":"102","author":"Farhan","journal-title":"J Plast Reconstr Aesthet Surg"},{"issue":"8","key":"R4","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1016\/j.bjps.2019.04.008","article-title":"Quality of life following aesthetic liposuction: a prospective outcome study","volume":"72","author":"Papadopulos","journal-title":"J Plast Reconstr Aesthet Surg"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-04505-3","article-title":"Machine learning-based prediction of respiratory depression during sedation for liposuction","volume":"15","author":"Kim","journal-title":"Sci Rep"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.9639","article-title":"A machine learning trauma triage model for critical care transport","volume":"8","author":"Weidman","journal-title":"JAMA Netw Open"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5546-z","article-title":"Multi-target regression via input space expansion: treating targets as inputs","volume":"104","author":"Spyromitros-Xioufis","journal-title":"Mach Learn"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.geoen.2023.212403","article-title":"Multiphase flow rate prediction using chained multi-output regression models","volume":"231","author":"Wahid","journal-title":"Geoenergy Sci Eng"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3359115","article-title":"Deep learning for multi-output regression using gradient boosting","volume":"12","author":"Emami","journal-title":"IEEE Access"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-79654-y","article-title":"Predictive model for abdominal liposuction volume in patients with obesity using machine learning in a longitudinal multi-center study in Korea","volume":"14","author":"Sang","journal-title":"Sci Rep"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","journal-title":"BMJ"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-11837-7","article-title":"Prediction of birthweight with early and mid-pregnancy antenatal markers utilising machine learning and explainable artificial intelligence","volume":"15","author":"Pavanya","journal-title":"Sci Rep"},{"issue":"30","key":"R13","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adx5922","article-title":"In-body current path manipulation with minimal attenuation","volume":"11","author":"Kang","journal-title":"Sci Adv"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-71521-0","article-title":"A rigorous workflow and comparative analysis for accurate determination of vitrinite reflectance using data-driven approaches in the Persian Gulf region","volume":"14","author":"Kharazi Esfahani","journal-title":"Sci Rep"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103069","article-title":"Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation study","volume":"80","author":"Lee","journal-title":"EClinicalMedicine"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/80156","article-title":"Research on the prediction of coal workers\u2019 pneumoconiosis based on easily detectable clinical data: machine learning model development and validation study","volume":"14","author":"Li","journal-title":"JMIR Med Inform"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0286-7","article-title":"A data-driven framework for selecting and validating digital health metrics: use-case in neurological sensorimotor impairments","volume":"3","author":"Kanzler","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-96520-7","article-title":"Prediction of cardiovascular disease based on multiple feature selection and improved PSO-XGBoost model","volume":"15","author":"Cao","journal-title":"Sci Rep"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111533","article-title":"Transfer learning on stacked machine-learning model for predicting pull-out behavior of steel fibers from concrete","volume":"158","author":"Shafighfard","journal-title":"Eng Appl Artif Intell"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmrt.2022.10.153","article-title":"Data-driven compressive strength prediction of steel fiber reinforced concrete (SFRC) subjected to elevated temperatures using stacked machine learning algorithms","volume":"21","author":"Shafighfard","journal-title":"J Mater Res Technol"},{"issue":"C","key":"R21","doi-asserted-by":"publisher","first-page":"107657","DOI":"10.1016\/j.compstruc.2025.107657","article-title":"RAGN-R: a multi-subject ensemble machine-learning method for estimating mechanical properties of advanced structural materials","volume":"308","author":"Kazemi","journal-title":"Comput Struct"},{"issue":"3","key":"R22","doi-asserted-by":"publisher","first-page":"e158","DOI":"10.1016\/S2589-7500(20)30314-9","article-title":"Application of a novel machine learning framework for predicting non-metastatic prostate cancer-specific mortality in men using the Surveillance, Epidemiology, and End Results (SEER) database","volume":"3","author":"Lee","journal-title":"Lancet Digit Health"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"137186","DOI":"10.1016\/j.cej.2022.137186","article-title":"Multi-output machine learning models for kinetic data evaluation: a Fischer\u2013Tropsch synthesis case study","volume":"446","author":"Chakkingal","journal-title":"Chem Eng J"},{"issue":"7","key":"R24","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1109\/TNNLS.2019.2945133","article-title":"Survey on multi-output learning","volume":"31","author":"Xu","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00716-4","article-title":"Representational ethical model calibration","volume":"5","author":"Carruthers","journal-title":"NPJ Digit Med"},{"key":"R26","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. In: NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc; 2017. [doi: 10.5555\/3295222.3295230]"},{"issue":"9","key":"R27","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.2337\/dc25-0355","article-title":"A multimodal predictive model for chronic kidney disease and its association with vascular complications in patients with type 2 diabetes: model development and validation study in South Korea and the U.K","volume":"48","author":"Cho","journal-title":"Diabetes Care"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.2196\/57359","article-title":"Sex-specific trends in the prevalence of osteoarthritis and rheumatoid arthritis from 2005 to 2021 in South Korea: nationwide cross-sectional study","volume":"10","author":"Park","journal-title":"JMIR Public Health Surveill"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01436-1","article-title":"Real-world feasibility, accuracy and acceptability of automated retinal photography and AI-based cardiovascular disease risk assessment in Australian primary care settings: a pragmatic trial","volume":"8","author":"Hu","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00568-x","article-title":"Explainable AI decision support improves accuracy during telehealth strep throat screening","volume":"4","author":"Gomez","journal-title":"Commun Med (Lond)"},{"key":"R31","unstructured":"365mc. URL: https:\/\/365mc.vercel.app\/ [Accessed 05-09-2026]"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","first-page":"63e","DOI":"10.1097\/PRS.0000000000012240","article-title":"Artificial intelligence-driven blood loss prediction in large-volume liposuction: enhancing precision and patient safety","volume":"157","author":"Perez Pachon","journal-title":"Plast Reconstr Surg"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","first-page":"121","DOI":"10.7570\/jome23031","article-title":"Diagnosis of obesity: 2022 update of clinical practice guidelines for obesity by the Korean Society for the Study of Obesity","volume":"32","author":"Haam","journal-title":"J Obes Metab Syndr"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.gerinurse.2024.12.038","article-title":"Interpretable machine learning for identifying overweight and obesity risk factors of older adults in China","volume":"61","author":"Peng","journal-title":"Geriatr Nurs"},{"key":"R35","unstructured":"Douglas D Mishra A Ratner D Petersen F Terao K . Uncertainty propagation within chained models for machine learning reconstruction of neutrino-LAr interactions. arXiv. Preprint posted online on Nov 15, 2024. [doi: 10.48550\/arXiv.2411.09864]"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00338-8","article-title":"Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study","volume":"3","author":"Zhao","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37232-8","article-title":"Computational intelligence modeling of hyoscine drug solubility and solvent density in supercritical processing: gradient boosting, extra trees, and random forest models","volume":"13","author":"Ghazwani","journal-title":"Sci Rep"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33981-8","article-title":"Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data","volume":"13","author":"Grae\u00dfner","journal-title":"Sci Rep"},{"issue":"4","key":"R39","doi-asserted-by":"publisher","first-page":"101790","DOI":"10.1016\/j.jsis.2023.101790","article-title":"Machine learning advice in managerial decision-making: the overlooked role of decision makers\u2019 advice utilization","volume":"32","author":"Sturm","journal-title":"J Strateg Inf Syst"},{"issue":"3","key":"R40","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.0734","article-title":"Obesity disparities among adult single-race and multiracial Asian and Pacific Islander populations","volume":"7","author":"Bacong","journal-title":"JAMA Netw Open"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2025.116429","article-title":"Trends in adolescent violence victimization pre-, intra-, and post-COVID-19 pandemic in South Korea, 2012-2023: a nationwide cross-sectional study","volume":"348","author":"Park","journal-title":"Psychiatry Res"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T20:22:13Z","timestamp":1790194933000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e82145"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.2196\/82145","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"v14i1e82145"}}