{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T04:11:55Z","timestamp":1791432715334,"version":"4.3.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Ministry of Health & Welfare, Republic of Korea","award":["HR22C1363"],"award-info":[{"award-number":["HR22C1363"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Lymphedema is a disease that refers to tissue swelling caused by an accumulation of protein-rich fluid that is usually drained through the lymphatic system. Detection of lymphedema is often based on expensive diagnoses such as bioimpedance spectroscopy, shear wave elastography, computed tomography, etc. In current machine learning models for lymphedema prediction, reliance on observable symptoms reported by patients introduces the possibility of errors in patient-input data. Moreover, these symptoms are often absent during the initial stages of lymphedema, creating challenges in its early detection. Identifying lymphedema before these observable symptoms manifest would greatly benefit patients by potentially minimizing the discomfort caused by these symptoms. In this study, we propose to use new data, such as complete blood count, serum, and therapy data, to develop predictive models for lymphedema. This approach aims to compensate for the limitations of using only observable symptoms data. We collected data from 2137 patients, including 356 patients with lymphedema and 1781 patients without lymphedema, with the lymphedema status of each patient confirmed by clinicians. The data for each patient included: (1) a complete blood count (CBC) test, (2) a serum test, and (3) therapy information. We used various machine learning algorithms (i.e. random forest, gradient boosting, decision tree, logistic regression, and artificial neural network) to develop predictive models on the training dataset (i.e. 80% of the data) and evaluated the models on the external validation dataset (i.e. 20% of the data). After selecting the best predictive models, we created a web application to aid medical doctors and clinicians in the rapid screening of lymphedema patients. A dataset of 2137 patients was assembled from Seoul National University Bundang Hospital. Predictive models based on the random forest algorithm exhibited satisfactory performance (balanced accuracy\u2009=\u200987.0\u2009\u00b1\u20090.7%, sensitivity\u2009=\u200984.3\u2009\u00b1\u20090.6%, specificity\u2009=\u200989.1\u2009\u00b1\u20091.5%, precision\u2009=\u200997.4\u2009\u00b1\u20090.7%, F1 score\u2009=\u200990.4\u2009\u00b1\u20090.4%, and AUC\u2009=\u20090.931\u2009\u00b1\u20090.007). We developed a web application to facilitate the swift screening of lymphedema among medical practitioners: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/snubhtxt.shinyapps.io\/SNUBH_Lymphedema\">https:\/\/snubhtxt.shinyapps.io\/SNUBH_Lymphedema<\/jats:ext-link>. Our study introduces a novel tool for the early detection of lymphedema and establishes the foundation for future investigations into predicting different stages of the condition.<\/jats:p>","DOI":"10.1038\/s41598-023-46567-1","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T11:01:44Z","timestamp":1699873304000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Development of predictive models for lymphedema by using blood tests and therapy data"],"prefix":"10.1038","volume":"13","author":[{"given":"Xuan-Tung","family":"Trinh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pham Ngoc","family":"Chien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nguyen-Van","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le Thi","family":"Van Anh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nguyen Ngan","family":"Giang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sun-Young","family":"Nam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujin","family":"Myung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"46567_CR1","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/S0002-9343(00)00727-0","volume":"110","author":"SG Rockson","year":"2001","unstructured":"Rockson, S. G. Lymphedema. Am. J. Med. 110, 288\u2013295 (2001).","journal-title":"Am. J. Med."},{"key":"46567_CR2","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1177\/1358836x9800300209","volume":"3","author":"A Szuba","year":"1998","unstructured":"Szuba, A. & Rockson, S. G. Lymphedema: Classification, diagnosis and therapy. Vasc. Med. 3, 145\u2013156. https:\/\/doi.org\/10.1177\/1358836x9800300209 (1998).","journal-title":"Vasc. Med."},{"key":"46567_CR3","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/j.jpainsymman.2009.04.030","volume":"38","author":"MR Fu","year":"2009","unstructured":"Fu, M. R. & Rosedale, M. Breast cancer survivors\u2019 experiences of lymphedema-related symptoms. J. Pain Symptom Manag. 38, 849\u2013859 (2009).","journal-title":"J. Pain Symptom Manag."},{"key":"46567_CR4","first-page":"193","volume":"39","author":"G Jager","year":"2006","unstructured":"Jager, G., Doller, W. & Roth, R. Quality-of-life and body image impairments in patients with lymphedema. Lymphology 39, 193\u2013200 (2006).","journal-title":"Lymphology"},{"key":"46567_CR5","first-page":"170","volume":"49","author":"Executive Committee","year":"2016","unstructured":"Executive Committee. The diagnosis and treatment of peripheral lymphedema: 2016 consensus document of the International Society of Lymphology. Lymphology 49, 170\u2013184 (2016).","journal-title":"Lymphology"},{"key":"46567_CR6","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.1245\/s10434-018-6601-8","volume":"25","author":"LJ Kilgore","year":"2018","unstructured":"Kilgore, L. J. et al. Reducing breast cancer-related lymphedema (BCRL) through prospective surveillance monitoring using bioimpedance spectroscopy (BIS) and patient directed self-interventions. Ann. Surg. Oncol. 25, 2948\u20132952 (2018).","journal-title":"Ann. Surg. Oncol."},{"key":"46567_CR7","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1007\/s10549-017-4451-x","volume":"166","author":"DI Kaufman","year":"2017","unstructured":"Kaufman, D. I., Shah, C., Vicini, F. A. & Rizzi, M. Utilization of bioimpedance spectroscopy in the prevention of chronic breast cancer-related lymphedema. Breast Cancer Res. Treat. 166, 809\u2013815 (2017).","journal-title":"Breast Cancer Res. Treat."},{"key":"46567_CR8","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1089\/lrb.2018.0012","volume":"17","author":"Z Erdogan Iyigun","year":"2019","unstructured":"Erdogan Iyigun, Z. et al. The role of elastography in diagnosis and staging of breast cancer-related lymphedema. Lymphat. Res. Biol. 17, 334\u2013339 (2019).","journal-title":"Lymphat. Res. Biol."},{"key":"46567_CR9","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1089\/lrb.2005.3.208","volume":"3","author":"JM Armer","year":"2005","unstructured":"Armer, J. M. & Stewart, B. R. A comparison of four diagnostic criteria for lymphedema in a post-breast cancer population. Lymphat. Res. Biol. 3, 208\u2013217 (2005).","journal-title":"Lymphat. Res. Biol."},{"key":"46567_CR10","doi-asserted-by":"publisher","first-page":"102023","DOI":"10.1016\/j.ejon.2021.102023","volume":"54","author":"X Wei","year":"2021","unstructured":"Wei, X. et al. Developing and validating a prediction model for lymphedema detection in breast cancer survivors. Eur. J. Oncol. Nurs. 54, 102023 (2021).","journal-title":"Eur. J. Oncol. Nurs."},{"key":"46567_CR11","doi-asserted-by":"publisher","first-page":"17","DOI":"10.21037\/mhealth.2018.04.02","volume":"4","author":"MR Fu","year":"2018","unstructured":"Fu, M. R. et al. Machine learning for detection of lymphedema among breast cancer survivors. mHealth 4, 17\u201317 (2018).","journal-title":"mHealth"},{"key":"46567_CR12","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1097\/00006199-200311000-00004","volume":"52","author":"JM Armer","year":"2003","unstructured":"Armer, J. M., Radina, M. E., Porock, D. & Culbertson, S. D. Predicting breast cancer-related lymphedema using self-reported symptoms. Nurs. Res. 52, 370\u2013379 (2003).","journal-title":"Nurs. Res."},{"key":"46567_CR13","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1159\/000443491","volume":"11","author":"L Wang","year":"2016","unstructured":"Wang, L. et al. A scoring system to predict arm lymphedema risk for individual Chinese breast cancer patients. Breast Care 11, 52\u201356 (2016).","journal-title":"Breast Care"},{"key":"46567_CR14","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/s00520-018-4388-6","volume":"27","author":"IW Penn","year":"2019","unstructured":"Penn, I. W. et al. Risk factors and prediction model for persistent breast-cancer-related lymphedema: A 5-year cohort study. Support. Care Cancer 27, 991\u20131000 (2019).","journal-title":"Support. Care Cancer"},{"key":"46567_CR15","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1111\/jan.15005","volume":"78","author":"P Mart\u00ednez-Jaimez","year":"2022","unstructured":"Mart\u00ednez-Jaimez, P. et al. Breast cancer-related lymphoedema: Risk factors and prediction model. J. Adv. Nurs. 78, 765\u2013775 (2022).","journal-title":"J. Adv. Nurs."},{"key":"46567_CR16","doi-asserted-by":"publisher","first-page":"2972","DOI":"10.1245\/s10434-017-5960-x","volume":"24","author":"TT Nguyen","year":"2017","unstructured":"Nguyen, T. T., Hoskin, T. L., Habermann, E. B., Cheville, A. L. & Boughey, J. C. Breast cancer-related lymphedema risk is related to multidisciplinary treatment and not surgery alone: Results from a large cohort study. Ann. Surg. Oncol. 24, 2972\u20132980 (2017).","journal-title":"Ann. Surg. Oncol."},{"key":"46567_CR17","doi-asserted-by":"publisher","DOI":"10.2147\/BCTT.S87854","author":"MR Fu","year":"2015","unstructured":"Fu, M. R. et al. Symptom report in detecting breast cancer-related lymphedema. Breast Cancer Targets Ther. https:\/\/doi.org\/10.2147\/BCTT.S87854 (2015).","journal-title":"Breast Cancer Targets Ther."},{"key":"46567_CR18","doi-asserted-by":"publisher","first-page":"241","DOI":"10.5306\/wjco.v5.i3.241","volume":"5","author":"MR Fu","year":"2014","unstructured":"Fu, M. R. Breast cancer-related lymphedema: Symptoms, diagnosis, risk reduction, and management. World J. Clin. Oncol. 5, 241 (2014).","journal-title":"World J. Clin. Oncol."},{"key":"46567_CR19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"46567_CR20","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J. H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29, 1189\u20131232 (2001).","journal-title":"Ann. Stat."},{"key":"46567_CR21","unstructured":"R Core Team. R: A language and environment for statistical computing (2022)."},{"key":"46567_CR22","unstructured":"RStudio Team. RStudio: Integrated development environment for R (2022)."},{"key":"46567_CR23","unstructured":"Schauberger, P. & Walker, A. openxlsx: Read, write and edit xlsx files (2021)."},{"key":"46567_CR24","unstructured":"Grosjean, P. SciViews::R (2022)."},{"key":"46567_CR25","unstructured":"Kuhn, M. caret: Classification and regression training. Astrophys. Source Code Libr. ascl--1505 (2021)."},{"key":"46567_CR26","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1021\/ci034160g","volume":"43","author":"V Svetnik","year":"2003","unstructured":"Svetnik, V. et al. Random forest: A classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci. 43, 1947\u20131958 (2003).","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"46567_CR27","unstructured":"Chen, T. et al. xgboost: Extreme gradient boosting (2022)."},{"key":"46567_CR28","unstructured":"Kuhn, M. & Quinlan, R. C50: C5.0 Decision trees and rule-based models (2022)."},{"key":"46567_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21706-2","volume-title":"Modern Applied Statistics with S","author":"WN Venables","year":"2002","unstructured":"Venables, W. N. & Ripley, B. D. Modern Applied Statistics with S (Springer, 2002)."},{"key":"46567_CR30","unstructured":"Chang, W. et al. shiny: Web application framework for R (2021)."},{"key":"46567_CR31","first-page":"1089","volume":"5","author":"Y Bengio","year":"2004","unstructured":"Bengio, Y. & Grandvalet, Y. No unbiased estimator of the variance of K-fold cross-validation Yoshua. J. Mach. Learn. Res. 5, 1089\u20131105 (2004).","journal-title":"J. Mach. Learn. Res."},{"key":"46567_CR32","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley, J. A. & McNeil, B. J. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143, 29\u201336 (1982).","journal-title":"Radiology"},{"key":"46567_CR33","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s11764-012-0251-9","volume":"7","author":"SA Dominick","year":"2013","unstructured":"Dominick, S. A., Madlensky, L., Natarajan, L. & Pierce, J. P. Risk factors associated with breast cancer-related lymphedema in the WHEL Study. J. Cancer Surviv. 7, 115\u2013123 (2013).","journal-title":"J. Cancer Surviv."},{"key":"46567_CR34","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1001\/archsurg.2010.231","volume":"145","author":"ML Kwan","year":"2010","unstructured":"Kwan, M. L. et al. Risk factors for lymphedema in a prospective breast cancer survivorship study: The pathways study. Arch. Surg. 145, 1055\u20131063 (2010).","journal-title":"Arch. Surg."},{"key":"46567_CR35","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1158\/1055-9965.EPI-06-0168","volume":"16","author":"ED Paskett","year":"2007","unstructured":"Paskett, E. D., Naughton, M. J., McCoy, T. P., Case, L. D. & Abbott, J. M. The epidemiology of arm and hand swelling in premenopausal breast cancer survivors. Cancer Epidemiol. Biomark. Prev. 16, 775\u2013782 (2007).","journal-title":"Cancer Epidemiol. Biomark. Prev."},{"key":"46567_CR36","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1002\/minf.201501019","volume":"35","author":"M Mathea","year":"2016","unstructured":"Mathea, M., Klingspohn, W. & Baumann, K. Chemoinformatic classification methods and their applicability domain. Mol. Inform. 35, 160\u2013180 (2016).","journal-title":"Mol. Inform."},{"key":"46567_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.chemolab.2015.04.013","volume":"145","author":"K Roy","year":"2015","unstructured":"Roy, K., Kar, S. & Ambure, P. On a simple approach for determining applicability domain of QSAR models. Chemom. Intell. Lab. Syst. 145, 22\u201329 (2015).","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"46567_CR38","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1039\/C8EN00061A","volume":"5","author":"X Trinh","year":"2018","unstructured":"Trinh, X. et al. Curation of datasets, assessment of their quality and completeness, and nanoSAR classification model development for metallic nanoparticles. Environ. Sci. Nano 5, 1902\u20131910 (2018).","journal-title":"Environ. Sci. Nano"},{"key":"46567_CR39","unstructured":"Poli\u010dar, P. G. & Stra\u017ear, M. Zupan. B. openTSNE a Modul. Python Libr. t-SNE Dimens. Reduct. Embed. bioRxiv, 731877 (2019)."},{"key":"46567_CR40","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1038\/s41592-018-0308-4","volume":"16","author":"GC Linderman","year":"2019","unstructured":"Linderman, G. C., Rachh, M., Hoskins, J. G., Steinerberger, S. & Kluger, Y. Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data. Nat. Methods 16, 243\u2013245 (2019).","journal-title":"Nat. Methods"},{"key":"46567_CR41","first-page":"3221","volume":"15","author":"L Van Der Maaten","year":"2014","unstructured":"Van Der Maaten, L. Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 3221\u20133245 (2014).","journal-title":"J. Mach. Learn. Res."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46567-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46567-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46567-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T11:02:32Z","timestamp":1699873352000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46567-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["46567"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-46567-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"15 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19720"}}