{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:08:45Z","timestamp":1780463325316,"version":"3.54.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To investigate risk factors for rebleeding in patients during the acute phase of intracerebral hemorrhage, compare the predictive performance of various machine learning models, and develop an optimal predictive model based on SHAP interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective analysis of clinical data from 368 patients with intracerebral hemorrhage was conducted. First, the chi-square test and the Mann\u2013Whitney U test were used to compare the rebleeding group with the non-rebleeding group; Lasso regression was then adopted to screen predictive factors. Based on the six core variables identified, the 10-fold cross-validation performance of nine models, XGBoost, logistic regression, LightGBM, random forest, AdaBoost, decision tree, GBDT, Gaussian Naive Bayes, and k-nearest neighbors, was compared. The most effective GBDT algorithm was used as the foundation, and four additional potential variables were incorporated based on clinical relevance to construct a final GBDT model comprising 10 variables. Bootstrap resampling (1,000 times) was used to calculate the confidence interval for the model\u2019s AUC. Calibration curves and decision curves were employed to evaluate the model\u2019s calibration and clinical utility, while SHAP values were utilized for global and local interpretation. SHAP dependency plots were generated for each feature, and a predictive website was ultimately developed based on this model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      There were statistically significant differences between the two groups in the history of anticoagulant or antiplatelet therapy, hematoma morphology, intraventricular hemorrhage, body temperature, white blood cell count, time from onset to CT scan, hematoma volume, Hematoma Heterogeneity Index (HII), GCS score, lactate, and partial pressure of carbon dioxide (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05). Lasso regression identified six variables: Shape, history of anticoagulant use, time from onset to CT, HII, GCS, and age. In the six-variable model, GBDT achieved the highest AUC (0.967, 95% CI 0.932\u20131.000) on the validation set. After incorporating DD, intraventricular hemorrhage, history of hypertension, and hematoma volume (V), the final 10-variable GBDT model achieved an AUC of 0.85 on the test set; the mean AUC from bootstrap internal validation was 0.964 (95% CI 0.939\u20130.982). The calibration curve demonstrated good agreement between the model\u2019s predicted probabilities and actual incidence rates, while the decision curve indicated a net benefit across a wide range of thresholds. The top three variables in the SHAP importance ranking were HII, GCS, and age. The dependency plot showed that a higher HII value, lower GCS score, more irregular hematoma shape, shorter time from onset to CT scan, and larger hematoma volume were all associated with a higher risk of rebleeding.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this single-center retrospective study, a 10-variable GBDT model accurately predicted early rebleeding risk after acute intracerebral hemorrhage, showing stable Bootstrap performance and improved interpretability via SHAP, which can aid early detection of high-risk patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1855223","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:54:23Z","timestamp":1780462463000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on predicting risk factors for re-bleeding in the acute phase of intracerebral hemorrhage using machine learning algorithms"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiong","family":"Deng","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Shaoyang University","place":["Shaoyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JieYao","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Shaoyang University","place":["Shaoyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhiJun","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Shaoyang University","place":["Shaoyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Shaoyang University","place":["Shaoyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1016\/S1474-4422(12)70104-7","article-title":"Intracerebral haemorrhage: mechanisms of injury and therapeutic targets","volume":"11","author":"Keep","year":"2012","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/S1474-4422(09)70340-0","article-title":"Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis","volume":"9","author":"van Asch","year":"2010","journal-title":"Lancet Neurol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1161\/CIRCULATIONAHA.116.025250","article-title":"Prevalence, incidence, and mortality of stroke in China: results from a nationwide population-based survey of 480 687 adults","volume":"135","author":"Wang","year":"2017","journal-title":"Circulation"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1212\/WNL.0b013e3182143317","article-title":"Defining hematoma expansion in intracerebral hemorrhage: relationship with patient outcomes","volume":"76","author":"Dowlatshahi","year":"2011","journal-title":"Neurology"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1161\/01.str.28.1.1","article-title":"Early hemorrhage growth in patients with intracerebral hemorrhage","volume":"28","author":"Brott","year":"1997","journal-title":"Stroke"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1136\/jnnp-2019-322468","article-title":"Absolute risk and predictors of thromboembolism after tranexamic acid in intracerebral haemorrhage: a secondary analysis of the TICH-2 trial","volume":"91","author":"Al-Shahi Salman","year":"2020","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1161\/STROKEAHA.120.032966","article-title":"Haemostatic therapy for spontaneous intracerebral hemorrhage: an updated systematic review and meta-analysis","volume":"52","author":"Steiner","year":"2021","journal-title":"Stroke"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2127","DOI":"10.1056\/NEJMoa0707564","article-title":"Efficacy and safety of recombinant activated factor VII for acute intracerebral hemorrhage","volume":"358","author":"Mayer","year":"2008","journal-title":"N Engl J Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/S0140-6736(18)30103-X","article-title":"Tranexamic acid for acute intracerebral haemorrhage (TICH-2): a randomised, placebo-controlled trial","volume":"391","author":"Sprigg","year":"2018","journal-title":"Lancet"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e1063","DOI":"10.1161\/STROKEAHA.117.020138","article-title":"Predicting intracerebral hemorrhage expansion with noncontrast computed tomography: the BAT score","volume":"100","author":"Morotti","year":"2023","journal-title":"Neurology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s10143-025-03933-z","article-title":"A novel dose-dependent predictor for hematoma expansion on non-contrast CT: the number of black hole signs in spontaneous intracerebral hemorrhage","volume":"49","author":"Huang","year":"2025","journal-title":"Neurosurg Rev"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit Med"},{"key":"ref13","first-page":"785","author":"Chen","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"660275","DOI":"10.3389\/fgene.2021.660275","article-title":"Predicting metabolite\u2013disease associations based on LightGBM model","volume":"12","author":"Zhang","year":"2021","journal-title":"Front Genet"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"114234","DOI":"10.1016\/j.dss.2024.114234","article-title":"Explaining the model and feature dependencies by decomposition of the Shapley value","volume":"182","author":"Michiels","year":"2024","journal-title":"Decis Support Syst"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref17","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1111\/ene.15789","article-title":"Guidelines for the management of spontaneous intracerebral hemorrhage","volume":"32","year":"2025","journal-title":"Eur J Neurol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1161\/01.str.27.8.1304","article-title":"The ABCs of measuring intracerebral hemorrhage volumes","volume":"27","author":"Kothari","year":"1996","journal-title":"Stroke"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1186\/s12883-022-02983-w","article-title":"3D slicer-based calculation of hematoma irregularity index for predicting hematoma expansion in intracerebral hemorrhage","volume":"22","author":"Cao","year":"2022","journal-title":"BMC Neurol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J Royal Stat Soc Series B"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"N55","DOI":"10.1088\/0031-9155\/44\/4\/021","article-title":"Bootstrap resampling: a powerful method of assessing confidence intervals for doses from experimental data","volume":"44","author":"Iwi","year":"1999","journal-title":"Phys Med Biol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1177\/0962280214558972","article-title":"Events per variable (EPV) and the relative performance of different strategies for estimating the performance of prediction models","volume":"26","author":"Austin","year":"2019","journal-title":"J Clin Epidemiol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Mak"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1161\/STROKEAHA.115.010566","article-title":"Intracerebral hematoma morphologic appearance on noncontrast computed tomography predicts significant hemorrhage growth","volume":"46","author":"Blacquiere","year":"2015","journal-title":"Stroke"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"999223","DOI":"10.3389\/fneur.2022.999223","article-title":"Quantitative hematoma heterogeneity associated with hematoma growth in patients with early intracerebral hemorrhage","volume":"13","author":"Zhao","year":"2022","journal-title":"Front Neurol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1161\/01.str.29.6.1160","article-title":"Multivariate analysis of predictors of hematoma enlargement in spontaneous intracerebral hemorrhage","volume":"29","author":"Fujii","year":"1998","journal-title":"Stroke"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1161\/01.str.27.10.1783","article-title":"Enlargement of spontaneous intracerebral hemorrhage. Incidence and time course","volume":"27","author":"Kazui","year":"1996","journal-title":"Stroke"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1212\/01.wnl.0000256290.15120.37","article-title":"Hematoma growth is a determinant of mortality and poor outcome after intracerebral hemorrhage","volume":"66","author":"Davis","year":"2006","journal-title":"Neurology"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"815","DOI":"10.32604\/cmes.2020.012345","article-title":"A novel heuristic algorithm for the modeling and risk assessment of the COVID-19 pandemic phenomenon","volume":"125","author":"Asteris","year":"2020","journal-title":"Comput Model Eng Sci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1111\/jcmm.17098","article-title":"Genetic prediction of ICU hospitalization and mortality in COVID-19 patients using artificial neural networks","volume":"26","author":"Asteris","year":"2022","journal-title":"J Cell Mol Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.ejim.2024.02.037","article-title":"Prognosis of COVID-19 severity using DERGA, a novel machine learning algorithm","volume":"125","author":"Asteris","year":"2024","journal-title":"Eur J Intern Med"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e18105","DOI":"10.1111\/jcmm.18105","article-title":"Genetic justification of COVID-19 patient outcomes using DERGA, a novel data ensemble refinement greedy algorithm","volume":"28","author":"Asteris","year":"2024","journal-title":"J Cell Mol Med"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1001\/jamaneurol.2013.5433","article-title":"Predicting hematoma expansion after primary intracerebral hemorrhage","volume":"71","author":"Brouwers","year":"2014","journal-title":"JAMA Neurol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1161\/STROKEAHA.114.006910","article-title":"Clinical prediction algorithm (BRAIN) to determine risk of hematoma growth in acute intracerebral hemorrhage","volume":"46","author":"Wang","year":"2023","journal-title":"J Neurol Neurosurg Psychiatry"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1855223\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:54:27Z","timestamp":1780462467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1855223\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":37,"alternative-id":["10.3389\/fmed.2026.1855223"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1855223","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"article-number":"1855223"}}