{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:08:55Z","timestamp":1791346135781,"version":"4.3.1"},"reference-count":36,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"47","license":[{"start":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T00:00:00Z","timestamp":1763683200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,21]]},"abstract":"<jats:p>Effective outcome prediction is crucial in the management of spontaneous intracerebral hemorrhage (SICH). This study developed machine learning models to predict the 180-day Glasgow Outcome Scale (GOS) score using clinical parameters and identify key prognostic factors. All patients with SICH were randomized into training and internal validation cohortsin a 7:3 ratio. After the most relevant variables were selected by the SVM-RFE and LASSO algorithms, the predictive efficiency of the gradient boosting decision tree (GBDT), XGBoost, random forest (RF), and lightgbm models was evaluated through an exhaustive suite of performance indicators. The Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) methods were engaged to explain the top-performingmodel. The model was developed for 215 patients. The GBDT model showed stable performance in predictive power in both the internal and external validation cohorts, with the following metrics assessed in the internal test set: AUROC (0.865\u2005\u00b1\u20050.069); AUPRC (0.834\u2005\u00b1\u20050.090); accuracy (0.822\u2005\u00b1\u20050.065), F1 (0.716\u2005\u00b1\u20050.114); precision (0.787\u2005\u00b1\u20050.147); recall (0.676\u2005\u00b1\u20050.138); sensitivity (0.902\u2005\u00b1\u20050.070) specificity, (0.787\u2005\u00b1\u20050.147). The GBDT model was assessed in the outer test set with the following metrics: AUROC: 0.785 (0.752, 0.832), AUPRC: 0.693 (0.649, 0.762), accuracy: 0.770 (0.739, 0.807), F1: 0.769 (0.738, 0.806), precision: 0.769 (0.738, 0.806), recall: 0.770 (0.739, 0.807), sensitivity: 0.826 (0.793, 0.863), Specificity: 0.710 (0.662, 0.761). We found that the blood platelet count, serum calcium level, and hemorrhage in the left occipital lobe, right temporal lobe, and right parietal lobe were the 5 most important features for GOS prediction in the GBDT and RF models. The outcomes of SHAP and LIME were consistent with those of previous studies. The GBDT model exhibited the best prediction performance. Moreover, it has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision making.<\/jats:p>","DOI":"10.1097\/md.0000000000045402","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T15:01:28Z","timestamp":1764169288000},"page":"e45402","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":2,"title":["Prediction of 180-day post-admission\u2019s GOS in patients with spontaneous intracerebral hemorrhage based on explainable machine learning technology"],"prefix":"10.1097","volume":"104","author":[{"given":"Cuijie","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yafang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Nursing, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengpeng","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Jiangshan People\u2019s Hospital, Jiangshan, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiafei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Nursing, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guofeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4074-2631","authenticated-orcid":false,"given":"Xinjiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Quzhou Affiliated Hospital of Wenzhou Medical University (Quzhou People\u2019s Hospital), Quzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260514","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1007\/s10143-019-01115-2","article-title":"Surgical management of spontaneous intracerebral hemorrhage: insights from randomized controlled trials.","volume":"43","author":"Rennert","year":"2019","journal-title":"Neurosurg Rev"},{"key":"R2-20260514","doi-asserted-by":"crossref","first-page":"214","DOI":"10.7461\/jcen.2013.15.3.214","article-title":"The outcomes of spontaneous intracerebral hemorrhage in young adults: a clinical study.","volume":"15","author":"Go","year":"2013","journal-title":"J Cerebrovascular Endovascular Neurosurg"},{"key":"R3-20260514","doi-asserted-by":"crossref","first-page":"e470","DOI":"10.1016\/j.wneu.2020.02.004","article-title":"Nomogram model for predicting hematoma expansion in spontaneous intracerebral hemorrhage: multicenter retrospective study.","volume":"137","author":"Yang","year":"2020","journal-title":"World Neurosurg"},{"key":"R4-20260514","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1016\/j.jstrokecerebrovasdis.2017.02.035","article-title":"Frequency and predictive factors for chronic expanding intracerebral hematoma in spontaneous intracerebral hemorrhage.","volume":"26","author":"Shimizu","year":"2017","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"R5-20260514","first-page":"e25","article-title":"Glasgow coma scale versus physiological scoring systems in predicting the outcome of ICU admitted trauma patients; a diagnostic accuracy study.","volume":"10","author":"Khari","year":"2022","journal-title":"Arch Acad Emerg Med"},{"key":"R6-20260514","doi-asserted-by":"crossref","first-page":"915370","DOI":"10.3389\/fneur.2022.915370","article-title":"Combining the modified Graeb score and intracerebral hemorrhage score to predict poor outcomes in patients with spontaneous intracerebral hemorrhage undergoing surgical treatment.","volume":"13","author":"Wang","year":"2022","journal-title":"Front Neurol"},{"key":"R7-20260514","doi-asserted-by":"crossref","first-page":"256","DOI":"10.5005\/jp-journals-10071-24651","article-title":"Comparison of glasgow coma scale full outline of unresponsiveness and glasgow coma scale: pupils score for predicting outcomes in patients with traumatic brain injury.","volume":"28","author":"Chawnchhim","year":"2024","journal-title":"Indian J Crit Care Med"},{"key":"R8-20260514","doi-asserted-by":"crossref","first-page":"350","DOI":"10.4037\/ajcc2021163","article-title":"Admission glasgow coma scale score as a predictor of outcomes in patients without traumatic brain injury.","volume":"30","author":"Li","year":"2021","journal-title":"Am J Crit Care"},{"key":"R9-20260514","doi-asserted-by":"crossref","first-page":"e141","DOI":"10.1016\/j.wneu.2024.06.001","article-title":"A novel machine learning model for predicting stroke-associated pneumonia after spontaneous intracerebral hemorrhage.","volume":"189","author":"Guo","year":"2024","journal-title":"World Neurosurg"},{"key":"R10-20260514","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine.","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"R11-20260514","doi-asserted-by":"crossref","first-page":"112","DOI":"10.3390\/jpm12010112","article-title":"Machine learning-based approaches for prediction of patients\u2019 functional outcomes and mortality after spontaneous intracerebral hemorrhage.","volume":"12","author":"Guo","year":"2022","journal-title":"J Pers Med"},{"key":"R12-20260514","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1186\/s12967-024-04896-3","article-title":"Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcomes of patients with spontaneous intracerebral hemorrhage.","volume":"22","author":"Geng","year":"2024","journal-title":"J Transl Med"},{"key":"R13-20260514","doi-asserted-by":"crossref","first-page":"102552","DOI":"10.1016\/j.artmed.2023.102552","article-title":"Identifying stroke-related quantified evidence from electronic health records in real-world studies.","volume":"140","author":"Yang","year":"2023","journal-title":"Artif Intell Med"},{"key":"R14-20260514","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.2147\/NDT.S368123","article-title":"Serum sulfonylurea receptor-1 levels after acute supratentorial intracerebral hemorrhage: implications for prognosis.","volume":"18","author":"Zhuge","year":"2022","journal-title":"Neuropsychiatr Dis Treat"},{"key":"R15-20260514","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.ejrad.2019.04.001","article-title":"Radiomics for predicting hematoma expansion in patients with hypertensive intraparenchymal hematoma.","volume":"115","author":"Ma","year":"2019","journal-title":"Eur J Radiol"},{"key":"R16-20260514","doi-asserted-by":"crossref","first-page":"105820","DOI":"10.1016\/j.clineuro.2020.105820","article-title":"Analysis of different hematoma expansion shapes caused by different risk factors in patients with hypertensive intracerebral hemorrhage.","volume":"194","author":"Wei","year":"2020","journal-title":"Clin Neurol Neurosurg"},{"key":"R17-20260514","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s12880-022-00772-y","article-title":"External validation study on the value of deep learning algorithms for the prediction of hematoma expansion from non-contrast CT scans.","volume":"22","author":"Guo","year":"2022","journal-title":"BMC Med Imaging"},{"key":"R18-20260514","doi-asserted-by":"crossref","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":"R19-20260514","doi-asserted-by":"crossref","first-page":"3509","DOI":"10.2147\/CCID.S443165","article-title":"Identification of dopachrome tautomerase (DCT) and Kinesin Family Member 1A (KIF1A) as related biomarkers and immune infiltration characteristics of vitiligo based on lasso-SVM algorithms.","volume":"16","author":"Zhao","year":"2023","journal-title":"Clin Cosmet Investig Dermatol"},{"key":"R20-20260514","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1186\/s12967-023-04487-8","article-title":"Advancing polytrauma care: Developing and validating machine learning models for early mortality prediction.","volume":"21","author":"He","year":"2023","journal-title":"J Transl Med"},{"key":"R21-20260514","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1186\/s12879-021-06503-y","article-title":"Time series analysis of hemorrhagic fever with renal syndrome in mainland China using the XGBoost forecasting model.","volume":"21","author":"Lv","year":"2021","journal-title":"BMC Infect Dis"},{"key":"R22-20260514","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1186\/s12911-023-02407-w","article-title":"Comparison of the LASSO and random forest models for predicting the risk of premature coronary artery disease.","volume":"23","author":"Wang","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"R23-20260514","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1245\/s10434-023-14619-5","article-title":"Machine learning radiomics liver function model for prognostic prediction after radical resection of advanced gastric cancer: a retrospective study.","volume":"31","author":"Shao","year":"2024","journal-title":"Ann Surg Oncol"},{"key":"R24-20260514","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1021\/acs.analchem.6b04498","article-title":"Personal information from latent fingerprints using desorption electrospray ionization mass spectrometry and machine learning.","volume":"89","author":"Zhou","year":"2017","journal-title":"Anal Chem"},{"key":"R25-20260514","first-page":"6505","article-title":"Tractability of SHAP explanations.","volume":"35","author":"Van den Broeck","year":"2021","journal-title":"Proc Conf AAAI Artif Intell"},{"key":"R26-20260514","doi-asserted-by":"crossref","first-page":"525","DOI":"10.3390\/make3030027","article-title":"Deterministic local interpretable model agnostic explanations for stable explainability.","volume":"3","author":"Zafar","year":"2021","journal-title":"Mach Learn Knowl Extr"},{"key":"R27-20260514","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1111\/cns.13219","article-title":"The risk factors and prognosis of delayed perihematomal edema in patients with spontaneous intracerebral hemorrhage.","volume":"25","author":"Peng","year":"2019","journal-title":"CNS Neurosci Ther"},{"key":"R28-20260514","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1007\/s00415-014-7297-8","article-title":"Frequency and predictors of spontaneous hemorrhagic transformation in ischemic stroke and their association with prognosis.","volume":"261","author":"Tan","year":"2014","journal-title":"J Neurol"},{"key":"R29-20260514","doi-asserted-by":"crossref","first-page":"3557","DOI":"10.1007\/s10143-021-01533-1","article-title":"Nomogram to predict the risk of early postoperative ischemic events in patients with spontaneous intracranial hematoma.","volume":"44","author":"Yang","year":"2021","journal-title":"Neurosurg Rev"},{"key":"R30-20260514","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/s00068-013-0269-3","article-title":"The Glasgow Coma Scale score at intensive care unit discharge predicts the 1-year outcome of patients with severe traumatic brain injury.","volume":"39","author":"Leitgeb","year":"2013","journal-title":"Eur J Trauma Emerg Surg"},{"key":"R31-20260514","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1046\/j.1468-1331.2003.00630.x","article-title":"Predicting spontaneous early neurological recovery after acute ischemic stroke.","volume":"10","author":"Arboix","year":"2003","journal-title":"Eur J Neurol"},{"key":"R32-20260514","doi-asserted-by":"crossref","first-page":"223","DOI":"10.3390\/biomedicines11010223","article-title":"Acute spontaneous lobar cerebral hemorrhages present a different clinical profile and more severe early prognosis than deep subcortical intracerebral hemorrhage-A hospital-based stroke registry study.","volume":"11","author":"Mendiola","year":"2023","journal-title":"Biomedicines"},{"key":"R33-20260514","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1007\/s12028-018-0564-2","article-title":"The role of serum calcium level in intracerebral hemorrhage hematoma expansion: is there any?","volume":"31","author":"Jafari","year":"2019","journal-title":"Neurocrit Care"},{"key":"R34-20260514","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1080\/02688697.2019.1571162","article-title":"Serum calcium levels at admission were associated with outcomes in patients with hypertensive intracerebral hemorrhage.","volume":"33","author":"Mao","year":"2019","journal-title":"Br J Neurosurg"},{"key":"R35-20260514","doi-asserted-by":"crossref","first-page":"751510","DOI":"10.3389\/fneur.2021.751510","article-title":"An elevated red cell distribution width-to-platelet ratio is associated with poor prognosis in patients with spontaneous, deep-seated intracerebral hemorrhage.","volume":"12","author":"Lehmann","year":"2021","journal-title":"Front Neurol"},{"key":"R36-20260514","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1097\/CCM.0000000000001628","article-title":"Prognostic significance of hyponatremia in acute intracerebral hemorrhage: pooled analysis of the intensive blood pressure reduction in acute cerebral hemorrhage trial studies.","volume":"44","author":"Carcel","year":"2016","journal-title":"Crit Care Med"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000045402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:12Z","timestamp":1778756772000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000045402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":36,"journal-issue":{"issue":"47","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000045402","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,21]]},"assertion":[{"value":"2025-05-14","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-28","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}