{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:57:28Z","timestamp":1767855448261,"version":"3.49.0"},"reference-count":35,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["81870904"],"award-info":[{"award-number":["81870904"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>To develop an artificial intelligence system that can accurately identify acute non-traumatic intracranial hemorrhage (ICH) etiology (aneurysms, hypertensive hemorrhage, arteriovenous malformation (AVM), Moyamoya disease (MMD), cavernous malformation (CM), or other causes) based on non-contrast computed tomography (NCCT) scans and investigate whether clinicians can benefit from it in a diagnostic setting.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>The deep learning model was developed with 1,868 eligible NCCT scans with non-traumatic ICH collected between January 2011 and April 2018. We tested the model on two independent datasets (TT200 and SD 98) collected after April 2018. The model\u2019s diagnostic performance was compared with clinicians\u2019 performance. We further designed a simulated study to compare the clinicians\u2019 performance with and without the deep learning system complements.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>The proposed deep learning system achieved area under the receiver operating curve of 0.986 (95% CI [0.967\u20131.000]) on aneurysms, 0.952 (0.917\u20130.987) on hypertensive hemorrhage, 0.950 (0.860\u20131.000) on arteriovenous malformation (AVM), 0.749 (0.586\u20130.912) on Moyamoya disease (MMD), 0.837 (0.704\u20130.969) on cavernous malformation (CM), and 0.839 (0.722\u20130.959) on other causes in TT200 dataset. Given a 90% specificity level, the sensitivities of our model were 97.1% and 90.9% for aneurysm and AVM diagnosis, respectively. On the test dataset SD98, the model achieved AUCs on aneurysms and hypertensive hemorrhage of 0.945 (95% CI [0.882\u20131.000]) and 0.883 (95% CI [0.818\u20130.948]), respectively. The clinicians achieve significant improvements in the sensitivity, specificity, and accuracy of diagnoses of certain hemorrhage etiologies with proposed system complements.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Conclusions<\/jats:title>\n<jats:p>The proposed deep learning tool can be an accuracy tool for early identification of hemorrhage etiologies based on NCCT scans. It may also provide more information for clinicians for triage and further imaging examination selection.<\/jats:p>\n<\/jats:sec>","DOI":"10.7717\/peerj.18850","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T08:04:47Z","timestamp":1740557087000},"page":"e18850","source":"Crossref","is-referenced-by-count":3,"title":["Deep-learning tool for early identification of non-traumatic intracranial hemorrhage etiology and application in clinical diagnostics based on computed tomography (CT) scans"],"prefix":"10.7717","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6751-9868","authenticated-orcid":true,"given":"Meng","family":"Zhao","sequence":"first","affiliation":[{"name":"Neurosurgery Department, Capital Medical University, Beijing, China"},{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent You Tu Lab, Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanli","family":"Zhao","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0669-9321","authenticated-orcid":true,"given":"Rong","family":"Wang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Cao","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonggang","family":"Ma","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxi","family":"Li","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaochen","family":"Yu","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Affiliated Hospital of Shandong Jining Medical College, Jining, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tencent You Tu Lab, Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizong","family":"Zhao","sequence":"additional","affiliation":[{"name":"China National Clinical Research Center for Neurological Diseases, Beijing, China"},{"name":"Beijing Tiantan Hospital, Capital Medical University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"key":"10.7717\/peerj.18850\/ref-1","volume-title":"Computer vision","author":"Ballard","year":"1982"},{"issue":"10","key":"10.7717\/peerj.18850\/ref-2","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1161\/01.STR.30.10.2025","article-title":"Extravasation of radiographic contrast is an independent predictor of death in primary intracerebral hemorrhage","volume":"30","author":"Becker","year":"1999","journal-title":"Stroke"},{"issue":"4","key":"10.7717\/peerj.18850\/ref-3","doi-asserted-by":"publisher","first-page":"761","DOI":"10.3171\/2012.7.JNS12281","article-title":"Computed tomography angiography: improving diagnostic yield and cost effectiveness in the initial evaluation of spontaneous nonsubarachnoid intracerebral hemorrhage","volume":"117","author":"Bekelis","year":"2012","journal-title":"Journal of Neurosurgery"},{"issue":"36","key":"10.7717\/peerj.18850\/ref-4","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"Chechik","year":"2010","journal-title":"Journal of Machine Learning Research"},{"issue":"10162","key":"10.7717\/peerj.18850\/ref-5","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1016\/S0140-6736(18)31645-3","article-title":"Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study","volume":"392","author":"Chilamkurthy","year":"2018","journal-title":"The Lancet"},{"issue":"4","key":"10.7717\/peerj.18850\/ref-6","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","article-title":"The use of confidence or fiducial limits illustrated in the case of the binomial","volume":"26","author":"Clopper","year":"1934","journal-title":"Biometrika"},{"issue":"1","key":"10.7717\/peerj.18850\/ref-7","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educational and Psychological Measurement"},{"issue":"10154","key":"10.7717\/peerj.18850\/ref-8","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1016\/S0140-6736(18)31878-6","article-title":"Intracerebral haemorrhage: current approaches to acute management","volume":"392","author":"Cordonnier","year":"2018","journal-title":"The Lancet"},{"issue":"4","key":"10.7717\/peerj.18850\/ref-9","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1161\/STROKEAHA.109.572495","article-title":"Radiological investigation of spontaneous intracerebral hemorrhage: systematic review and trinational survey","volume":"41","author":"Cordonnier","year":"2010","journal-title":"Stroke"},{"issue":"9","key":"10.7717\/peerj.18850\/ref-10","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nature Medicine"},{"issue":"1","key":"10.7717\/peerj.18850\/ref-11","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1161\/STROKEAHA.115.009171","article-title":"Comparing vessel imaging: noncontrast computed tomography\/computed tomographic angiography should be the new minimum standard in acute disabling stroke","volume":"47","author":"Demchuk","year":"2016","journal-title":"Stroke"},{"issue":"8","key":"10.7717\/peerj.18850\/ref-12","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1161\/STR.0000000000000134","article-title":"Management of brain arteriovenous malformations: a scientific statement for healthcare professionals from the American Heart Association\/American Stroke Association","volume":"48","author":"Derdeyn","year":"2017","journal-title":"Stroke"},{"key":"10.7717\/peerj.18850\/ref-13","first-page":"6202","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"issue":"3","key":"10.7717\/peerj.18850\/ref-14","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1177\/001316447303300309","article-title":"The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability","volume":"33","author":"Fleiss","year":"1973","journal-title":"Educational and Psychological Measurement"},{"key":"10.7717\/peerj.18850\/ref-15","volume-title":"Statistical methods for rates and proportions","author":"Fleiss","year":"2013"},{"issue":"22","key":"10.7717\/peerj.18850\/ref-16","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1001\/jama.2017.14580","article-title":"Deep learning algorithms for detection of lymph node metastases from breast cancer: helping artificial intelligence be seen","volume":"318","author":"Golden","year":"2017","journal-title":"JAMA"},{"issue":"22","key":"10.7717\/peerj.18850\/ref-17","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"10.7717\/peerj.18850\/ref-18","first-page":"1556","article-title":"Comparison of commonly used image interpolation methods","author":"Han","year":"2013"},{"issue":"1","key":"10.7717\/peerj.18850\/ref-19","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"10.7717\/peerj.18850\/ref-20","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"7","key":"10.7717\/peerj.18850\/ref-21","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.1161\/STR.0000000000000069","article-title":"Guidelines for the management of spontaneous intracerebral hemorrhage: a guideline for healthcare professionals from the American Heart Association\/American Stroke Association","volume":"46","author":"Hemphill","year":"2015","journal-title":"Stroke"},{"issue":"7","key":"10.7717\/peerj.18850\/ref-22","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1136\/jnnp-2017-317262","article-title":"Predicting the presence of macrovascular causes in non-traumatic intracerebral haemorrhage: the DIAGRAM prediction score","volume":"89","author":"Hilkens","year":"2018","journal-title":"Journal of Neurology, Neurosurgery & Psychiatry"},{"key":"10.7717\/peerj.18850\/ref-23","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.7717\/peerj.18850\/ref-24","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"issue":"4","key":"10.7717\/peerj.18850\/ref-25","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1212\/01.wnl.0000172915.71933.00","article-title":"The incidence of deep and lobar intracerebral hemorrhage in whites, blacks, and Hispanics","volume":"65","author":"Labovitz","year":"2005","journal-title":"Neurology"},{"issue":"3","key":"10.7717\/peerj.18850\/ref-26","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/s41551-018-0324-9","article-title":"An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets","volume":"3","author":"Lee","year":"2019","journal-title":"Nature Biomedical Engineering"},{"issue":"10","key":"10.7717\/peerj.18850\/ref-27","doi-asserted-by":"publisher","first-page":"2592","DOI":"10.1161\/STROKEAHA.112.661603","article-title":"SMASH-U: a proposal for etiologic classification of intracerebral hemorrhage","volume":"43","author":"Meretoja","year":"2012","journal-title":"Stroke"},{"issue":"7","key":"10.7717\/peerj.18850\/ref-28","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1161\/STROKEAHA.108.546127","article-title":"CT angiography for intracerebral hemorrhage does not increase risk of acute nephropathy","volume":"40","author":"Oleinik","year":"2009","journal-title":"Stroke"},{"issue":"9675","key":"10.7717\/peerj.18850\/ref-29","doi-asserted-by":"publisher","first-page":"1632","DOI":"10.1016\/S0140-6736(09)60371-8","article-title":"Intracerebral haemorrhage","volume":"373","author":"Qureshi","year":"2009","journal-title":"The Lancet"},{"issue":"12","key":"10.7717\/peerj.18850\/ref-30","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1055\/s-0043-115872","article-title":"Diagnostic accuracy of dual-layer spectral CT using electron density images to detect post-traumatic prevertebral hematoma of the cervical spine","volume":"193","author":"Sedaghat","year":"2021","journal-title":"R\u00f6Fo-Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren"},{"key":"10.7717\/peerj.18850\/ref-31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12028-017-0452-1","article-title":"Approach to a patient in the neurology emergency","volume":"I","author":"Singh","year":"2019","journal-title":"Emergencies in Neurology"},{"issue":"1","key":"10.7717\/peerj.18850\/ref-32","doi-asserted-by":"publisher","first-page":"45","DOI":"10.2176\/nmc.oa.2019-0152","article-title":"Benefits and risks of CT angiography immediately after emergency arrival for patients with intracerebral hematoma","volume":"60","author":"Sorimachi","year":"2020","journal-title":"Neurologia medico-chirurgica"},{"issue":"5","key":"10.7717\/peerj.18850\/ref-33","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1161\/STROKEAHA.120.028993","article-title":"Impact of treatment delay on outcome in the international subarachnoid aneurysm trial","volume":"51","author":"van Donkelaar","year":"2020","journal-title":"Stroke"},{"issue":"11","key":"10.7717\/peerj.18850\/ref-34","doi-asserted-by":"publisher","first-page":"6191","DOI":"10.1007\/s00330-019-06163-2","article-title":"Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network","volume":"29","author":"Ye","year":"2019","journal-title":"European Radiology"},{"key":"10.7717\/peerj.18850\/ref-35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.00953","article-title":"Deep-learning tool for early identifying non-traumatic intracranial hemorrhage etiology based on CT scan","author":"Zhao","year":"2023"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/18850.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/18850.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/18850.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/18850.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T08:04:57Z","timestamp":1740557097000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/18850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":35,"alternative-id":["10.7717\/peerj.18850"],"URL":"https:\/\/doi.org\/10.7717\/peerj.18850","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,26]]},"article-number":"e18850"}}