{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T07:06:36Z","timestamp":1776755196244,"version":"3.51.2"},"reference-count":30,"publisher":"BMJ","issue":"5","funder":[{"DOI":"10.13039\/100011950","name":"ITEA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100011950","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J NeuroIntervent Surg"],"accepted":{"date-parts":[[2018,10,11]]},"published-print":{"date-parts":[[2019,5]]},"abstract":"<jats:sec><jats:title>Background and purpose<\/jats:title><jats:p>Delayed cerebral ischemia (DCI) is a severe complication in patients with aneurysmal subarachnoid hemorrhage. Several associated predictors have been previously identified. However, their predictive value is generally low. We hypothesize that Machine Learning (ML) algorithms for the prediction of DCI using a combination of clinical and image data lead to higher predictive accuracy than previously applied logistic regressions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>Clinical and baseline CT image data from 317 patients with aneurysmal subarachnoid hemorrhage were included. Three types of analysis were performed to predict DCI. First, the prognostic value of known predictors was assessed with logistic regression models. Second, ML models were created using all clinical variables. Third, image features were extracted from the CT images using an auto-encoder and combined with clinical data to create ML models. Accuracy was evaluated based on the area under the curve (AUC), sensitivity and specificity with 95%\u2009CI.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The best AUC of the logistic regression models for known predictors was 0.63 (95% CI 0.62 to 0.63). For the ML algorithms with clinical data there was a small but statistically significant improvement in the AUC to 0.68 (95% CI 0.65 to 0.69). Notably, aneurysm width and height were included in many of the ML models. The AUC was highest for ML models that also included image features: 0.74 (95% CI 0.72 to 0.75).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>ML algorithms significantly improve the prediction of DCI in patients with aneurysmal subarachnoid hemorrhage, particularly when image features are also included. Our experiments suggest that aneurysm characteristics are also associated with the development of DCI.<\/jats:p><\/jats:sec>","DOI":"10.1136\/neurintsurg-2018-014258","type":"journal-article","created":{"date-parts":[[2018,11,10]],"date-time":"2018-11-10T17:25:33Z","timestamp":1541870733000},"page":"497-502","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":79,"title":["Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage"],"prefix":"10.1136","volume":"11","author":[{"given":"Lucas Alexandre","family":"Ramos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wessel E","family":"van der Steen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renan","family":"Sales Barros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles B L M","family":"Majoie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rene","family":"van den Berg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dagmar","family":"Verbaan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W Peter","family":"Vandertop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I Jsbrand Andreas Jan","family":"Zijlstra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A H","family":"Zwinderman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustav J","family":"Strijkers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia Delgado","family":"Olabarriaga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henk A","family":"Marquering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2018,11,10]]},"reference":[{"key":"2024052304361522000_11.5.497.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(07)60153-6"},{"key":"2024052304361522000_11.5.497.2","doi-asserted-by":"publisher","DOI":"10.1038\/nrneurol.2013.246"},{"key":"2024052304361522000_11.5.497.3","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A4771"},{"key":"2024052304361522000_11.5.497.4","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.110.600775"},{"key":"2024052304361522000_11.5.497.5","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.115.008728"},{"key":"2024052304361522000_11.5.497.6","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.113.001125"},{"key":"2024052304361522000_11.5.497.7","first-page":"1","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","volume":"5","author":"Kohavi","year":"1995","journal-title":"Appear Int Jt Conf Articial Intell"},{"key":"2024052304361522000_11.5.497.8","doi-asserted-by":"publisher","DOI":"10.5853\/jos.2017.02054"},{"key":"2024052304361522000_11.5.497.9","doi-asserted-by":"publisher","DOI":"10.1038\/ajg.2013.332"},{"key":"2024052304361522000_11.5.497.10","doi-asserted-by":"crossref","first-page":"e88225","DOI":"10.1371\/journal.pone.0088225","article-title":"Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy","volume":"9","author":"Asadi","year":"2014","journal-title":"PLoS One"},{"key":"2024052304361522000_11.5.497.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.01.008"},{"key":"2024052304361522000_11.5.497.12","unstructured":"As B , Nutt DJ , Mcgonigle J . Identifying patients at risk for aortic stenosis through learning from multimodal data.\u00a0 MICCAI 2016. 2016."},{"key":"2024052304361522000_11.5.497.13","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.110.589275"},{"key":"2024052304361522000_11.5.497.14","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"2024052304361522000_11.5.497.15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2024052304361522000_11.5.497.16","first-page":"482","article-title":"Neural networks for pattern recognition","volume":"92","author":"Bishop","year":"1995","journal-title":"J Am Stat Assoc"},{"key":"2024052304361522000_11.5.497.17","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1109\/TCYB.2016.2536638","article-title":"Stacked convolutional denoising auto-encoders for feature representation","volume":"47","author":"Du","year":"2017","journal-title":"IEEE Trans Cybern"},{"key":"2024052304361522000_11.5.497.18","doi-asserted-by":"crossref","first-page":"171","DOI":"10.2528\/PIER13121310","article-title":"Classification of Alzheimer Disease based on structural magnetic resonance imaging by kernel support vector machine decision tree","volume":"144","author":"Zhang","year":"2014","journal-title":"Progress In Electromagnetics Research"},{"key":"2024052304361522000_11.5.497.19","doi-asserted-by":"crossref","unstructured":"van Stein B , Wojtek K . An incremental algorithm for repairing training sets with missing values. Int Conf Inf Process Manag Uncertain Knowledge-Based Syst 2016:175\u201386.","DOI":"10.1007\/978-3-319-40581-0_15"},{"key":"2024052304361522000_11.5.497.20","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2. 1201.0490"},{"key":"2024052304361522000_11.5.497.21","unstructured":"Bengio Y , Courville A , Vincent P . Representation learning: a review and new perspectives. 2012:1\u201330."},{"key":"2024052304361522000_11.5.497.22","unstructured":"Duda RO , Hart PE . Pattern classification. Pattern Recognit 2000:680."},{"key":"2024052304361522000_11.5.497.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2016.11.003"},{"key":"2024052304361522000_11.5.497.24","first-page":"52","article-title":"Stacked convolutional auto-encoders for hierarchical feature extraction","volume":"6791","author":"Masci","year":"2011","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)"},{"key":"2024052304361522000_11.5.497.25","unstructured":"Yu D , Eversole A , Seltzer M , et al . An introduction to computational networks and the computational network toolkit. Microsoft Tech Rep. 2015:112."},{"key":"2024052304361522000_11.5.497.26","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"Why should I trust you? Explaining the predictions of any classifier.","volume":"44","author":"Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"2024052304361522000_11.5.497.27","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2009.2020434"},{"key":"2024052304361522000_11.5.497.28","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwk052"},{"key":"2024052304361522000_11.5.497.29","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2011.02.006"},{"key":"2024052304361522000_11.5.497.30","doi-asserted-by":"crossref","unstructured":"Aubry M , Russell BC . Understanding deep features with computer-generated imagery. Proc IEEE Int Conf Comput Vis 2015:2875\u201383.","DOI":"10.1109\/ICCV.2015.329"}],"container-title":["Journal of NeuroInterventional Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/neurintsurg-2018-014258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T12:11:45Z","timestamp":1716466305000},"score":1,"resource":{"primary":{"URL":"https:\/\/jnis.bmj.com\/lookup\/doi\/10.1136\/neurintsurg-2018-014258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,10]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2019,4,15]]},"published-print":{"date-parts":[[2019,5]]}},"alternative-id":["10.1136\/neurintsurg-2018-014258"],"URL":"https:\/\/doi.org\/10.1136\/neurintsurg-2018-014258","relation":{},"ISSN":["1759-8478","1759-8486"],"issn-type":[{"value":"1759-8478","type":"print"},{"value":"1759-8486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,10]]}}}