{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:09:48Z","timestamp":1790226588555,"version":"4.1.0"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"SNUH Lee Kun-hee Child Cancer & Rare Disease Project","award":["22C-003-0100"],"award-info":[{"award-number":["22C-003-0100"]}]},{"name":"Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Background<\/jats:title>\n Postoperative cerebrovascular events, including transient ischemic attacks, infarctions, and hemorrhages, remain a significant concern in pediatric patients with Moyamoya disease (MMD)undergoing surgical revascularization. This study aimed to develop an explainable deep learning-based classification model using intraoperative arterial blood pressure (ABP) waveform analysis for postoperative cerebrovascular events in pediatric patients undergoing surgery for MMD, with exploratory analysis of associated waveform-derived physiologic features.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This retrospective study included 181 pediatric patients (\u226418 years) who underwent revascularization surgery for MMD, with an independent temporal holdout cohort of 79 patients reserved for validation. ABP signals were preprocessed using detrending, pulse segmentation, and normalization, then converted into image representations for deep learning classification. Various convolutional neural network (CNN) models, including ResNet50, ResNet34, DenseNet121, VGG16, and VGG19, were evaluated against Vision Transformer (ViT) architectures. Multiple image transformation methods were tested, and Grad-CAM analysis and statistical comparisons of waveform-derived physiologic features were conducted between patients with and without postoperative cerebrovascular events.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The optimal model configuration achieved the best performance using raw pulse waveforms with three consecutive pulses per image. CNN-based models outperformed ViT-based models, with the highest internal classification performance observed using raw pulse waveforms (AUROC\u2009=\u20090.772, SD\u2009=\u20090.070).In the independent temporal validation cohort, the model achieved an AUROC of 0.738\u2009\u00b1\u20090.011 at the patient level. Grad-CAM visualization highlighted the diastolic runoff phase as a region of interest for classification. Four waveform-derived features related to arterial compliance were significantly associated with postoperative cerebrovascular events (p\u2009<\u20090.05).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n In this study, CNN-based deep learning models demonstrated the feasibility of predicting postoperative cerebrovascular events from intraoperative ABP waveforms, with diastolic runoff dynamics emerging as a potentially relevant physiologic pattern. These findings are exploratory and require prospective multi-center validation before clinical application.<\/jats:p>\n <\/jats:sec>","DOI":"10.1371\/journal.pone.0350637","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:34:14Z","timestamp":1780594454000},"page":"e0350637","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning-based arterial waveform analysis for predicting postoperative cerebrovascular events in pediatric patients with Moyamoya disease"],"prefix":"10.1371","volume":"21","author":[{"given":"Jung-Bin","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youmin","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoon Jung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6817-5793","authenticated-orcid":true,"given":"Seung-Bo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun-Hee","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joo Whan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Ki","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2661-7944","authenticated-orcid":true,"given":"Hee-Soo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1299","authenticated-orcid":true,"given":"Young-Gon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"issue":"1","key":"pone.0350637.ref001","doi-asserted-by":"crossref","first-page":"12","DOI":"10.5853\/jos.2015.01760","article-title":"The pathophysiology of moyamoya disease: an update","volume":"18","author":"OY Bang","year":"2016","journal-title":"J Stroke"},{"key":"pone.0350637.ref002","article-title":"Postoperative symptomatic cerebral infarction in pediatric moyamoya disease: risk factors and clinical outcome","volume":"136","author":"JW Choi","year":"2020","journal-title":"World Neurosurg"},{"issue":"6","key":"pone.0350637.ref003","doi-asserted-by":"crossref","first-page":"408","DOI":"10.3340\/jkns.2015.57.6.408","article-title":"Moyamoya syndrome: a window of moyamoya disease","volume":"57","author":"JH Phi","year":"2015","journal-title":"J Korean Neurosurg Soc"},{"issue":"6","key":"pone.0350637.ref004","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1161\/STROKEAHA.124.046999","article-title":"Moyamoya vasculopathy and moyamoya-related systemic vasculopathy: a review with histopathological and genetic viewpoints","volume":"55","author":"T Abumiya","year":"2024","journal-title":"Stroke"},{"issue":"1","key":"pone.0350637.ref005","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3171\/2010.4.PEDS09478","article-title":"Postoperative neurological deterioration in pediatric moyamoya disease: watershed shift and hyperperfusion","volume":"6","author":"T Hayashi","year":"2010","journal-title":"J Neurosurg Pediatr"},{"issue":"4","key":"pone.0350637.ref006","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1227\/01.NEU.0000114140.41509.14","article-title":"Moyamoya disease among young patients: its aggressive clinical course and the role of active surgical treatment","volume":"54","author":"S-K Kim","year":"2004","journal-title":"Neurosurgery"},{"issue":"2","key":"pone.0350637.ref007","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1007\/s10143-019-01118-z","article-title":"High variance of intraoperative blood pressure predicts early cerebral infarction after revascularization surgery in patients with Moyamoya disease","volume":"43","author":"J Li","year":"2020","journal-title":"Neurosurg Rev"},{"issue":"1","key":"pone.0350637.ref008","first-page":"101168","article-title":"Transient ischemic attack after indirect revascularization surgery for pediatric patients with moyamoya disease: A retrospective study of intraoperative blood pressure","volume":"42","author":"B Zhu","year":"2023","journal-title":"Anaesth Crit Care Pain Med"},{"issue":"4","key":"pone.0350637.ref009","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.bpa.2014.08.002","article-title":"Arterial waveform analysis","volume":"28","author":"SA Esper","year":"2014","journal-title":"Best Pract Res Clin Anaesthesiol"},{"key":"pone.0350637.ref010","doi-asserted-by":"crossref","DOI":"10.1016\/j.amjhyper.2004.10.009","article-title":"Clinical measurement of arterial stiffness obtained from noninvasive pressure waveforms","volume":"18","author":"WW Nichols","year":"2005","journal-title":"Am J Hypertens"},{"issue":"4","key":"pone.0350637.ref011","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1213\/ANE.0b013e31822773ec","article-title":"Arterial waveform analysis for the anesthesiologist: past, present, and future concepts","volume":"113","author":"RH Thiele","year":"2011","journal-title":"Anesth Analg"},{"issue":"1","key":"pone.0350637.ref012","doi-asserted-by":"crossref","first-page":"21881","DOI":"10.1038\/s41598-023-49062-9","article-title":"Machine learning model for predicting immediate postoperative desaturation using spirometry signal data","volume":"13","author":"Y Shin","year":"2023","journal-title":"Sci Rep"},{"issue":"3","key":"pone.0350637.ref013","article-title":"Machine learning-based prediction of intraoperative hypoxemia for pediatric patients","volume":"18","author":"J-B Park","year":"2023","journal-title":"PLoS One"},{"issue":"1","key":"pone.0350637.ref014","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s41597-022-01411-5","article-title":"VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients","volume":"9","author":"H-C Lee","year":"2022","journal-title":"Sci Data"},{"issue":"4","key":"pone.0350637.ref015","doi-asserted-by":"crossref","first-page":"045001","DOI":"10.1088\/1361-6579\/ad33a2","article-title":"pyPPG: a Python toolbox for comprehensive photoplethysmography signal analysis","volume":"45","author":"M\u00c1 Goda","year":"2024","journal-title":"Physiol Meas"},{"key":"pone.0350637.ref016","doi-asserted-by":"crossref","DOI":"10.1109\/CENTCON52345.2021.9687944","article-title":"A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for image classification","author":"S Mascarenhas","year":"2021","journal-title":"2021 International conference on disruptive technologies for multy-disciplinary research and applications (CEVTCON). IEEE"},{"key":"pone.0350637.ref017","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"A Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0350637.ref018","article-title":"Attention is all you need","volume":"30","author":"V Ashish","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0350637.ref019","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep Residual Learning for Image Recognition","author":"K He","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0350637.ref020","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely Connected Convolutional Networks","author":"G Huang","year":"2017","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0350637.ref021","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"pone.0350637.ref022","article-title":"Implementation of deep neural networks to classify EEG signals using gramian angular summation field for epilepsy diagnosis","author":"KP Thanaraj","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0350637.ref023","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.patrec.2020.03.006","article-title":"Feature extraction from EEG spectrograms for epileptic seizure detection","volume":"133","author":"R Ramos-Aguilar","year":"2020","journal-title":"Pattern Recognition Letters"},{"issue":"6","key":"pone.0350637.ref024","doi-asserted-by":"crossref","first-page":"751","DOI":"10.3390\/e24060751","article-title":"A New Fault Diagnosis of Rolling Bearing Based on Markov Transition Field and CNN","volume":"24","author":"M Wang","year":"2022","journal-title":"Entropy (Basel)"},{"key":"pone.0350637.ref025","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.physrep.2006.11.001","article-title":"Recurrence plots for the analysis of complex systems","volume":"438","author":"N Marwan","year":"2007","journal-title":"Physics Reports"},{"key":"pone.0350637.ref026","article-title":"A framework for multiple-instance learning","volume":"10","author":"O Maron","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"pone.0350637.ref027","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","author":"RR Selvaraju","year":"2017","journal-title":"2017 IEEE International Conference on Computer Vision (ICCV)"},{"key":"pone.0350637.ref028","unstructured":"Lu K, Xu Y, Yang Y. Comparison of the potential between transformer and CNN in image classification. ICMLCA 2021; 2nd International Conference on Machine Learning and computer Application; 2021."},{"key":"pone.0350637.ref029","volume-title":"Medical image classification with convolutional neural network. 2014 13th international conference on control automation robotics & vision (ICARCV","author":"Q Li","year":"2014"},{"issue":"7","key":"pone.0350637.ref030","doi-asserted-by":"crossref","first-page":"5930","DOI":"10.3390\/su15075930","article-title":"A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope","volume":"15","author":"AW Salehi","year":"2023","journal-title":"Sustainability"},{"issue":"3","key":"pone.0350637.ref031","doi-asserted-by":"crossref","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep learning for electroencephalogram (EEG) classification tasks: a review","volume":"16","author":"A Craik","year":"2019","journal-title":"J Neural Eng"},{"key":"pone.0350637.ref032","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.patrec.2019.02.016","article-title":"Classification of myocardial infarction with multi-lead ECG signals and deep CNN","volume":"122","author":"UB Baloglu","year":"2019","journal-title":"Pattern Recognition Letters"},{"issue":"4","key":"pone.0350637.ref033","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1111\/j.1751-7176.2008.04746.x","article-title":"Effects of arterial stiffness, pulse wave velocity, and wave reflections on the central aortic pressure waveform","volume":"10","author":"WW Nichols","year":"2008","journal-title":"J Clin Hypertens (Greenwich)"},{"issue":"1","key":"pone.0350637.ref034","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1186\/s12987-023-00467-8","article-title":"Cerebral arterial flow dynamics during systole and diastole phases in young and older healthy adults","volume":"20","author":"KP OwashI","year":"2023","journal-title":"Fluids and Barriers of the CNS"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:34:21Z","timestamp":1780594461000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350637"}},"subtitle":[],"editor":[{"given":"Haipeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":34,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350637","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]}}}