{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T18:01:12Z","timestamp":1780941672862,"version":"3.54.1"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001729","name":"Stiftelsen f\u00f6r Strategisk Forskning","doi-asserted-by":"publisher","award":["RMX18-0152"],"award-info":[{"award-number":["RMX18-0152"]}],"id":[{"id":"10.13039\/501100001729","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["2021-00711_VR\/JPND"],"award-info":[{"award-number":["2021-00711_VR\/JPND"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Future Artificial Intelligence Research Foundation","award":["PE0000013-FAIR"],"award-info":[{"award-number":["PE0000013-FAIR"]}]},{"name":"Regional agreement between Ume\u00e5 University and Region V\u00e4sterbotten"},{"name":"Regional agreement between Ume\u00e5 University and Region V\u00e4sterbotten"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Idiopathic normal pressure hydrocephalus (INPH) is a treatable neurological condition, yet predicting which patients will benefit from a cerebrospinal fluid shunt remains challenging. Structural brain MRI is a core part of the diagnostic workup, but traditional radiological measures show limited predictive accuracy. This study aimed to assess whether deep learning and radiomics-based machine learning approaches can provide clinically useful predictions of shunt outcome based on preoperative MRI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We investigated 149 shunted INPH patients with available preoperative T1-weighted, T2-weighted, and FLAIR images. Patients were classified as responders (n\u2009=\u2009113) or non-responders (n\u2009=\u200936) based on postoperative gait speed improvement. For INPH, this is a large sample with typical outcome distribution. Three artificial intelligence approaches were tested: a late-fusion ensemble of multiple 3D convolutional neural networks; a multimodal intermediate fusion model; and radiomics-based machine learning models trained on features extracted from whole-brain masks. Models were assessed using 10-fold cross-validation. The best performing model on the validation set was selected from each approach. Performance metrics included the area under the receiving operating characteristic curve (AUROC), sensitivity, and specificity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Performance was considered poor in all models, and none reached an area under the receiving operating characteristic curve above 70%. Of the three methodologies, the best performance was achieved with a radiomics-based model (Linear Discriminant Analysis classifier on T1-weighted images) which achieved an AUROC of 63.7%. In a reduced subset of clearly separated responders and non-responders (n\u2009=\u200972), the best model (late fusion ensemble of 5 convolutional neural networks) reached an AUROC of 69.2%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Despite the use of advanced artificial intelligence techniques, structural MRI alone were insufficient for reliably predicting gait outcome after surgery in idiopathic normal pressure hydrocephalus. To capture the complexity of the condition and enable clinically meaningful predictions, our findings indicate the need for research investigating multimodal input and using large multi-center datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0350335","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T17:35:24Z","timestamp":1780940124000},"page":"e0350335","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6341-8444","authenticated-orcid":true,"given":"Klara","family":"Mogensen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1860-7447","authenticated-orcid":true,"given":"Valerio","family":"Guarrasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia","family":"Behndig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Eriksson De Ryst","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Soda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2031-722X","authenticated-orcid":true,"given":"Anders","family":"Eklund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Malm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1454-4725","authenticated-orcid":true,"given":"Sara","family":"Qvarlander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"issue":"1","key":"pone.0350335.ref001","doi-asserted-by":"crossref","first-page":"235","DOI":"10.3233\/JAD-221250","article-title":"Artificial Intelligence Model for Alzheimer\u2019s Disease Detection with Convolution Neural Network for Magnetic Resonance Images","volume":"93","author":"SR Ziyad","year":"2023","journal-title":"J Alzheimers Dis"},{"key":"pone.0350335.ref002","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1136\/jnnp.2006.088351","article-title":"Idiopathic normal pressure hydrocephalus","volume":"6","author":"J Malm","year":"2006","journal-title":"Pract Neurol"},{"issue":"5","key":"pone.0350335.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0217705","article-title":"Prevalence of idiopathic normal pressure hydrocephalus: A prospective, population-based study","volume":"14","author":"J Andersson","year":"2019","journal-title":"PLoS One"},{"issue":"5","key":"pone.0350335.ref004","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1111\/ane.13710","article-title":"Prevalence and development of idiopathic normal pressure hydrocephalus: A 16-year longitudinal study in Japan","volume":"146","author":"C Iseki","year":"2022","journal-title":"Acta Neurol Scand"},{"key":"pone.0350335.ref005","doi-asserted-by":"crossref","DOI":"10.1227\/01.NEU.0000168185.29659.C5","article-title":"Diagnosing idiopathic normal-pressure hydrocephalus","volume":"57","author":"N Relkin","year":"2005","journal-title":"Neurosurgery"},{"issue":"22","key":"pone.0350335.ref006","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1056\/NEJMoa2503109","article-title":"A Randomized Trial of Shunting for Idiopathic Normal-Pressure Hydrocephalus","volume":"393","author":"MG Luciano","year":"2025","journal-title":"N Engl J Med"},{"key":"pone.0350335.ref007","doi-asserted-by":"crossref","DOI":"10.1227\/01.NEU.0000168184.01002.60","article-title":"The value of supplemental prognostic tests for the preoperative assessment of idiopathic normal-pressure hydrocephalus","volume":"57","author":"A Marmarou","year":"2005","journal-title":"Neurosurgery"},{"issue":"7","key":"pone.0350335.ref008","article-title":"Efficacy and safety of shunt surgery in patients with idiopathic normal-pressure hydrocephalus: can we predict shunt response by preoperative magnetic resonance imaging (MRI)?","volume":"79","author":"SY Yun","year":"2024","journal-title":"Clin Radiol"},{"issue":"10","key":"pone.0350335.ref009","doi-asserted-by":"crossref","first-page":"2641","DOI":"10.1007\/s00701-021-04922-z","article-title":"Clinical predictors of shunt response in the diagnosis and treatment of idiopathic normal pressure hydrocephalus: a systematic review and meta-analysis","volume":"163","author":"SG Thavarajasingam","year":"2021","journal-title":"Acta Neurochir (Wien)"},{"issue":"2","key":"pone.0350335.ref010","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s00701-022-05402-8","article-title":"Radiological predictors of shunt response in the diagnosis and treatment of idiopathic normal pressure hydrocephalus: a systematic review and meta-analysis","volume":"165","author":"SG Thavarajasingam","year":"2023","journal-title":"Acta Neurochir (Wien)"},{"key":"pone.0350335.ref011","doi-asserted-by":"crossref","first-page":"109457","DOI":"10.1016\/j.compbiomed.2024.109457","article-title":"An optimized ensemble search approach for classification of higher-level gait disorder using brain magnetic resonance images","volume":"184","author":"K Mogensen","year":"2025","journal-title":"Comput Biol Med"},{"issue":"10","key":"pone.0350335.ref012","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.3174\/ajnr.A8372","article-title":"MRI-Based Prediction of Clinical Improvement after Ventricular Shunt Placement for Normal Pressure Hydrocephalus: Development and Evaluation of an Integrated Multisequence Machine Learning Algorithm","volume":"45","author":"OP Leary","year":"2024","journal-title":"AJNR Am J Neuroradiol"},{"issue":"1","key":"pone.0350335.ref013","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1186\/s13244-022-01311-7","article-title":"Reproducibility of artificial intelligence models in computed tomography of the head: a quantitative analysis","volume":"13","author":"F Gunzer","year":"2022","journal-title":"Insights Imaging"},{"key":"pone.0350335.ref014","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.inffus.2013.04.006","article-title":"A survey of multiple classifier systems as hybrid systems","volume":"16","author":"M Wo\u017aniak","year":"2014","journal-title":"Information Fusion"},{"key":"pone.0350335.ref015","first-page":"1","volume-title":"Timing Is Everything: Finding the Optimal Fusion Points in Multimodal Medical Imaging. 2025 International Joint Conference on Neural Networks (IJCNN","author":"V Guarrasi","year":"2025"},{"key":"pone.0350335.ref016","doi-asserted-by":"crossref","first-page":"196","DOI":"10.2522\/ptj.20090079","article-title":"Meaningful gait speed improvement during the first 60 days poststroke: minimal clinically important difference","volume":"90","author":"JK Tilson","year":"2010","journal-title":"Phys Ther"},{"issue":"3","key":"pone.0350335.ref017","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1016\/j.neuroimage.2005.02.018","article-title":"Unified segmentation","volume":"26","author":"J Ashburner","year":"2005","journal-title":"Neuroimage"},{"key":"pone.0350335.ref018","doi-asserted-by":"crossref","first-page":"119474","DOI":"10.1016\/j.neuroimage.2022.119474","article-title":"SynthStrip: skull-stripping for any brain image","volume":"260","author":"A Hoopes","year":"2022","journal-title":"Neuroimage"},{"key":"pone.0350335.ref019","first-page":"770","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR","author":"K He","year":"2016"},{"key":"pone.0350335.ref020","first-page":"2261","volume-title":"Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR","author":"G Huang","year":"2017"},{"key":"pone.0350335.ref021","doi-asserted-by":"crossref","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","volume-title":"Squeeze-and-Excitation Networks. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Hu","year":"2018"},{"key":"pone.0350335.ref022","doi-asserted-by":"crossref","first-page":"101871","DOI":"10.1016\/j.media.2020.101871","article-title":"Accurate brain age prediction with lightweight deep neural networks","volume":"68","author":"H Peng","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0350335.ref023","first-page":"13286","volume-title":"MMTM: Multimodal Transfer Module for CNN Fusion. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Joze Vaezi","year":"2020"},{"key":"pone.0350335.ref024","first-page":"328","article-title":"Image biomarker standardisation initiative","volume":"295","author":"A Zwanenburg","year":"2020","journal-title":"Radiology"},{"issue":"4","key":"pone.0350335.ref025","doi-asserted-by":"crossref","first-page":"195","DOI":"10.4103\/tjem.tjem_182_23","article-title":"Receiver operating characteristic curve analysis in diagnostic accuracy studies: A guide to interpreting the area under the curve value","volume":"23","author":"\u015eK \u00c7orbac\u0131o\u011flu","year":"2023","journal-title":"Turk J Emerg Med"},{"issue":"2","key":"pone.0350335.ref026","doi-asserted-by":"crossref","first-page":"63","DOI":"10.2176\/nmc.st.2020-0292","article-title":"Guidelines for Management of Idiopathic Normal Pressure Hydrocephalus (Third Edition): Endorsed by the Japanese Society of Normal Pressure Hydrocephalus","volume":"61","author":"M Nakajima","year":"2021","journal-title":"Neurol Med Chir (Tokyo)"},{"issue":"4","key":"pone.0350335.ref027","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1111\/j.1600-0404.2012.01677.x","article-title":"A new scale for assessment of severity and outcome in iNPH","volume":"126","author":"P Hellstr\u00f6m","year":"2012","journal-title":"Acta Neurol Scand"},{"issue":"7","key":"pone.0350335.ref028","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1136\/jnnp-2012-302924","article-title":"Pulsatility in CSF dynamics: pathophysiology of idiopathic normal pressure hydrocephalus","volume":"84","author":"S Qvarlander","year":"2013","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"pone.0350335.ref029","article-title":"Ventriculoperitoneal shunt outcomes of normal pressure hydrocephalus: a case series of 116 patients","author":"EM Wu","year":"2019","journal-title":"Cureus"},{"issue":"23","key":"pone.0350335.ref030","doi-asserted-by":"crossref","first-page":"2063","DOI":"10.1212\/WNL.0000000000002193","article-title":"Practice guideline: Idiopathic normal pressure hydrocephalus: Response to shunting and predictors of response: Report of the Guideline Development, Dissemination, and Implementation Subcommittee of the American Academy of Neurology","volume":"85","author":"JJ Halperin","year":"2015","journal-title":"Neurology"},{"key":"pone.0350335.ref031","doi-asserted-by":"crossref","first-page":"977123","DOI":"10.3389\/fsurg.2022.977123","article-title":"One-year outcome of a lumboperitoneal shunt in older adults with idiopathic normal pressure hydrocephalus","volume":"9","author":"X Fang","year":"2022","journal-title":"Front Surg"},{"issue":"1","key":"pone.0350335.ref032","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s12987-022-00309-z","article-title":"Cerebrospinal fluid biomarkers that reflect clinical symptoms in idiopathic normal pressure hydrocephalus patients","volume":"19","author":"H Lukkarinen","year":"2022","journal-title":"Fluids Barriers CNS"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T17:35:29Z","timestamp":1780940129000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350335"}},"subtitle":[],"editor":[{"given":"Md Nasir","family":"Uddin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":32,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350335","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,8]]}}}