{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["7(2)"],"submitter":["Kawka M"],"pubmed_abstract":["<h4>Aims</h4>Thrombo- and microembolic complications following abdominal aortic aneurysm (AAA) repair are hypothesized to be associated with wall thrombus burden. Fully automatic volume segmentation (FAVS) of imaging enables extraction of morphological features from which thrombogenic phenotypes may be identified.<h4>Methods and results</h4>This was a multi-centre retrospective cohort study using FAVS to examine pre-operative imaging for elective AAA repairs (2013-23). Radiological data were matched with National Vascular Registry thromboembolic outcomes data (cerebral, bowel, renal or limb ischaemia). Principal component analysis was used for dimensionality reduction, followed by unsupervised machine learning with <i>k</i>-nearest neighbours clustering, with number of clusters determined "],"journal":["European heart journal. Digital health"],"pagination":["ztaf136"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12853115"],"repository":["biostudies-literature"],"pubmed_title":["Unsupervised machine learning for identifying morphological phenotypes in abdominal aortic aneurysms using fully automated volume-segmented imaging: a multicentre cohort study."],"pmcid":["PMC12853115"],"pubmed_authors":["Pouncey AL","Scicluna R","Caradu C","Gohel M","Powell JT","Kawka M","Bown MJ","Bicknell C"],"additional_accession":[]},"is_claimable":false,"name":"Unsupervised machine learning for identifying morphological phenotypes in abdominal aortic aneurysms using fully automated volume-segmented imaging: a multicentre cohort study.","description":"<h4>Aims</h4>Thrombo- and microembolic complications following abdominal aortic aneurysm (AAA) repair are hypothesized to be associated with wall thrombus burden. Fully automatic volume segmentation (FAVS) of imaging enables extraction of morphological features from which thrombogenic phenotypes may be identified.<h4>Methods and results</h4>This was a multi-centre retrospective cohort study using FAVS to examine pre-operative imaging for elective AAA repairs (2013-23). Radiological data were matched with National Vascular Registry thromboembolic outcomes data (cerebral, bowel, renal or limb ischaemia). Principal component analysis was used for dimensionality reduction, followed by unsupervised machine learning with <i>k</i>-nearest neighbours clustering, with number of clusters determined ","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Mar","modification":"2026-06-18T05:51:39.726Z","creation":"2026-06-18T03:07:10.596Z"},"accession":"S-EPMC12853115","cross_references":{"pubmed":["41624562"],"doi":["10.1093/ehjdh/ztaf136"]}}