{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:43:41Z","timestamp":1789724621379,"version":"4.0.1"},"reference-count":47,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["eJHaem"],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Hereditary haemorrhagic telangiectasia (HHT) can result in challenging anaemia and thrombosis phenotypes. Clinical presentations of HHT vary for relatives with identical casual mutations, suggesting other factors may modify severity. To examine objectively, we developed unsupervised machine learning algorithms to test whether haematological data at presentation could be categorised into sub\u2010groupings and fitted to known biological factors. With ethical approval, we examined 10 complete blood count (CBC) variables, four iron index variables, four coagulation variables and eight iron\/coagulation indices combined from 336 genotyped HHT patients (40% male, 60% female, 86.5% not using iron supplementation) at a single centre. T\u2010SNE unsupervised, dimension reduction, machine learning algorithms assigned each high\u2010dimensional datapoint to a location in a two\u2010dimensional plane. k\u2010Means clustering algorithms grouped into profiles, enabling visualisation and inter\u2010profile comparisons of patients\u2019 clinical and genetic features. The unsupervised machine learning algorithms using t\u2010SNE and k\u2010Means identified two distinct CBC profiles, two iron profiles, four clotting profiles and three combined profiles. Validating the methodology, profiles for CBC or iron indices fitted expected patterns for haemorrhage. Distinct coagulation profiles displayed no association with age, sex, C\u2010reactive protein, pulmonary arteriovenous malformations (AVMs), <jats:italic>ENG<\/jats:italic>\/<jats:italic>ACVRL1<\/jats:italic> genotype or epistaxis severity. The most distinct profiles were from t\u2010SNE\/k\u2010Means analyses of combined iron\u2010coagulation indices and mapped to three risk states \u2013 for venous thromboembolism in HHT; for ischaemic stroke attributed to paradoxical emboli through pulmonary AVMs in HHT; and for cerebral abscess attributed to odontogenic bacteremias in immunocompetent HHT patients with right\u2010to\u2010left shunting through pulmonary AVMs. In conclusion, unsupervised machine learning algorithms categorise HHT haematological indices into distinct, clinically relevant profiles which are independent of age, sex or HHT genotype. Further evaluation may inform prophylaxis and management for HHT patients\u2019 haemorrhagic and thrombotic phenotypes.<\/jats:p>","DOI":"10.1002\/jha2.746","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T14:59:03Z","timestamp":1688396343000},"page":"602-611","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised machine learning algorithms identify expected haemorrhage relationships but define unexplained coagulation profiles mapping to thrombotic phenotypes in hereditary haemorrhagic telangiectasia"],"prefix":"10.1002","volume":"4","author":[{"given":"Ghazel","family":"Mukhtar","sequence":"first","affiliation":[{"name":"National Heart and Lung Institute Imperial College London London UK"},{"name":"Imperial College School of Medicine London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9007-5775","authenticated-orcid":false,"given":"Claire L.","family":"Shovlin","sequence":"additional","affiliation":[{"name":"National Heart and Lung Institute Imperial College London London UK"},{"name":"Specialist Medicine Imperial College Healthcare NHS Trust London UK"},{"name":"NIHR Imperial Biomedical Research Centre London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,7,3]]},"reference":[{"key":"e_1_2_13_2_1","unstructured":"European Reference Network for Rare Vascular Disease (VASCERN): Hereditary haemorrhagic telangiectasia. Available from:www.orpha.net\/consor\/www\/cgi\u2010bin\/OC_Exp.php?lng=EN&Expert=774. Accessed 23 Oct2022."},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199510053331407"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.blre.2010.07.001"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.20818"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood.2019004560"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9113571"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021203487"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-8628(20000306)91:1<66::AID-AJMG12>3.0.CO;2-P"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2021-218332"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200310-1441OC"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1136\/jmg.2005.035451"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2015.07.040"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-020-01386-9"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.120.032073"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000013169"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0088812"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/cix373"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1086\/511645"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2017-210764"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00270-019-02396-2"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10620-011-1585-2"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.7326\/M20\u20101443"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmg.2021.104370"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0076516"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32594-0"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2018.205682"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2011-201076"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470720325.ch11"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.1038\/ng0294-205"},{"key":"e_1_2_13_31_1","doi-asserted-by":"publisher","DOI":"10.1086\/513906"},{"key":"e_1_2_13_32_1","article-title":"Iron deficiency responses and integrated compensations in patients according to hereditary haemorrhagic telangiectasia ACVRL1\u00b8 ENG and SMAD4 genotypes","author":"Sharma L","year":"2023","journal-title":"Haematologica"},{"key":"e_1_2_13_33_1","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2022007136"},{"key":"e_1_2_13_34_1","unstructured":"Scikit\u2010learn. Sklearn.preprocessing.StandardScaler. Available from:https:\/\/scikitlearn.org\/stable\/modules\/generated\/sklearn.preprocessing.StandardScaler.html. Accessed 24 May2022."},{"key":"e_1_2_13_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2398954"},{"key":"e_1_2_13_36_1","unstructured":"Scikit\u2010learn. sklearn.manifold.TSNE. Available from:https:\/\/scikit\u2010learn.org\/stable\/modules\/generated\/sklearn.manifold.TSNE.html. Accessed 24 May2022."},{"key":"e_1_2_13_37_1","doi-asserted-by":"crossref","unstructured":"ShahapureKR.NicholasC.Cluster Quality Analysis Using Silhouette Score. \u2013 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA) 2020 747\u201348.","DOI":"10.1109\/DSAA49011.2020.00096"},{"key":"e_1_2_13_38_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2018-99-119352"},{"key":"e_1_2_13_39_1","volume-title":"Wintrobe's Clinical Haematology","author":"Greer JP","year":"2009"},{"issue":"5","key":"e_1_2_13_40_1","first-page":"1031","article-title":"Elevated factor VIII in hereditary haemorrhagic telangiectasia (HHT): association with venous thromboembolism","volume":"98","author":"Shovlin CL","year":"2007","journal-title":"Thromb Haemost"},{"key":"e_1_2_13_41_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc1213554"},{"key":"e_1_2_13_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-019-1179-1"},{"key":"e_1_2_13_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9061699"},{"key":"e_1_2_13_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.thromres.2023.04.017"},{"key":"e_1_2_13_45_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2796.1999.00398.x"},{"key":"e_1_2_13_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.25959"},{"key":"e_1_2_13_47_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2015-05-642223"},{"key":"e_1_2_13_48_1","doi-asserted-by":"publisher","DOI":"10.1183\/23120541.00035-2016"}],"container-title":["eJHaem"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jha2.746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T18:00:20Z","timestamp":1694714420000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jha2.746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,3]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/jha2.746"],"URL":"https:\/\/doi.org\/10.1002\/jha2.746","archive":["Portico"],"relation":{},"ISSN":["2688-6146","2688-6146"],"issn-type":[{"value":"2688-6146","type":"print"},{"value":"2688-6146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,3]]},"assertion":[{"value":"2023-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}