{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:58:06Z","timestamp":1793609886288,"version":"4.5.0"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T00:00:00Z","timestamp":1728777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T00:00:00Z","timestamp":1728777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Orphanet J Rare Dis"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Paroxysmal Nocturnal Haemoglobinuria (PNH) is an ultra-rare, acquired disorder that is challenging to diagnose due to varied symptoms, heterogeneous patient presentations, and lack of awareness among healthcare professionals. This leads to frequent misdiagnosis and delays in diagnosis. This study evaluated the feasibility of a machine learning model to identify undiagnosed PNH patients using structured electronic health records.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>The study used data from the Optimum Patient Care Research Database, which contains electronic health records from general practitioner (GP) practices across the United Kingdom. PNH patients were identified by the presence, and control patients by the absence of a PNH diagnosis code in their records. Clinical features (symptoms, diagnoses, healthcare utilisation) from 131 patients in the PNH group and 593,838 patients in the control group, were inputted to a tree-based XGBoost machine learning model to classify patients as either \u201cpositive\u201d or \u201cnegative\u201d for PNH suspicion. The algorithm was finalised after additional exclusions and inclusions applied. Performance was assessed using positive predictive value (PPV), recall and specificity. As the sample used to develop the algorithm was not representative of the true population prevalence, PPV was additionally adjusted to reflect performance in the wider population.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Of all the patients in the PNH group, 27% were classified as positive (recall). 99.99% of the control group were classified as negative (specificity). Of all the patients classified as positive, 60.4% had a diagnosis of PNH in their record (PPV). The PPV adjusted for the population prevalence of PNH was 19.59 suggesting nearly 1 in 5 patients flagged may warrant further PNH investigation. The key clinical features in the model were aplastic anaemia, pancytopenia, haemolytic anaemia, myelodysplastic syndrome, and Budd-Chiari syndrome.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>This is the first study to combine clinical understanding of PNH with machine learning, demonstrating the ability to discriminate between PNH and control patients in retrospective electronic health records. With further investigation and validation, this algorithm could be deployed on live health data, potentially leading to earlier diagnosis for patients who currently experience long diagnostic delays or remain undiagnosed.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13023-024-03406-4","type":"journal-article","created":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T22:01:33Z","timestamp":1728856893000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A machine learning algorithm for the detection of paroxysmal nocturnal haemoglobinuria (PNH) in UK primary care electronic health records"],"prefix":"10.1186","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-867X","authenticated-orcid":false,"given":"Amanda","family":"Worker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadley","family":"Mahon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Sams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Freya","family":"Boardman-Pretty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Marchini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rand","family":"Dubis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Warren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jez","family":"Stockdale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyothika","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth","family":"Varones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Ollerenshaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Calum","family":"Grant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Fish","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard J.","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,13]]},"reference":[{"issue":"2","key":"3406_CR1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1111\/ejh.13640","volume":"107","author":"SJ Richards","year":"2021","unstructured":"Richards SJ, Painter D, Dickinson AJ, Griffin M, Munir T, Arnold L, Payne D, Pike A, Muus P, Hill A, Newton DJ. The incidence and prevalence of patients with paroxysmal nocturnal haemoglobinuria and aplastic anaemia PNH syndrome: a retrospective analysis of the UK\u2019s population-based haematological malignancy research network 2004\u20132018. Eur J Haematol. 2021;107(2):211\u20138.","journal-title":"Eur J Haematol"},{"key":"3406_CR2","unstructured":"National PNH Service. The National PNH Service website. Leeds Teaching Hospitals NHS Trust. https:\/\/pnhserviceuk.co.uk\/. Accessed 15 Jul 2024."},{"issue":"25","key":"3406_CR3","first-page":"6786","volume":"117","author":"RJ Kelly","year":"2011","unstructured":"Kelly RJ, Hill A, Arnold LM, Brooksbank GL, Richards SJ, Cullen M, Mitchell LD, Cohen DR, Gregory WM, Hillmen P. Long-term treatment with eculizumab in paroxysmal nocturnal hemoglobinuria: sustained efficacy and improved survival. Blood J Am Soc Hematol. 2011;117(25):6786\u201392.","journal-title":"Blood J Am Soc Hematol"},{"key":"3406_CR4","doi-asserted-by":"crossref","unstructured":"Kelly RJ, Holt M, Vidler J, Arnold LM, Large J, Forrest B, Barnfield C, Pike A, Griffin M, Munir T, Muus P. Treatment outcomes of complement protein C5 inhibition in 509 UK patients with paroxysmal nocturnal hemoglobinuria. Blood J. 2023:blood-2023021762.","DOI":"10.1182\/blood-2022-167725"},{"issue":"1","key":"3406_CR5","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/ejh.13059","volume":"101","author":"A R\u00f6th","year":"2018","unstructured":"R\u00f6th A, Maciejewski J, Nishimura JI, Jain D, Weitz JI. Screening and diagnostic clinical algorithm for paroxysmal nocturnal hemoglobinuria: expert consensus. Eur J Haematol. 2018;101(1):3\u201311.","journal-title":"Eur J Haematol"},{"issue":"12","key":"3406_CR6","doi-asserted-by":"publisher","DOI":"10.2196\/11293","volume":"20","author":"B McMillan","year":"2018","unstructured":"McMillan B, Eastham R, Brown B, Fitton R, Dickinson D. Primary care patient records in the United Kingdom: past, present, and future research priorities. J Med Internet Res. 2018;20(12): e11293.","journal-title":"J Med Internet Res"},{"key":"3406_CR7","first-page":"39","volume":"31","author":"A Lynam","year":"2023","unstructured":"Lynam A, Curtis C, Stanley B, Heatley H, Worthington C, Roberts EJ, Price C, Carter V, Dennis J, McGovern A, Price D. Data-resource profile: united kingdom optimum patient care research database. Pragm Observ Res. 2023;31:39\u201349.","journal-title":"Pragm Observ Res"},{"issue":"8","key":"3406_CR8","first-page":"3099","volume":"112","author":"RP de Latour","year":"2008","unstructured":"de Latour RP, Mary JY, Salanoubat C, Terriou L, Etienne G, Mohty M, Roth S, de Guibert S, Maury S, Cahn JY, Soci\u00e9 G. Paroxysmal nocturnal hemoglobinuria: natural history of disease subcategories. Blood J Am Soc Hematol. 2008;112(8):3099\u2013106.","journal-title":"Blood J Am Soc Hematol"},{"key":"3406_CR9","unstructured":"NHS Digital. (n.d.). NHS Digital Terminology Server: Reference Data Services. Retrieved from https:\/\/isd.digital.nhs.uk\/trud\/users\/guest\/filters\/0\/categories\/26"},{"key":"3406_CR10","doi-asserted-by":"crossref","unstructured":"Parker CJ. Update on the diagnosis and management of paroxysmal nocturnal hemoglobinuria. Hematology 2014, the American Society of Hematology Education Program Book. 2016;2016(1):208\u201316.","DOI":"10.1182\/asheducation-2016.1.208"},{"key":"3406_CR11","doi-asserted-by":"crossref","unstructured":"Bektas M, Copley-Merriman C, Khan S, Sarda SP, Shammo JM. Paroxysmal nocturnal hemoglobinuria: patient journey and burden of disease. J Manag Care Special Pharm. 2020 Dec;26(12-b Suppl):S8\u201314.","DOI":"10.18553\/jmcp.2020.26.12-b.s8"},{"key":"3406_CR12","unstructured":"Alexion. Real PNH stories. https:\/\/alexion.com\/our-inspiration\/real-stories\/pnh. Accessed 01 Nov 2023."},{"key":"3406_CR13","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2016 Aug 13, pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"issue":"12","key":"3406_CR14","doi-asserted-by":"publisher","first-page":"3699","DOI":"10.1182\/blood-2005-04-1717","volume":"106","author":"C Parker","year":"2005","unstructured":"Parker C, Omine M, Richards S, Nishimura JI, Bessler M, Ware R, Hillmen P, Luzzatto L, Young N, Kinoshita T, Rosse W. Diagnosis and management of paroxysmal nocturnal hemoglobinuria. Blood. 2005;106(12):3699\u2013709.","journal-title":"Blood"}],"container-title":["Orphanet Journal of Rare Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13023-024-03406-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13023-024-03406-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13023-024-03406-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T10:02:59Z","timestamp":1728900179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojrd.biomedcentral.com\/articles\/10.1186\/s13023-024-03406-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,13]]},"references-count":14,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["3406"],"URL":"https:\/\/doi.org\/10.1186\/s13023-024-03406-4","relation":{},"ISSN":["1750-1172"],"issn-type":[{"value":"1750-1172","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,13]]},"assertion":[{"value":"6 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study is based wholly on data from the Optimum Patient Care Research Database obtained under a limited licence from Optimum Patient Care Limited and its execution is approved by the Anonymised Data Ethic and Protocol Transparency Committee (ADEPT)\u2014reference: ADEPT0822, Protocol 2318. However, the interpretation and conclusions contained in this report are those of the author\/s alone. OPCRD is approved by the NHS Health Research Authority Research Ethics Committee (HRA REC reference: 20\/EM\/0148) to receive and provide anonymised datasets for scientific, exploratory and public health research. OPC receives consent from GP practices who act as Data Controllers and provide consent on-behalf of their patients for the de-identified patient data that they contribute to OPCRD for research purposes. Participating GP practices provide their written and signed consent in the form of a signed Service, Data Processing and Data Sharing Agreement between the GP practice and OPC, with explicit consent for de-identified patient data to be contributed to OPCRD for research purposes. Patients who have opted-out of data sharing are excluded from the data contributed to OPCRD. Patients are informed of data contribution to OPCRD by means of poster(s) provided to contributing GP practices for public display and patient awareness.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"During study conduct, AW, HM, JS, FBP, EM, RD, AW, EV, DO, CG and PF were employees of Mendelian. RJK receives research funding from Novartis, acts as a consultant for Sobi, AstraZeneca and Alexion. RJK also sits on the advisory boards for Alexion, AstraZeneca, Novartis, Sobi, Jazz, Amgen and receives honoraria from Alexion, Sobi, Biologix.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"378"}}