{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:55:36Z","timestamp":1781650536362,"version":"3.54.5"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004047","name":"Karolinska Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004047","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Atrial fibrillation (AF) is a major risk factor for atherothrombotic complications but is often asymptomatic and undiagnosed. This study aimed to develop a machine learning model to distinguish between individuals with low and high risk of AF, using routinely collected diagnostic data from Swedish primary health care.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Cases (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200942,607, aged\u2009\u2265\u200945 years) with diagnosed new onset AF and controls (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009427,169) matched by age and sex. Machine learning models stratified for age (45\u201369 and \u2265\u200970 years) and sex were developed using stochastic gradient boosting, based on number of primary health care visits during the year before the index AF diagnosis, age, and ICD-10 codes from electronic medical records 2014\u20132019. Performance was evaluated by AUC, sensitivity and specificity, and key predictors ranked by normalized relative influence (NRI) and odds ratios for marginal effects.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The most influential predictors were the number of visits (NRI: 29.9\u201346.3%) and age (NRI: 6.2\u201315.9%), followed by risk factors for AF such as heart failure, hypertension, and cardiac arrhythmias. Model AUC ranged from 0.77 to 0.79 across subgroups. Sensitivity was 0.76\u20130.80, and specificity 0.58\u20130.66, with higher sensitivity in older groups and higher specificity in younger ones. The models correctly identified 95\u201398% of individuals without known AF.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The models show good predictive ability, effectively ruling out low-risk patients while identifying known risk factors. With AUC values comparable to more complex models, our approach using only visit frequency, age, and diagnoses may support initial risk assessment in primary health care for identifying individuals at risk of AF.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-026-03491-4","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T12:46:55Z","timestamp":1776430015000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning model to simplify recognition of patients with atrial fibrillation based on diagnostic codes in Swedish primary health care"],"prefix":"10.1186","volume":"26","author":[{"given":"Anders","family":"Norrman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Wachtler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Per","family":"W\u00e4ndell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Eriksson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toralph","family":"Ruge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boel","family":"Brynedal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Hasselstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kahan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Axel C.","family":"Carlsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"36","key":"3491_CR1","doi-asserted-by":"publisher","first-page":"3314","DOI":"10.1093\/eurheartj\/ehae176","volume":"45","author":"IC Van Gelder","year":"2024","unstructured":"Van Gelder IC, Rienstra M, Bunting KV, Casado-Arroyo R, Caso V, Crijns H, et al. 2024 ESC Guidelines for the management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS). Eur Heart J. 2024;45(36):3314\u2013414.","journal-title":"Eur Heart J"},{"issue":"5","key":"3491_CR2","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1111\/joim.12114","volume":"274","author":"L Friberg","year":"2013","unstructured":"Friberg L, Bergfeldt L. Atrial fibrillation prevalence revisited. J Intern Med. 2013;274(5):461\u20138.","journal-title":"J Intern Med"},{"issue":"25","key":"3491_CR3","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1161\/CIRCULATIONAHA.114.014343","volume":"131","author":"E Svennberg","year":"2015","unstructured":"Svennberg E, Engdahl J, Al-Khalili F, Friberg L, Frykman V, Rosenqvist M. Mass Screening for Untreated Atrial Fibrillation: The STROKESTOP Study. Circulation. 2015;131(25):2176\u201384.","journal-title":"Circulation"},{"issue":"8","key":"3491_CR4","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1161\/CIRCULATIONAHA.112.126656","volume":"127","author":"J Engdahl","year":"2013","unstructured":"Engdahl J, Andersson L, Mirskaya M, Rosenqvist M. Stepwise screening of atrial fibrillation in a 75-year-old population: implications for stroke prevention. Circulation. 2013;127(8):930\u20137.","journal-title":"Circulation"},{"key":"3491_CR5","doi-asserted-by":"crossref","unstructured":"Petzl AM, Jabbour G, Cadrin-Tourigny J, P\u00fcrerfellner H, Macle L, Khairy P, et al. Innovative approaches to atrial fibrillation prediction: Should polygenic scores and machine learning be implemented in clinical practice? Europace. 2024;26(8).","DOI":"10.1093\/europace\/euae201"},{"key":"3491_CR6","doi-asserted-by":"crossref","unstructured":"Schnabel RB, Sullivan LM, Levy D, Pencina MJ, Massaro JM, D\u2019Agostino RB, Sr, et al. Development of a risk score for atrial fibrillation (Framingham Heart Study): a community-based cohort study. Lancet. 2009;373(9665):739\u201345.","DOI":"10.1016\/S0140-6736(09)60443-8"},{"issue":"1","key":"3491_CR7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.amjcard.2010.08.049","volume":"107","author":"AM Chamberlain","year":"2011","unstructured":"Chamberlain AM, Agarwal SK, Folsom AR, Soliman EZ, Chambless LE, Crow R, et al. A clinical risk score for atrial fibrillation in a biracial prospective cohort (from the Atherosclerosis Risk in Communities [ARIC] study). Am J Cardiol. 2011;107(1):85\u201391.","journal-title":"Am J Cardiol"},{"issue":"2","key":"3491_CR8","doi-asserted-by":"publisher","first-page":"e000102","DOI":"10.1161\/JAHA.112.000102","volume":"2","author":"A Alonso","year":"2013","unstructured":"Alonso A, Krijthe BP, Aspelund T, Stepas KA, Pencina MJ, Moser CB, et al. Simple risk model predicts incidence of atrial fibrillation in a racially and geographically diverse population: the CHARGE-AF consortium. J Am Heart Assoc. 2013;2(2):e000102.","journal-title":"J Am Heart Assoc"},{"key":"3491_CR9","doi-asserted-by":"publisher","first-page":"752317","DOI":"10.3389\/fphys.2021.752317","volume":"12","author":"AS Tseng","year":"2021","unstructured":"Tseng AS, Noseworthy PA. Prediction of Atrial Fibrillation Using Machine Learning: A Review. Front Physiol. 2021;12:752317.","journal-title":"Front Physiol"},{"issue":"11","key":"3491_CR10","doi-asserted-by":"publisher","first-page":"e0224582","DOI":"10.1371\/journal.pone.0224582","volume":"14","author":"NR Hill","year":"2019","unstructured":"Hill NR, Ayoubkhani D, McEwan P, Sugrue DM, Farooqui U, Lister S, et al. Predicting atrial fibrillation in primary care using machine learning. PLoS ONE. 2019;14(11):e0224582.","journal-title":"PLoS ONE"},{"issue":"1","key":"3491_CR11","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1093\/ehjqcco\/qcac013","volume":"9","author":"RB Schnabel","year":"2022","unstructured":"Schnabel RB, Witt H, Walker J, Ludwig M, Geelhoed B, Kossack N, et al. Machine learning-based identification of risk-factor signatures for undiagnosed atrial fibrillation in primary prevention and post-stroke in clinical practice. Eur Heart J Qual Care Clin Outcomes. 2022;9(1):16\u201323.","journal-title":"Eur Heart J Qual Care Clin Outcomes"},{"issue":"1","key":"3491_CR12","doi-asserted-by":"publisher","first-page":"e1919396","DOI":"10.1001\/jamanetworkopen.2019.19396","volume":"3","author":"P Tiwari","year":"2020","unstructured":"Tiwari P, Colborn KL, Smith DE, Xing F, Ghosh D, Rosenberg MA. Assessment of a Machine Learning Model Applied to Harmonized Electronic Health Record Data for the Prediction of Incident Atrial Fibrillation. JAMA Netw Open. 2020;3(1):e1919396.","journal-title":"JAMA Netw Open"},{"key":"3491_CR13","doi-asserted-by":"publisher","first-page":"e080811","DOI":"10.1136\/bmj-2024-080811","volume":"388","author":"SA Martin","year":"2025","unstructured":"Martin SA, Johansson M, Heath I, Lehman R, Korownyk C. Sacrificing patient care for prevention: distortion of the role of general practice. BMJ. 2025;388:e080811.","journal-title":"BMJ"},{"key":"3491_CR14","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD\u2009+\u2009AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378.","journal-title":"BMJ"},{"issue":"1","key":"3491_CR15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s12875-025-02716-1","volume":"26","author":"P W\u00e4ndell","year":"2025","unstructured":"W\u00e4ndell P, Norrman A, Eriksson J, Ivarsson C, Gudjonsdottir H, Hagstr\u00f6mer M, et al. Differences between private and public primary health care centers and differences between men and women in antihypertensive care and cardiovascular prevention in all patients with hypertension treated in primary care in Stockholm County, Sweden. BMC Prim Care. 2025;26(1):20.","journal-title":"BMC Prim Care"},{"issue":"2","key":"3491_CR16","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1111\/j.1365-2796.2012.02519.x","volume":"272","author":"P Andersson","year":"2012","unstructured":"Andersson P, L\u00f6ndahl M, Abdon NJ, Terent A. The prevalence of atrial fibrillation in a geographically well-defined population in northern Sweden: implications for anticoagulation prophylaxis. J Intern Med. 2012;272(2):170\u20136.","journal-title":"J Intern Med"},{"issue":"5","key":"3491_CR17","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.pcd.2024.06.010","volume":"18","author":"P W\u00e4ndell","year":"2024","unstructured":"W\u00e4ndell P, Carlsson AC, Wierzbicka M, Sigurdsson K, \u00c4rnl\u00f6v J, Eriksson J, et al. A machine learning tool for identifying patients with newly diagnosed diabetes in primary care. Prim Care Diabetes. 2024;18(5):501\u20135.","journal-title":"Prim Care Diabetes"},{"key":"3491_CR18","doi-asserted-by":"publisher","first-page":"102806","DOI":"10.1016\/j.pmedr.2024.102806","volume":"44","author":"A Norrman","year":"2024","unstructured":"Norrman A, Hasselstr\u00f6m J, Ljunggren G, Wachtler C, Eriksson J, Kahan T, et al. Predicting new cases of hypertension in Swedish primary care with a machine learning tool. Prev Med Rep. 2024;44:102806.","journal-title":"Prev Med Rep"},{"key":"3491_CR19","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1186\/1471-2458-13-670","volume":"13","author":"AC Carlsson","year":"2013","unstructured":"Carlsson AC, W\u00e4ndell P, \u00d6sby U, Zarrinkoub R, Wettermark B, Ljunggren G. High prevalence of diagnosis of diabetes, depression, anxiety, hypertension, asthma and COPD in the total population of Stockholm, Sweden - a challenge for public health. BMC Public Health. 2013;13:670.","journal-title":"BMC Public Health"},{"issue":"1","key":"3491_CR20","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1186\/s12875-025-02938-3","volume":"26","author":"P W\u00e4ndell","year":"2025","unstructured":"W\u00e4ndell P, Ljunggren G, Carlsson AC. The most common diagnoses in primary care, and changes over time, in the total population of Stockholm, Sweden. BMC Prim Care. 2025;26(1):235.","journal-title":"BMC Prim Care"},{"key":"3491_CR21","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.ejca.2023.01.011","volume":"182","author":"E Nemlander","year":"2023","unstructured":"Nemlander E, Ewing M, Abedi E, Hasselstr\u00f6m J, Sj\u00f6vall A, Carlsson AC, et al. A machine learning tool for identifying non-metastatic colorectal cancer in primary care. Eur J Cancer. 2023;182:100\u20136.","journal-title":"Eur J Cancer"},{"issue":"5","key":"3491_CR22","doi-asserted-by":"publisher","first-page":"100115","DOI":"10.1016\/j.tjpad.2025.100115","volume":"12","author":"J Wallensten","year":"2025","unstructured":"Wallensten J, Wachtler C, Bogdanovic N, Olofsson A, Kivipelto M, J\u00f6nsson L, et al. Machine learning to detect Alzheimer\u2019s disease with data on drugs and diagnoses. J Prev Alzheimers Dis. 2025;12(5):100115.","journal-title":"J Prev Alzheimers Dis"},{"key":"3491_CR23","unstructured":"Team RC. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. 2016. http:\/\/www.R-project.org\/."},{"issue":"1","key":"3491_CR24","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.amjcard.2019.09.034","volume":"125","author":"GYH Lip","year":"2020","unstructured":"Lip GYH, Skj\u00f8th F, Nielsen PB, Larsen TB. Evaluation of the C(2)HEST Risk Score as a Possible Opportunistic Screening Tool for Incident Atrial Fibrillation in a Healthy Population (From a Nationwide Danish Cohort Study). Am J Cardiol. 2020;125(1):48\u201354.","journal-title":"Am J Cardiol"},{"issue":"2","key":"3491_CR25","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.ijcard.2013.10.063","volume":"170","author":"T Forslund","year":"2013","unstructured":"Forslund T, Wettermark B, W\u00e4ndell P, von Euler M, Hasselstr\u00f6m J, Hjemdahl P. Risk scoring and thromboprophylactic treatment of patients with atrial fibrillation with and without access to primary healthcare data: experience from the Stockholm health care system. Int J Cardiol. 2013;170(2):208\u201314.","journal-title":"Int J Cardiol"},{"issue":"9","key":"3491_CR26","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1016\/j.hrthm.2018.05.019","volume":"15","author":"FE Ugowe","year":"2018","unstructured":"Ugowe FE, Jackson LR 2nd, Thomas KL. Racial and ethnic differences in the prevalence, management, and outcomes in patients with atrial fibrillation: A systematic review. Heart Rhythm. 2018;15(9):1337\u201345.","journal-title":"Heart Rhythm"},{"key":"3491_CR27","doi-asserted-by":"publisher","first-page":"100157","DOI":"10.1016\/j.lanepe.2021.100157","volume":"7","author":"SC Chung","year":"2021","unstructured":"Chung SC, Sofat R, Acosta-Mena D, Taylor JA, Lambiase PD, Casas JP, et al. Atrial fibrillation epidemiology, disparity and healthcare contacts: a population-wide study of 5.6 million individuals. Lancet Reg Health Eur. 2021;7:100157.","journal-title":"Lancet Reg Health Eur"},{"issue":"9","key":"3491_CR28","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1093\/eurjhf\/hft064","volume":"15","author":"R Zarrinkoub","year":"2013","unstructured":"Zarrinkoub R, Wettermark B, W\u00e4ndell P, Mejhert M, Szulkin R, Ljunggren G, et al. The epidemiology of heart failure, based on data for 2.1 million inhabitants in Sweden. Eur J Heart Fail. 2013;15(9):995\u20131002.","journal-title":"Eur J Heart Fail"},{"key":"3491_CR29","doi-asserted-by":"publisher","first-page":"105019","DOI":"10.1016\/j.ijmedinf.2023.105019","volume":"172","author":"D Shamsutdinova","year":"2023","unstructured":"Shamsutdinova D, Das-Munshi J, Ashworth M, Roberts A, Stahl D. Predicting type 2 diabetes prevalence for people with severe mental illness in a multi-ethnic East London population. Int J Med Inf. 2023;172:105019.","journal-title":"Int J Med Inf"},{"issue":"3","key":"3491_CR30","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.jpsychores.2014.06.012","volume":"77","author":"P W\u00e4ndell","year":"2014","unstructured":"W\u00e4ndell P, Ljunggren G, Wahlstr\u00f6m L, Carlsson AC. Diabetes and psychiatric illness in the total population of Stockholm. J Psychosom Res. 2014;77(3):169\u201373.","journal-title":"J Psychosom Res"},{"issue":"2","key":"3491_CR31","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1093\/fampra\/cmaa056","volume":"38","author":"T Forslund","year":"2021","unstructured":"Forslund T, Carlsson AC, Ljunggren G, \u00c4rnl\u00f6v J, Wachtler C. Patterns of multimorbidity and pharmacotherapy: a total population cross-sectional study. Fam Pract. 2021;38(2):132\u201340.","journal-title":"Fam Pract"},{"issue":"46","key":"3491_CR32","doi-asserted-by":"publisher","first-page":"4831","DOI":"10.1093\/eurheartj\/ehad727","volume":"44","author":"FS van Royen","year":"2023","unstructured":"van Royen FS, Asselbergs FW, Alfonso F, Vardas P, van Smeden M. Five critical quality criteria for artificial intelligence-based prediction models. Eur Heart J. 2023;44(46):4831\u20134.","journal-title":"Eur Heart J"},{"issue":"23","key":"3491_CR33","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1161\/CIRCULATIONAHA.124.071176","volume":"150","author":"K Kemp Gudmundsdottir","year":"2024","unstructured":"Kemp Gudmundsdottir K, Svennberg E, Friberg L, Hygrell T, Frykman V, Al-Khalili F, et al. Randomized Invitation to Systematic NT-proBNP and ECG Screening in 75-Year-Olds to Detect Atrial Fibrillation: STROKESTOP II. Circulation. 2024;150(23):1837\u201346.","journal-title":"Circulation"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-026-03491-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03491-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03491-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:17:41Z","timestamp":1781648261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12911-026-03491-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3491"],"URL":"https:\/\/doi.org\/10.1186\/s12911-026-03491-4","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"7 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study adheres to the Helsinki declaration. All data was pseudonymized. The use of the data was approved by the Swedish Ethical Review Authority without patient consent (reference number 2021\u2009\u2212\u200901016 with amendments 2021-05735-02, 2022\u201306729, 2023-07166-0202 and 2024-05462-02). The need for consent to participate was waived by Institutional Review Board at Karolinska Institutet.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"There was no patient or public involvement in the design, conduct, reporting, interpretation, or dissemination of this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"126"}}