{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:44:40Z","timestamp":1776444280440,"version":"3.51.2"},"reference-count":34,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Max Planck Society"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>(1) In the present study, we used data comprising patient medical histories from a panel of primary care practices in Germany to predict post-COVID-19 conditions in patients after COVID-19 diagnosis and to evaluate the relevant factors associated with these conditions using machine learning methods. (2) Methods: Data retrieved from the IQVIATM Disease Analyzer database were used. Patients with at least one COVID-19 diagnosis between January 2020 and July 2022 were selected for inclusion in the study. Age, sex, and the complete history of diagnoses and prescription data before COVID-19 infection at the respective primary care practice were extracted for each patient. A gradient boosting classifier (LGBM) was deployed. The prepared design matrix was randomly divided into train (80%) and test data (20%). After optimizing the hyperparameters of the LGBM classifier by maximizing the F2 score, model performance was evaluated using several test metrics. We calculated SHAP values to evaluate the importance of the individual features, but more importantly, to evaluate the direction of influence of each feature in our dataset, i.e., whether it is positively or negatively associated with a diagnosis of long COVID. (3) Results: In both the train and test data sets, the model showed a high recall (sensitivity) of 81% and 72% and a high specificity of 80% and 80%; this was offset, however, by a moderate precision of 8% and 7% and an F2-score of 0.28 and 0.25. The most common predictive features identified using SHAP included COVID-19 variant, physician practice, age, distinct number of diagnoses and therapies, sick days ratio, sex, vaccination rate, somatoform disorders, migraine, back pain, asthma, malaise and fatigue, as well as cough preparations. (4) Conclusions: The present exploratory study describes an initial investigation of the prediction of potential features increasing the risk of developing long COVID after COVID-19 infection by using the patient history from electronic medical records before COVID-19 infection in primary care practices in Germany using machine learning. Notably, we identified several predictive features for the development of long COVID in patient demographics and their medical histories.<\/jats:p>","DOI":"10.3390\/jcm12103511","type":"journal-article","created":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T01:58:06Z","timestamp":1684288686000},"page":"3511","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Predictive Attributes for Developing Long COVID\u2014A Study Using Machine Learning and Real-World Data from Primary Care Physicians in Germany"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4154-7451","authenticated-orcid":false,"given":"Roman","family":"Kessler","sequence":"first","affiliation":[{"name":"Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos","family":"Philipp","sequence":"additional","affiliation":[{"name":"IQVIA, 60549 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joanna","family":"Wilfer","sequence":"additional","affiliation":[{"name":"IQVIA, 60549 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-7227","authenticated-orcid":false,"given":"Karel","family":"Kostev","sequence":"additional","affiliation":[{"name":"IQVIA, 60549 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,17]]},"reference":[{"key":"ref_1","unstructured":"(2023, February 25). WHO Coronavirus (COVID-19) Dashboard. Available online: https:\/\/covid19.who.int\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1093\/infdis\/jiac136","article-title":"Global Prevalence of Post-Coronavirus Disease 2019 (COVID-19) Condition or Long COVID: A Meta-Analysis and Systematic Review","volume":"226","author":"Chen","year":"2022","journal-title":"J. Infect. Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e97","DOI":"10.1016\/j.jinf.2023.02.015","article-title":"Prevalence and clinical features of long COVID from omicron infection in children and adults","volume":"86","author":"Chen","year":"2023","journal-title":"J. Infect."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"18126","DOI":"10.1038\/s41598-022-22547-9","article-title":"A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study","volume":"12","author":"Caracena","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1007\/s12065-022-00704-3","article-title":"Vaccine hesitancy in the post-vaccination COVID-19 era: A machine learning and statistical analysis driven study","volume":"16","author":"Gupta","year":"2023","journal-title":"Evol. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3246","DOI":"10.1038\/s41598-021-81844-x","article-title":"Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients","volume":"11","author":"Petersen","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1038\/s41591-021-01292-y","article-title":"Attributes and Predictors of Long COVID","volume":"27","author":"Sudre","year":"2021","journal-title":"Nat. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e532","DOI":"10.1016\/S2589-7500(22)00048-6","article-title":"Identifying who has long COVID in the USA: A machine learning approach using N3C data","volume":"4","author":"Pfaff","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"459","DOI":"10.5414\/CP203320","article-title":"Basic characteristics and representativeness of the German Disease Analyzer database","volume":"56","author":"Rathmann","year":"2018","journal-title":"Int. J. Clin. Pharmacol. Ther."},{"key":"ref_10","unstructured":"Federal Institute for Drugs and Medical Devices (BfArM) (2022, October 12). Internationale statistische Klassifikation der Krankheiten und verwandter Gesundheitsprobleme, 10. Revision, German Modification, Version 2023. Available online: https:\/\/www.dimdi.de\/static\/de\/klassifikationen\/icd\/icd-10-gm\/kode-suche\/htmlgm2023\/#IV."},{"key":"ref_11","unstructured":"(2022, October 12). EphMRA. Available online: https:\/\/www.ephmra.org\/."},{"key":"ref_12","unstructured":"Robert Koch Institute (2022, October 12). Anzahl und Anteile von VOC und VOI in Deutschland. Available online: https:\/\/www.rki.de\/DE\/Content\/InfAZ\/N\/Neuartiges_Coronavirus\/Daten\/VOC_VOI_Tabelle.xlsx."},{"key":"ref_13","unstructured":"(2022, June 20). Impfdashboard Deutschland. Available online: https:\/\/impfdashboard.de\/static\/data\/germany_vaccinations_timeseries_v3.tsv."},{"key":"ref_14","unstructured":"Guyon, I., von Luxburg, U., Bengio Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_15","unstructured":"Grinsztajn, L., Oyallon, E., and Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on typical tabular data?. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sch\u00f6ler, D., Kostev, K., Peters, M., Zamfir, C., Wolk, A., Roderburg, C., and Loosen, S.H. (2022). Machine Learning Can Predict the Probability of Biologic Therapy in Patients with Inflammatory Bowel Disease. J. Clin. Med., 11.","DOI":"10.3390\/jcm11154586"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5472","DOI":"10.1038\/s41598-022-09521-1","article-title":"Human activity recognition of children with wearable devices using LightGBM machine learning","volume":"12","author":"Csizmadia","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rahman, S., Irfan, M., Raza, M., Moyeezullah Ghori, K., Yaqoob, S., and Awais, M. (2020). Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17031082"},{"key":"ref_19","unstructured":"Sasaki, Y. (2023, February 26). The Truth of the F-Measure. Available online: https:\/\/www.cs.odu.edu\/mukka\/cs795sum09dm\/Lecturenotes\/Day3\/F-measure-YS-26Oct07.pdf."},{"key":"ref_20","unstructured":"Lundberg, S., and Lee, S. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA. Available online: https:\/\/papers.nips.cc\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf."},{"key":"ref_21","unstructured":"O\u2019Sullivan, C. (2023, February 26). SHAP for Categorical Features. Available online: https:\/\/towardsdatascience.com\/shap-for-categorical-features-7c63e6a554ea."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e25884","DOI":"10.2196\/25884","article-title":"Machine Learning Approach to Predicting COVID-19 Disease Severity Based on Clinical Blood Test Data: Statistical Analysis and Model Development","volume":"9","author":"Aktar","year":"2021","journal-title":"JMIR Med. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Du, M., Ma, Y., Deng, J., Liu, M., and Liu, J. (2022). Comparison of Long COVID-19 Caused by Different SARS-CoV-2 Strains: A Systematic Review and Meta-Analysis. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph192316010"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"ofac333","DOI":"10.1093\/ofid\/ofac333","article-title":"Prevalence of and Factors Associated with Post-Coronavirus Disease 2019 (COVID-19) Condition in the 12 Months After the Diagnosis of COVID-19 in Adults Followed in General Practices in Germany","volume":"9","author":"Kostev","year":"2022","journal-title":"Open Forum Infect. Dis."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1016\/j.cmi.2021.05.033","article-title":"Post-COVID-19 symptoms 6 months after acute infection among hospitalized and non-hospitalized patients","volume":"27","author":"Peghin","year":"2021","journal-title":"Clin. Microbiol. Infect."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-De-Las-Pe\u00f1as, C., Mart\u00edn-Guerrero, J.D., Pellicer-Valero, \u00d3.J., Navarro-Pardo, E., G\u00f3mez-Mayordomo, V., Cuadrado, M.L., Arias-Naval\u00f3n, J.A., Cigar\u00e1n-M\u00e9ndez, M., Hern\u00e1ndez-Barrera, V., and Arendt-Nielsen, L. (2022). Female Sex Is a Risk Factor Associated with Long-Term Post-COVID Related-Symptoms but Not with COVID-19 Symptoms: The LONG-COVID-EXP-CM Multicenter Study. J. Clin. Med., 11.","DOI":"10.3390\/jcm11020413"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1038\/s41467-022-30836-0","article-title":"Long COVID burden and risk factors in 10 UK longitudinal studies and electronic health records","volume":"13","author":"Thompson","year":"2022","journal-title":"Nat. Commun."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1080\/23744235.2021.1924397","article-title":"Long COVID or post-COVID-19 syndrome: Putative pathophysiology, risk factors, and treatments","volume":"53","author":"Yong","year":"2021","journal-title":"Infect. Dis."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tsampasian, V., Elghazaly, H., Chattopadhyay, R., Debski, M., Naing, T.K.P., Garg, P., Clark, A., Ntatsaki, E., and Vassiliou, V.S. (2023). Risk Factors Associated with Post\u2212COVID-19 Condition: A Systematic Review and Meta-analysis. JAMA Intern. Med.","DOI":"10.1001\/jamainternmed.2023.0750"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.bbi.2021.07.018","article-title":"Psychiatric and neuropsychiatric sequelae of COVID-19\u2014A systematic review","volume":"97","author":"Schou","year":"2021","journal-title":"Brain Behav. Immun."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1036556","DOI":"10.3389\/fmed.2022.1036556","article-title":"Lifestyle, course of COVID-19, and risk of Long-COVID in non-hospitalized patients","volume":"9","author":"Chudzik","year":"2022","journal-title":"Front. Med."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"ckac129.137","DOI":"10.1093\/eurpub\/ckac129.137","article-title":"How multimorbidity and socio-economic factors affect Long COVID: Evidence from European Countries","volume":"32","author":"Wilk","year":"2022","journal-title":"Eur. J. Public Health"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"38","DOI":"10.3399\/bjgp22X718229","article-title":"Impact of COVID-19 on individuals with multimorbidity in primary care","volume":"72","author":"Hayhoe","year":"2021","journal-title":"Br. J. Gen. Pract."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"101624","DOI":"10.1016\/j.eclinm.2022.101624","article-title":"Impact of COVID-19 vaccination on the risk of developing long-COVID and on existing long-COVID symptoms: A systematic review","volume":"53","author":"Notarte","year":"2022","journal-title":"eClinicalMedicine"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/10\/3511\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:36:33Z","timestamp":1760124993000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/10\/3511"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,17]]},"references-count":34,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["jcm12103511"],"URL":"https:\/\/doi.org\/10.3390\/jcm12103511","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,17]]}}}