{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T01:50:25Z","timestamp":1768009825652,"version":"3.49.0"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Fonden","doi-asserted-by":"publisher","award":["NNF18OC0033978"],"award-info":[{"award-number":["NNF18OC0033978"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Chronic disease monitoring programs often adopt a one-size-fits-all approach that does not consider variation in need, potentially leading to excessive or insufficient support for patients at different risk levels. Machine learning (ML) developments offer new opportunities for personalised medicine in clinical practice.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Objective<\/jats:title>\n<jats:p>To demonstrate the potential of ML to guide resource allocation and tailored disease management, this study aims to predict the optimal testing interval for monitoring blood glucose (HbA1c) for patients with Type 2 Diabetes (T2D). We examine fairness across income and education levels and evaluate the risk of false-positives and false-negatives.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Data<\/jats:title>\n<jats:p>Danish administrative registers are linked with national clinical databases. Our population consists of all T2D patients from 2015-2018, a sample of more than 57,000. Data contains patient-level clinical measures, healthcare utilisation, medicine, and socio-demographics.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We classify HbA1c test intervals into four categories (3, 6, 9, and 12 months) using three classification algorithms: logistic regression, random forest, and extreme gradient boosting (XGBoost). Feature importance is assessed with SHAP model explanations on the best-performing model, which was XGBoost. A training set comprising 80% of the data is used to predict optimal test intervals, with 20% reserved for testing. Cross-validation is employed to enhance the model\u2019s reliability and reduce overfitting. Model performance is evaluated using ROC-AUC, and optimal intervals are determined based on a \u201ctime-to-next-positive-test\u201d concept, with different durations associated with specific intervals.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Results<\/jats:title>\n<jats:p>The model exhibits varying predictive accuracy, with AUC scores ranging from 0.53 to 0.89 across different test intervals. We find significant potential to free resources by prolonging the test interval for well-controlled patients. The fairness metric suggests models perform well in terms of equality. There is a sizeable risk of false negatives (predicting longer intervals than optimal), which requires attention.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec006\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>We demonstrate the potential to use ML in personalised diabetes management by assisting physicians in categorising patients by testing frequencies. Clinical validation on diverse patient populations is needed to assess the model\u2019s performance in real-world settings.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0317722","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:23:18Z","timestamp":1739470998000},"page":"e0317722","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimising test intervals for individuals with type 2 diabetes: A machine learning approach"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-4625","authenticated-orcid":true,"given":"Sasja Maria","family":"Pedersen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4649-3109","authenticated-orcid":true,"given":"Nicolai","family":"Damslund","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9554-374X","authenticated-orcid":true,"given":"Trine","family":"Kj\u00e6r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kim Rose","family":"Olsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"issue":"7","key":"pone.0317722.ref001","doi-asserted-by":"crossref","first-page":"e18228","DOI":"10.2196\/18228","article-title":"Artificial Intelligence in Health Care: Bibliometric Analysis","volume":"22","author":"Y Guo","year":"2020","journal-title":"J Med Internet Res"},{"issue":"7","key":"pone.0317722.ref002","doi-asserted-by":"crossref","first-page":"e0271723","DOI":"10.1371\/journal.pone.0271723","article-title":"An evolutionary machine learning algorithm for cardiovascular disease risk prediction","volume":"17","author":"M Ordikhani","year":"2022","journal-title":"PLOS ONE"},{"issue":"11","key":"pone.0317722.ref003","doi-asserted-by":"crossref","first-page":"e0224582","DOI":"10.1371\/journal.pone.0224582","article-title":"Predicting atrial fibrillation in primary care using machine learning","volume":"14","author":"NR Hill","year":"2019","journal-title":"PLOS ONE"},{"issue":"11","key":"pone.0317722.ref004","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","article-title":"Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data","volume":"178","author":"MA Gianfrancesco","year":"2018","journal-title":"JAMA Internal Medicine"},{"issue":"5","key":"pone.0317722.ref005","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1257\/aer.p20171084","article-title":"Does Machine Learning Automate Moral Hazard and Error?","volume":"107","author":"S Mullainathan","year":"2017","journal-title":"Am Econ Rev"},{"key":"pone.0317722.ref006","unstructured":"Kleinberg J, Mullainathan S, Raghavan M. Inherent Trade-Offs in the Fair Determination of Risk Scores. 2016."},{"key":"pone.0317722.ref007","doi-asserted-by":"crossref","unstructured":"Ahmad MA, Eckert C, Teredesai A. Interpretable Machine Learning in Healthcare. In: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. BCB\u201918. ACM; 2018. p. 559\u2013560. Available from: http:\/\/dx.doi.org\/10.1145\/3233547.3233667.","DOI":"10.1145\/3233547.3233667"},{"key":"pone.0317722.ref008","unstructured":"Tonekaboni S, Joshi S, McCradden MD, Goldenberg A. What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use; 2019. Available from: https:\/\/arxiv.org\/abs\/1905.05134."},{"issue":"8","key":"pone.0317722.ref009","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1038\/s41591-021-01461-z","article-title":"AI in medicine must be explainable","volume":"27","author":"S Kundu","year":"2021","journal-title":"Nature Medicine"},{"key":"pone.0317722.ref010","article-title":"Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?","author":"MA Ribers","year":"2019","journal-title":"SSRN Electronic Journal"},{"issue":"5","key":"pone.0317722.ref011","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1257\/aer.p20151023","article-title":"Prediction Policy Problems","volume":"105","author":"J Kleinberg","year":"2015","journal-title":"Am Econ Rev"},{"issue":"9","key":"pone.0317722.ref012","doi-asserted-by":"crossref","first-page":"e0291961","DOI":"10.1371\/journal.pone.0291961","article-title":"An interpretable machine learning framework for diagnosis and prognosis of COVID-19","volume":"18","author":"Y Fan","year":"2023","journal-title":"PLOS ONE"},{"issue":"4","key":"pone.0317722.ref013","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1056\/NEJMp1006304","article-title":"The path to personalized medicine","volume":"363","author":"MA Hamburg","year":"2010","journal-title":"N Engl J Med"},{"issue":"14","key":"pone.0317722.ref014","doi-asserted-by":"crossref","first-page":"7346","DOI":"10.3390\/ijerph18147346","article-title":"Predicting Type 2 Diabetes Using Logistic Regression and Machine Learning Approaches","volume":"18","author":"RD Joshi","year":"2021","journal-title":"International Journal of Environmental Research and Public Health"},{"issue":"10","key":"pone.0317722.ref015","doi-asserted-by":"crossref","first-page":"e0163942","DOI":"10.1371\/journal.pone.0163942","article-title":"Prediction of Incident Diabetes in the Jackson Heart Study Using High-Dimensional Machine Learning","volume":"11","author":"R Casanova","year":"2016","journal-title":"PLOS ONE"},{"issue":"11","key":"pone.0317722.ref016","doi-asserted-by":"crossref","first-page":"e0207096","DOI":"10.1371\/journal.pone.0207096","article-title":"Patient clusters based on HbA1c trajectories: A step toward individualized medicine in type 2 diabetes","volume":"13","author":"T Karpati","year":"2018","journal-title":"PLOS ONE"},{"issue":"2","key":"pone.0317722.ref017","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1177\/19322968211056917","article-title":"Evaluation of Machine Learning Methods Developed for Prediction of Diabetes Complications: A Systematic Review","volume":"17","author":"KR Tan","year":"2021","journal-title":"Journal of Diabetes Science and Technology"},{"issue":"1","key":"pone.0317722.ref018","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1186\/s13098-021-00717-5","article-title":"HbA1C variability among type 2 diabetic patients: a retrospective cohort study","volume":"13","author":"D Akselrod","year":"2021","journal-title":"Diabetol Metab Syndr"},{"issue":"5","key":"pone.0317722.ref019","doi-asserted-by":"crossref","first-page":"e25237","DOI":"10.2196\/25237","article-title":"Improving Current Glycated Hemoglobin Prediction in Adults: Use of Machine Learning Algorithms With Electronic Health Records","volume":"9","author":"Z Alhassan","year":"2021","journal-title":"JMIR Med Inform"},{"key":"pone.0317722.ref020","unstructured":"Lundberg S, Lee SI. A Unified Approach to Interpreting Model Predictions; 2017. Available from: https:\/\/arxiv.org\/abs\/1705.07874."},{"key":"pone.0317722.ref021","unstructured":"Sundhedsdatastyrelsen. Register of Selected Chronic Diseases; 2022."},{"key":"pone.0317722.ref022","unstructured":"Diabetes dk. Langtidsblodsukker-hba1c; 2022. Available from: https:\/\/diabetes.dk\/diabetes-2\/fakta-om-type-2\/blodsukker-og-maling\/langtidsblodsukker-hba1c."},{"issue":"7 Suppl","key":"pone.0317722.ref023","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1177\/1403494811399171","article-title":"Database on Danish population-based registers for public health and welfare research","volume":"39","author":"C Sortso","year":"2011","journal-title":"Scand J Public Health"},{"issue":"7 Suppl","key":"pone.0317722.ref024","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1177\/1403494811405098","article-title":"Danish registers on personal income and transfer payments","volume":"39","author":"M Baadsgaard","year":"2011","journal-title":"Scand J Public Health"},{"issue":"7","key":"pone.0317722.ref025","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph18073390","article-title":"Hemoglobin A1c Levels Associated with Age and Gender in Taiwanese Adults without Prior Diagnosis with Diabetes","volume":"18","author":"SH Huang","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"7-suppl","key":"pone.0317722.ref026","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1177\/1403494810394718","article-title":"The Danish National Health Service Register","volume":"39","author":"J Sahl Andersen","year":"2011","journal-title":"Scandinavian Journal of Public Health"},{"key":"pone.0317722.ref027","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. 2016.","DOI":"10.1145\/2939672.2939785"},{"issue":"5","key":"pone.0317722.ref028","doi-asserted-by":"crossref","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"The Annals of Statistics"},{"issue":"1","key":"pone.0317722.ref029","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-020-00349-y","article-title":"Boosting methods for multi-class imbalanced data classification: an experimental review","volume":"7","author":"J Tanha","year":"2020","journal-title":"Journal of Big Data"},{"key":"pone.0317722.ref030","doi-asserted-by":"crossref","first-page":"101822","DOI":"10.1016\/j.ecoinf.2022.101822","article-title":"An approach to multi-class imbalanced problem in ecology using machine learning","volume":"71","author":"B Sidumo","year":"2022","journal-title":"Ecological Informatics"},{"issue":"1","key":"pone.0317722.ref031","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1146\/annurev-publhealth-040119-094437","article-title":"Machine Learning in Epidemiology and Health Outcomes Research","volume":"41","author":"TL Wiemken","year":"2020","journal-title":"Annual Review of Public Health"},{"issue":"4","key":"pone.0317722.ref032","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1002\/sam.11583","article-title":"Optimal ratio for data splitting","volume":"15","author":"VR Joseph","year":"2022","journal-title":"Statistical Analysis and Data Mining: The ASA Data Science Journal"},{"key":"pone.0317722.ref033","doi-asserted-by":"crossref","unstructured":"Wang W, Li L, Gu H, Chen Y, Zhen Y, Dong Z. Random forest-based prediction of acute respiratory distress syndrome in patients undergoing cardiac surgery. 2022.","DOI":"10.22541\/au.165871983.37552803\/v1"},{"key":"pone.0317722.ref034","doi-asserted-by":"crossref","first-page":"11759","DOI":"10.3168\/jds.2021-20413","article-title":"A data-driven prediction of lifetime resilience of dairy cows using commercial sensor data collected during first lactation","volume":"104","author":"W Ouweltjes","year":"2021","journal-title":"Journal of Dairy Science"},{"key":"pone.0317722.ref035","doi-asserted-by":"crossref","DOI":"10.1186\/bcr2633","article-title":"Benefits of biomarker selection and clinico-pathological covariate inclusion in breast cancer prognostic models","volume":"12","author":"F Parisi","year":"2010","journal-title":"Breast Cancer Research"},{"key":"pone.0317722.ref036","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.stamet.2005.02.003","article-title":"Asymptotics of cross-validated risk estimation in estimator selection and performance assessment","volume":"2","author":"S Dudoit","year":"2005","journal-title":"Statistical Methodology"},{"key":"pone.0317722.ref037","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.3390\/app9163322","article-title":"Special issue on using machine learning algorithms in the prediction of kyphosis disease: a comparative study","volume":"9","author":"S Dankwa","year":"2019","journal-title":"Applied Sciences"},{"key":"pone.0317722.ref038","doi-asserted-by":"crossref","unstructured":"Ting KM. Confusion Matrix. In: Encyclopedia of Machine Learning. Springer US; 2011. p. 209\u2013209. Available from: https:\/\/doi.org\/10.1007\/978-0-387-30164-8_157.","DOI":"10.1007\/978-0-387-30164-8_157"},{"key":"pone.0317722.ref039","doi-asserted-by":"crossref","unstructured":"Shapley LS. In: 17. A Value for n-Person Games. Princeton University Press; 1953. p. 307\u2013318. Available from: http:\/\/dx.doi.org\/10.1515\/9781400881970-018.","DOI":"10.1515\/9781400881970-018"},{"issue":"8","key":"pone.0317722.ref040","doi-asserted-by":"crossref","first-page":"e0289613","DOI":"10.1371\/journal.pone.0289613","article-title":"Predicting the risk of hypertension using machine learning algorithms: A cross sectional study in Ethiopia","volume":"18","author":"MM Islam","year":"2023","journal-title":"PLOS ONE"},{"issue":"12","key":"pone.0317722.ref041","doi-asserted-by":"crossref","first-page":"e0227007","DOI":"10.1371\/journal.pone.0227007","article-title":"Health literacy as a mediator of the relationship between socioeconomic status and health: A cross-sectional study in a population-based sample in Florence","volume":"14","author":"V Lastrucci","year":"2019","journal-title":"PLOS ONE"},{"key":"pone.0317722.ref042","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.socscimed.2014.12.028","article-title":"Inequities in health care utilization by people aged 50+: Evidence from 12 European countries","volume":"126","author":"M Terraneo","year":"2015","journal-title":"Social Science & Medicine"},{"issue":"1","key":"pone.0317722.ref043","doi-asserted-by":"crossref","first-page":"96","DOI":"10.12927\/hcpol.2007.19177","article-title":"Education Level, Income Level and Mental Health Services Use in Canada: Associations and Policy Implications","volume":"3","author":"L Steele","year":"2007","journal-title":"Healthcare Policy | Politiques de Sant\u00e9"},{"issue":"1","key":"pone.0317722.ref044","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/S0167-6296(96)00532-2","article-title":"Income-related inequalities in health: some international comparisons","volume":"16","author":"E Van Doorslaer","year":"1997","journal-title":"Journal of Health Economics"},{"key":"pone.0317722.ref045","unstructured":"Pessach D, Shmueli E. Algorithmic Fairness. 2020."},{"key":"pone.0317722.ref046","unstructured":"Denis C, Elie R, Hebiri M, Hu F. Fairness guarantee in multi-class classification; 2021. Available from: https:\/\/arxiv.org\/abs\/2109.13642."},{"issue":"1","key":"pone.0317722.ref047","doi-asserted-by":"crossref","DOI":"10.1007\/s44176-022-00006-z","article-title":"A brief review on algorithmic fairness","volume":"1","author":"X Wang","year":"2022","journal-title":"Management System Engineering"},{"key":"pone.0317722.ref048","unstructured":"Baniecki H, Kretowicz W, Piatyszek P, Wisniewski J, Biecek P. dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python. 2020."},{"key":"pone.0317722.ref049","doi-asserted-by":"crossref","unstructured":"Kearns M, Neel S, Roth A, Wu ZS. An Empirical Study of Rich Subgroup Fairness for Machine Learning. In: Proceedings of the Conference on Fairness, Accountability, and Transparency. FAT*\u201919. ACM; 2019. Available from: http:\/\/dx.doi.org\/10.1145\/3287560.3287592.","DOI":"10.1145\/3287560.3287592"},{"key":"pone.0317722.ref050","unstructured":"Ascensia. HbA1c-monitoring; 2022. Available from: https:\/\/www.diabetes.ascensia.co.uk\/about-diabetes\/HbA1c-monitoring\/."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:23:38Z","timestamp":1739471018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317722"}},"subtitle":[],"editor":[{"given":"Jacopo","family":"Sabbatinelli","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":50,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0317722","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]}}}