{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T21:01:54Z","timestamp":1791925314749,"version":"4.3.4"},"reference-count":43,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007446","name":"Deanship of Scientific Research","doi-asserted-by":"publisher","award":["R.G.P.2\/21\/46"],"award-info":[{"award-number":["R.G.P.2\/21\/46"]}],"id":[{"id":"10.13039\/501100007446","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: Diabetes mellitus represents one of the most prevalent chronic metabolic disorders worldwide, necessitating precise insulin dose management to prevent both acute and long-term complications. The optimization of insulin dosing remains a significant clinical challenge, as inappropriate dosing can lead to hypoglycemia or hyperglycemia, each carrying substantial morbidity risks. Machine learning approaches have emerged as promising tools for developing clinical decision support systems; however, their practical implementation requires both high predictive accuracy and model interpretability. This study aimed to develop and evaluate an explainable machine learning framework for predicting insulin dose adjustments in diabetic patients. We sought to compare multiple ensemble learning approaches and identify the optimal model configuration that balances predictive performance with clinical interpretability through comprehensive SHAP and LIME analyses. Materials and Methods: A comprehensive dataset comprising 10,000 patient records with 12 clinical and demographic features was utilized. We implemented and compared nine machine learning models, including gradient boosting variants (XGBoost, LightGBM, CatBoost, GradientBoosting), AdaBoost, and four ensemble strategies (Voting, Stacking, Blending, and Meta-Learning). Model interpretability was achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analyses. Performance was evaluated using accuracy, weighted F1-score, area under the receiver operating characteristic curve (AUC-ROC), precision-recall AUC (PR-AUC), sensitivity, specificity, and cross-entropy loss. Results: The Meta-Learning Ensemble achieved superior performance across all evaluation metrics, attaining an accuracy of 81.35%, weighted F1-score of 0.8121, macro-averaged AUC-ROC of 0.9637, and PR-AUC of 0.9317. The model demonstrated exceptional sensitivity (86.61%) and specificity (91.79%), with particularly high performance in detecting dose reduction requirements (100% sensitivity for the \u2018down\u2019 class). SHAP analysis revealed insulin sensitivity, previous medications, sleep hours, weight, and body mass index as the most influential predictors across different insulin adjustment categories. The meta-model feature importance analysis indicated that LightGBM probability estimates contributed most significantly to the ensemble predictions. Conclusions: The proposed explainable Meta-Learning Ensemble framework demonstrates robust predictive capability for insulin dose adjustment recommendations while maintaining clinical interpretability. The integration of SHAP-based explanations facilitates clinician understanding of model predictions, supporting transparent and informed decision-making in diabetes management. This approach represents a significant advancement toward the clinical implementation of artificial intelligence in personalized insulin therapy.<\/jats:p>","DOI":"10.3390\/medicina62030502","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T11:06:52Z","timestamp":1773054412000},"page":"502","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable Meta-Learning Ensemble Framework for Predicting Insulin Dose Adjustments in Diabetic Patients: A Comparative Machine Learning Approach with SHAP-Based Clinical Interpretability"],"prefix":"10.3390","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5436-8164","authenticated-orcid":false,"given":"Emek","family":"Guldogan","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, Malatya 44280, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-979X","authenticated-orcid":false,"given":"Burak","family":"Yagin","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, Malatya 44280, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4870-3015","authenticated-orcid":false,"given":"Hasan","family":"Ucuzal","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, Malatya 44280, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7556-958X","authenticated-orcid":false,"given":"Abdulmohsen","family":"Algarni","sequence":"additional","affiliation":[{"name":"Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5795-9966","authenticated-orcid":false,"given":"Fahaid","family":"Al-Hashem","sequence":"additional","affiliation":[{"name":"Department of Physiology, College of Medicine, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5735-3825","authenticated-orcid":false,"given":"Mohammadreza","family":"Aghaei","sequence":"additional","affiliation":[{"name":"Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), 6009 Alesund, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109119","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S11","DOI":"10.2337\/dc11-S011","article-title":"Standards of medical care in diabetes\u20142011","volume":"34","author":"Association","year":"2011","journal-title":"Diabetes Care"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Al-Hashem, F., Ahmad, I., Ahmad, F., and Alkhateeb, A. (2024). Pilot-study to explore metabolic signature of type 2 diabetes: A pipeline of tree-based machine learning and bioinformatics techniques for biomarkers discovery. Nutrients, 16.","DOI":"10.3390\/nu16101537"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Arslan, A.K., Yagin, F.H., Algarni, A., Karaaslan, E., Al-Hashem, F., and Ardig\u00f2, L.P. (2024). Enhancing type 2 diabetes mellitus prediction by integrating metabolomics and tree-based boosting approaches. Front. Endocrinol., 15.","DOI":"10.3389\/fendo.2024.1444282"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rehman, N.U., Contreras, I., Beneyto, A., and Vehi, J. (2025). Explainable cluster-based learning for prediction of postprandial glycemic events and insulin dose optimization in type 1 diabetes. PLoS Digit. Health, 4.","DOI":"10.1371\/journal.pdig.0000996"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1515\/jpem-2023-0554","article-title":"Artificial intelligence in paediatric endocrinology: Conflict or cooperation","volume":"37","author":"Dimitri","year":"2024","journal-title":"J. Pediatr. Endocrinol. Metab."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e3093","DOI":"10.1210\/clinem\/dgae863","article-title":"Prediction of insulin requirements by explainable machine learning for individuals with type 1 diabetes","volume":"110","author":"Yoshimura","year":"2025","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mohebbi, A., Kjoller, N.-K., Johansen, A.R., Bengtsson, H., Jensen, M.L., Stallknecht, B.M., and Morup, M. (2025, January 14\u201318). Predicting Treatment Outcome of Patients with Type 2 Diabetes on Once-Daily Basal Insulin Injections using Machine Learning. Proceedings of the 2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Copenhagen, Denmark.","DOI":"10.1109\/EMBC58623.2025.11253142"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e1857","DOI":"10.7717\/peerj-cs.1857","article-title":"Development of an expert system for the classification of myalgic encephalomyelitis\/chronic fatigue syndrome","volume":"10","author":"Yagin","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., El Shawi, R., Algarni, A., Colak, C., Al-Hashem, F., and Ardig\u00f2, L.P. (2024). Metabolomics Biomarker Discovery to Optimize Hepatocellular Carcinoma Diagnosis: Methodology Integrating AutoML and Explainable Artificial Intelligence. Diagnostics, 14.","DOI":"10.3390\/diagnostics14182049"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1049\/htl2.12039","article-title":"Diabetes prediction using machine learning and explainable AI techniques","volume":"10","author":"Tasin","year":"2023","journal-title":"Healthc. Technol. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Tominaga, H., Hamaguchi, M., Hamaguchi, Y., Yashiki, R., Yamaguchi, A., Arai, T., Yamazaki, M., Kitagawa, N., Hashimoto, Y., and Okada, H. (2025). Prediction of Postprandial Blood Glucose Variability Using Machine Learning in Frequent Insulin Injection Therapy with a Simplified Carbohydrate Counting Model. Nutrients, 17.","DOI":"10.3390\/nu17243832"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1038\/s41598-025-31234-4","article-title":"An ethnic-sensitive hybrid framework for T2D prediction with explainable AI and weighted ensembles","volume":"16","author":"Abnoosian","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"43104","DOI":"10.1038\/s41598-025-26583-z","article-title":"SMENN-hybrid: An efficient technique combining the synthetic minority oversampling technique with ensemble learning for diabetes prediction","volume":"15","author":"Houssein","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Harumy, H.F., Hardi, S.M., and Al Banna, M.F. (2024). EarlyStage diabetes risk detection using Comparison of xgboost, lightgbm, and catboost algorithms. Proceedings of the International Conference on Advanced Information Networking and Applications, Springer.","DOI":"10.1007\/978-3-031-57931-8_2"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jain, E., and Singh, A. (2024, January 15\u201316). Optimizing gradient boosting algorithms for obesity risk prediction: A comparative analysis of xgboost, lightgbm, and catboost models. Proceedings of the 2024 International Conference on Cybernation and Computation (CYBERCOM), Dehradun, India.","DOI":"10.1109\/CYBERCOM63683.2024.10803186"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jaiswal, S., and Gupta, P. (2022, January 8). Ensemble approach: XGBoost, CATBoost, and LightGBM for diabetes mellitus risk prediction. Proceedings of the 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India.","DOI":"10.1109\/ICCSEA54677.2022.9936130"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Aziz, N., Akhir, E.A.P., Aziz, I.A., Jaafar, J., Hasan, M.H., and Abas, A.N.C. (2020, January 8\u20139). A study on gradient boosting algorithms for development of AI monitoring and prediction systems. Proceedings of the 2020 International conference on computational intelligence (ICCI), Bandar Seri Iskandar, Malaysia.","DOI":"10.1109\/ICCI51257.2020.9247843"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 22\u201326). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_20","first-page":"1","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e70621","DOI":"10.2196\/70621","article-title":"Optimizing Feature Selection and Machine Learning Algorithms for Early Detection of Prediabetes Risk: Comparative Study","volume":"6","author":"Almadhoun","year":"2025","journal-title":"JMIR Bioinform. Biotechnol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21501319251400546","DOI":"10.1177\/21501319251400546","article-title":"Exploring Explainable Machine Learning for Predicting and Interpreting Self-Reported Diabetes among Tennessee Adults: Insights from the 2023 Behavioral Risk Factor Surveillance System (BRFSS)","volume":"16","author":"Muhammad","year":"2025","journal-title":"J. Prim. Care Community Health"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Arslan, A.K., Yagin, F.H., Algarni, A., Al-Hashem, F., and Ardig\u00f2, L.P. (2024). Combining the strengths of the explainable boosting machine and metabolomics approaches for biomarker discovery in acute myocardial infarction. Diagnostics, 14.","DOI":"10.3390\/diagnostics14131353"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Colak, C., Algarni, A., Gormez, Y., Guldogan, E., and Ardig\u00f2, L.P. (2024). Hybrid explainable artificial intelligence models for targeted metabolomics analysis of diabetic retinopathy. Diagnostics, 14.","DOI":"10.3390\/diagnostics14131364"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1038\/s41598-025-31562-5","article-title":"Predicting and classifying type 2 diabetes using a transparent ensemble model combining random forest, k-nearest neighbor, and neural networks","volume":"16","author":"Zaferani","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Slack, D., Hilgard, S., Jia, E., Singh, S., and Lakkaraju, H. (2020, January 7\u20139). Fooling lime and shap: Adversarial attacks on post hoc explanation methods. Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, New York, NY, USA.","DOI":"10.1145\/3375627.3375830"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, X., Hu, H., Zhou, X., Hu, N., Liu, W., Zhang, Y., Mao, P., Xu, L., and Zhu, Q. (2025). Development and validation of a risk prediction model for painful diabetic peripheral neuropathy in type 2 diabetes mellitus: A multicenter retrospective study. Front. Endocrinol., 16.","DOI":"10.3389\/fendo.2025.1651493"},{"key":"ref_28","unstructured":"Burns, R. (2025, December 03). Insulin Dosage. Kaggle Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/robyburns\/insulin-dosage."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1177\/1747016120988767","article-title":"Ethical approval: None sought. How discourse analysts report ethical issues around publicly available online data","volume":"17","author":"Stommel","year":"2021","journal-title":"Res. Ethics"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1002\/bjs.9736","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement","volume":"102","author":"Collins","year":"2015","journal-title":"J. Br. Surg."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis in machine-learning-based science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"key":"ref_32","first-page":"1","article-title":"CatBoost: Unbiased boosting with categorical features","volume":"31","author":"Prokhorenkova","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1023\/A:1018046112532","article-title":"Stacked regressions","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","article-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy","volume":"51","author":"Kuncheva","year":"2003","journal-title":"Mach. Learn."},{"key":"ref_35","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3626","DOI":"10.1038\/s41598-025-33645-9","article-title":"Clinical predictive fusion network for accurate disease prediction in patient cohorts","volume":"16","author":"Zeyauddin","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Li, Q., Tang, Y., Yang, X., Song, T., Wei, G., Gu, R., Pan, Y., Wang, J., Li, Y., and Wei, L. (2025). Development and external validation of a non-invasive early gestational diabetes mellitus prediction model integrating social network variables: A machine learning-based prospective cohort study. BMC Pregnancy Childbirth, 25.","DOI":"10.1186\/s12884-025-08500-4"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e66200","DOI":"10.2196\/66200","article-title":"A Responsible Framework for Assessing, Selecting, and Explaining Machine Learning Models in Cardiovascular Disease Outcomes Among People With Type 2 Diabetes: Methodology and Validation Study","volume":"13","author":"Yang","year":"2025","journal-title":"JMIR Med. Inform."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e153728","DOI":"10.3897\/folmed.67.e153728","article-title":"AI and telemedicine in management of diabetes","volume":"67","author":"Petrov","year":"2025","journal-title":"Folia Medica"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kibria, H.B., Nahiduzzaman, M., Goni, M.O.F., Ahsan, M., and Haider, J. (2022). An ensemble approach for the prediction of diabetes mellitus using a soft voting classifier with an explainable AI. Sensors, 22.","DOI":"10.3390\/s22197268"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Agliata, A., Giordano, D., Bardozzo, F., Bottiglieri, S., Facchiano, A., and Tagliaferri, R. (2023). Machine learning as a support for the diagnosis of type 2 diabetes. Int. J. Mol. Sci., 24.","DOI":"10.3390\/ijms24076775"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"111900","DOI":"10.3748\/wjg.v31.i47.111900","article-title":"Artificial intelligence applications for managing metabolic dysfunction-associated steatotic liver disease: Current status and future prospects","volume":"31","author":"Lou","year":"2025","journal-title":"World J. Gastroenterol."}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/3\/502\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T11:44:48Z","timestamp":1773056688000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/3\/502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":43,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["medicina62030502"],"URL":"https:\/\/doi.org\/10.3390\/medicina62030502","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]}}}