{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:33:20Z","timestamp":1772642000849,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Slovenian Research Agency","award":["ARRS P2-0057"],"award-info":[{"award-number":["ARRS P2-0057"]}]},{"name":"Slovenian Research Agency","award":["ARRS N3-0307"],"award-info":[{"award-number":["ARRS N3-0307"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Introduction: Type 2 diabetes mellitus is a major global health concern, but interpreting machine learning models for diagnosis remains challenging. This study investigates combining association rule mining with advanced natural language processing to improve both diagnostic accuracy and interpretability. This novel approach has not been explored before in using pretrained transformers for diabetes classification on tabular data. Methods: The study used the Pima Indians Diabetes dataset to investigate Type 2 diabetes mellitus. Python and Jupyter Notebook were employed for analysis, with the NiaARM framework for association rule mining. LightGBM and the dalex package were used for performance comparison and feature importance analysis, respectively. SHAP was used for local interpretability. OpenAI GPT version 3.5 was utilized for outcome prediction and interpretation. The source code is available on GitHub. Results: NiaARM generated 350 rules to predict diabetes. LightGBM performed better than the GPT-based model. A comparison of GPT and NiaARM rules showed disparities, prompting a similarity score analysis. LightGBM\u2019s decision making leaned heavily on glucose, age, and BMI, as highlighted in feature importance rankings. Beeswarm plots demonstrated how feature values correlate with their influence on diagnosis outcomes. Discussion: Combining association rule mining with GPT for Type 2 diabetes mellitus classification yields limited effectiveness. Enhancements like preprocessing and hyperparameter tuning are required. Interpretation challenges and GPT\u2019s dependency on provided rules indicate the necessity for prompt engineering and similarity score methods. Variations in feature importance rankings underscore the complexity of T2DM. Concerns regarding GPT\u2019s reliability emphasize the importance of iterative approaches for improving prediction accuracy.<\/jats:p>","DOI":"10.3390\/info15030162","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T12:14:40Z","timestamp":1710245680000},"page":"162","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Using Generative AI to Improve the Performance and Interpretability of Rule-Based Diagnosis of Type 2 Diabetes Mellitus"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6647-9988","authenticated-orcid":false,"given":"Leon","family":"Kopitar","sequence":"first","affiliation":[{"name":"Faculty of Health Sciences, University of Maribor, Zitna Ulica 15, 2000 Maribor, Slovenia"},{"name":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroska Cesta 46, 2000 Maribor, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6418-1272","authenticated-orcid":false,"suffix":"Jr.","given":"Iztok","family":"Fister","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroska Cesta 46, 2000 Maribor, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-8679","authenticated-orcid":false,"given":"Gregor","family":"Stiglic","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, University of Maribor, Zitna Ulica 15, 2000 Maribor, Slovenia"},{"name":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroska Cesta 46, 2000 Maribor, Slovenia"},{"name":"Usher Institute, University of Edinburgh, Teviot Place, Edinburgh 0131, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,12]]},"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","unstructured":"Oh, S.H., Lee, S.J., and Park, J. (2022). Precision medicine for hypertension patients with type 2 diabetes via reinforcement learning. J. Pers. Med., 12.","DOI":"10.3390\/jpm12010087"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1177\/1932296820985567","article-title":"Diabetic retinopathy screening using artificial intelligence and handheld smartphone-based retinal camera","volume":"16","author":"Malerbi","year":"2022","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1007\/s13246-023-01254-3","article-title":"A deep learning nomogram of continuous glucose monitoring data for the risk prediction of diabetic retinopathy in type 2 diabetes","volume":"46","author":"Tao","year":"2023","journal-title":"Phys. Eng. Sci. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1169595","DOI":"10.3389\/frai.2023.1169595","article-title":"ChatGPT in medicine: An overview of its applications, advantages, limitations, future prospects, and ethical considerations","volume":"6","author":"Dave","year":"2023","journal-title":"Front. Artif. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Patil, B., Joshi, R., and Toshniwal, D. (2010, January 9\u201311). Association rule for classification of type-2 diabetic patients. Proceedings of the 2010 Second International Conference on Machine Learning and Computing, Bangalore, India.","DOI":"10.1109\/ICMLC.2010.67"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"11981","DOI":"10.1038\/s41598-020-68771-z","article-title":"Early detection of type 2 diabetes mellitus using machine learning-based prediction models","volume":"10","author":"Kopitar","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Deberneh, H.M., and Kim, I. (2021). Prediction of type 2 diabetes based on machine learning algorithm. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18063317"},{"key":"ref_9","unstructured":"Smith, J.W., Everhart, J.E., Dickson, W., Knowler, W.C., and Johannes, R.S. (1988). Proceedings of the Annual Symposium on Computer Application in Medical Care, American Medical Informatics Association."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4448","DOI":"10.21105\/joss.04448","article-title":"NiaARM: A minimalistic framework for Numerical Association Rule Mining","volume":"7","author":"Stupan","year":"2022","journal-title":"J. Open Source Softw."},{"key":"ref_11","unstructured":"Fister, I., Podgorelec, V., and Fister, I. (2021). Intelligent Computing and Optimization, Proceedings of the 3rd International Conference on Intelligent Computing and Optimization 2020 (ICO 2020), Hua Hin, Thailand, 8\u20139 October 2020, Springer."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kaushik, M., Sharma, R., Peious, S.A., Shahin, M., Ben Yahia, S., and Draheim, D. (2020, January 25\u201327). On the potential of numerical association rule mining. Proceedings of the International Conference on Future Data and Security Engineering, Quy Nhon, Vietnam.","DOI":"10.1007\/978-981-33-4370-2_1"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1109\/69.846291","article-title":"Scalable algorithms for association mining","volume":"12","author":"Zaki","year":"2000","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_14","unstructured":"Agrawal, R., and Srikant, R. (1994, January 12\u201315). Fast algorithms for mining association rules. Proceedings of the 20th International Conference on Very Large Data Bases, VLDB, Santiago de Chile, Chile."},{"key":"ref_15","unstructured":"Kaushik, M., Sharma, R., Fister, I., and Draheim, D. (2023). Numerical association rule mining: A systematic literature review. arXiv."},{"key":"ref_16","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst., 3146\u20133154."},{"key":"ref_17","first-page":"1","article-title":"dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python","volume":"22","author":"Baniecki","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref_18","unstructured":"Molnar, C. (2020). Interpretable Machine Learning, Lulu.com."},{"key":"ref_19","unstructured":"(2023, September 28). OpenAI Platform\u2014platform.openai.com. Available online: https:\/\/platform.openai.com\/account\/rate-limits."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1008202821328","article-title":"Differential evolution\u2014A simple and efficient heuristic for global optimization over continuous spaces","volume":"11","author":"Storn","year":"1997","journal-title":"J. Glob. Optim."},{"key":"ref_22","first-page":"111","article-title":"Evidence based emergency medicine; part 5 receiver operating curve and area under the curve","volume":"4","author":"Safari","year":"2016","journal-title":"Emergency"},{"key":"ref_23","unstructured":"\u0160ter, B., and Dobnikar, A. (1996, January 17\u201319). Neural networks in medical diagnosis: Comparison with other methods. Proceedings of the International Conference on Engineering Applications of Neural Networks, London, UK."},{"key":"ref_24","unstructured":"Li, W., Han, J., and Pei, J. (December, January 29). CMAR: Accurate and efficient classification based on multiple class-association rules. Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, CA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, J., and Karypis, G. (2005, January 21\u201323). HARMONY: Efficiently mining the best rules for classification. Proceedings of the 2005 SIAM International Conference on Data Mining, Newport Beach, CA, USA.","DOI":"10.1137\/1.9781611972757.19"},{"key":"ref_26","unstructured":"Ma, B., Liu, B., and Hsu, Y. (1998, January 27\u201331). Integrating classification and association rule mining. Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, New York, NY, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Drew, B.J., Harris, P., Z\u00e8gre-Hemsey, J.K., Mammone, T., Schindler, D., Salas-Boni, R., Bai, Y., Tinoco, A., Ding, Q., and Hu, X. (2014). Insights into the problem of alarm fatigue with physiologic monitor devices: A comprehensive observational study of consecutive intensive care unit patients. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0110274"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1629","DOI":"10.1056\/NEJMoa1415236","article-title":"Systemic inflammatory response syndrome criteria in defining severe sepsis","volume":"372","author":"Kaukonen","year":"2015","journal-title":"N. Engl. J. Med."},{"key":"ref_30","unstructured":"Kopitar, L., Cilar, L., Kocbek, P., and Stiglic, G. (2019). International Workshop on Knowledge Representation for Health Care, Springer."},{"key":"ref_31","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Joshi, R.D., and Dhakal, C.K. (2021). Predicting type 2 diabetes using logistic regression and machine learning approaches. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18147346"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"110878","DOI":"10.1016\/j.diabres.2023.110878","article-title":"Risk prediction models for type 2 diabetes using either fasting plasma glucose or HbA1c in Chinese, Malay, and Indians: Results from three multi-ethnic Singapore cohorts","volume":"203","author":"Seah","year":"2023","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_34","unstructured":"International Diabetes Federation (2021). IDF Diabetes Atlas, International Diabetes Federation. [10th ed.]."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1172\/JCI111533","article-title":"Relationships between insulin secretion, insulin action, and fasting plasma glucose concentration in nondiabetic and noninsulin-dependent diabetic subjects","volume":"74","author":"Bogardus","year":"1984","journal-title":"J. Clin. Investig."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.ecl.2004.12.001","article-title":"Compensatory hyperinsulinemia and the development of an atherogenic lipoprotein profile: The price paid to maintain glucose homeostasis in insulin-resistant individuals","volume":"34","author":"Reaven","year":"2005","journal-title":"Endocrinol. Metab. Clin."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"S169","DOI":"10.2337\/diabetes.50.2007.S169","article-title":"Decreased insulin secretion in type 2 diabetes: A problem of cellular mass or function?","volume":"50","author":"Clark","year":"2001","journal-title":"Diabetes"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.jcmgh.2018.10.016","article-title":"Resolving the paradox of hepatic insulin resistance","volume":"7","author":"Santoleri","year":"2019","journal-title":"Cell. Mol. Gastroenterol. Hepatol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1002\/ijc.30729","article-title":"Association between hyperinsulinemia and increased risk of cancer death in nonobese and obese people: A population-based observational study","volume":"141","author":"Tsujimoto","year":"2017","journal-title":"Int. J. Cancer"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1161\/HYPERTENSIONAHA.121.17981","article-title":"Hypertension in diabetes: An update of basic mechanisms and clinical disease","volume":"78","author":"Jia","year":"2021","journal-title":"Hypertension"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Przezak, A., Bielka, W., and Pawlik, A. (2022). Hypertension and Type 2 Diabetes\u2014The Novel Treatment Possibilities. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms23126500"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"667","DOI":"10.4093\/dmj.2022.0215","article-title":"Blood pressure target in type 2 diabetes mellitus","volume":"46","author":"Kim","year":"2022","journal-title":"Diabetes Metab. J."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1038\/hr.2015.72","article-title":"Hypertension is an independent risk factor for type 2 diabetes: The Korean genome and epidemiology study","volume":"38","author":"Kim","year":"2015","journal-title":"Hypertens. Res."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1038\/hr.2011.89","article-title":"The effect of body mass index and fasting glucose on the relationship between blood pressure and incident diabetes mellitus: A 5-year follow-up study","volume":"34","author":"Lee","year":"2011","journal-title":"Hypertens. Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1161\/HYPERTENSIONAHA.122.19256","article-title":"Hypertension, arterial stiffness, and diabetes: A prospective cohort study","volume":"79","author":"Tian","year":"2022","journal-title":"Hypertension"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1161\/CIRCRESAHA.121.318061","article-title":"Arterial Stiffness and Cardiovascular Risk in Hypertension","volume":"128","author":"Boutouyrie","year":"2021","journal-title":"Circ. Res."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"544302","DOI":"10.3389\/fcvm.2020.544302","article-title":"Arterial Stiffness and Hypertension in the Elderly","volume":"7","author":"Laurent","year":"2020","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e1379","DOI":"10.1002\/widm.1379","article-title":"Interpretability of machine learning-based prediction models in healthcare","volume":"10","author":"Stiglic","year":"2020","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/3\/162\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:12:28Z","timestamp":1760105548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/3\/162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,12]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["info15030162"],"URL":"https:\/\/doi.org\/10.3390\/info15030162","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,12]]}}}