{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:04:12Z","timestamp":1787504652716,"version":"build-2736575974"},"reference-count":37,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Complication risks in children and adolescents with type 1 diabetes (T1D) can lead to serious health outcomes if not detected early. Despite the availability of clinical data, there remains a gap in interpretable tools that support risk stratification in this age group, particularly in alignment with local clinical guidelines.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The purpose of this study is to develop a clinically interpretable model that classifies the risk levels of T1D complications\u2014acute, chronic, and low\u2014using real-world data and expert clinical rules derived from the Saudi Diabetes Clinical Practice Guidelines.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n A pediatric T1D dataset comprising of 306 patients was preprocessed through structured cleaning and feature engineering. Risk labels were constructed using Saudi Diabetes Clinical Practice Guidelines\u2013derived rules. Feature selection was performed using a hybrid approach that combined the SHAP (Shapley Additive Explanations) analysis with exhaustive feature selection. A decision tree model was trained and optimized via cross-validation, using the\n F<\/jats:italic>\n 1<\/jats:sub>\n -score as the primary performance metric.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The final model achieved a high mean\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.9876 with a low variance of 0.0189, using only 5 clinical features: BMI, hypoglycemia, disease duration,\n \n hemoglobin A\n 1c<\/jats:sub>\n , and impaired glucose metabolism. These features were consistently ranked as the most influential. The resulting decision tree offered a transparent logic path, enhancing its clinical interpretability and usability.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study demonstrates that a simple and interpretable model, guided by national clinical guidelines, can effectively predict the risk levels of T1D complications in children and adolescents. Its strong performance, clarity, and reliance on a small number of clinically meaningful features make it a promising candidate for integration into clinical decision support systems. This supports a shift toward predictive and personalized diabetes care.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81039","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T18:21:45Z","timestamp":1778869305000},"page":"e81039-e81039","source":"Crossref","is-referenced-by-count":1,"title":["Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8477-0050","authenticated-orcid":false,"given":"Jalilah","family":"Fllatah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4475-4878","authenticated-orcid":false,"given":"Haneen","family":"Banjar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,15]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s13340-024-00748-z","article-title":"Type 1 diabetes: immune pathology and novel therapeutic approaches","volume":"15","author":"Ling","journal-title":"Diabetol Int"},{"key":"R2","unstructured":"Type 1 diabetes estimates in children and adults. International Diabetes Federation; 2022. URL: https:\/\/diabetesatlas.org\/resources\/idf-diabetes-atlas-reports\/type-1-diabetes-estimates-in-children-and-adults\/ [Accessed 03-03-2026]"},{"key":"R3","unstructured":"Melmed S Auchus RJ Goldfine AB Rosen CJ Kopp PA . Williams Textbook of Endocrinology. 15\n th\n ed. Elsevier; 2024. ISBN: 9780323932301"},{"issue":"8","key":"R4","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1111\/pedi.13443","article-title":"ISPAD clinical practice consensus guidelines 2022: assessment and management of hypoglycemia in children and adolescents with diabetes","volume":"23","author":"Abraham","journal-title":"Pediatr Diabetes"},{"issue":"12","key":"R5","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare9121712","article-title":"A machine learning approach to predicting diabetes complications","volume":"9","author":"Jian","journal-title":"Healthcare (Basel)"},{"issue":"Supplement_1","key":"R6","doi-asserted-by":"publisher","first-page":"S111","DOI":"10.2337\/dc24-S006","article-title":"6. Glycemic goals and hypoglycemia: standards of care in diabetes\u20142024","volume":"47","author":"American Diabetes Association Professional Practice Committee","journal-title":"Diabetes Care"},{"issue":"6","key":"R7","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1177\/19322968251365245","article-title":"Machine learning to diagnose complications of diabetes","volume":"19","author":"Scheideman","journal-title":"J Diabetes Sci Technol"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","first-page":"2906","DOI":"10.3390\/app15062906","article-title":"Prediction models for diabetes in children and adolescents: a review","volume":"15","author":"Cveticanin","journal-title":"Appl Sci"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41746-021-00394-8","article-title":"Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data","volume":"4","author":"Ravaut","journal-title":"NPJ Digit Med"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.130042.1","article-title":"Predicting diabetic ketoacidosis in pediatric patients using machine learning","volume":"12","author":"Eid","journal-title":"F1000Res"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/53338","article-title":"A machine learning model for risk stratification of postdiagnosis diabetic ketoacidosis hospitalization in pediatric type 1 diabetes: retrospective study","volume":"9","author":"Subramanian","journal-title":"JMIR Diabetes"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2025.1451290","article-title":"Engineering novel features for diabetes complication prediction using synthetic electronic health records","volume":"16","author":"Voskergian","journal-title":"Front Genet"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2023.110910","article-title":"Predicting the onset of diabetes-related complications after a diabetes diagnosis with machine learning algorithms","volume":"204","author":"Mora","journal-title":"Diabetes Res Clin Pract"},{"issue":"5","key":"R14","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1007\/s00467-022-05689-w","article-title":"Acute and chronic kidney complications in children with type 1 diabetes mellitus","volume":"38","author":"Rivetti","journal-title":"Pediatr Nephrol"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1186\/s13098-021-00767-9","article-title":"Machine learning and deep learning predictive models for type 2 diabetes: a systematic review","volume":"13","author":"Fregoso-Aparicio","journal-title":"Diabetol Metab Syndr"},{"issue":"20","key":"R16","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13202588","article-title":"Interpretable machine learning framework for diabetes prediction: integrating SMOTE balancing with SHAP explainability for clinical decision support","volume":"13","author":"Netayawijit","journal-title":"Healthcare (Basel)"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2018.10.018","article-title":"Dataset on significant risk factors for type 1 diabetes: a Bangladeshi perspective","volume":"21","author":"Asaduzzaman","journal-title":"Data Brief"},{"issue":"16","key":"R18","doi-asserted-by":"publisher","first-page":"4102","DOI":"10.3923\/jeasci.2017.4102.4107","article-title":"Review of data preprocessing techniques in data mining","volume":"12","author":"Alasadi","journal-title":"J Eng Appl Sci"},{"key":"R19","unstructured":"Hosmer DW Lemeshow S May S . Applied Survival Analysis: Regression Modeling of Time-to-Event Data. 2\n nd\n ed. John Wiley & Sons, Inc; 2008. URL: https:\/\/download.e-bookshelf.de\/download\/0000\/5709\/18\/L-G-0000570918-0002357449.pdf [Accessed 21-04-2026]"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.0077","article-title":"Association of achieving time in range clinical targets with treatment modality among youths with type 1 diabetes","volume":"6","author":"Dovc","journal-title":"JAMA Netw Open"},{"key":"R21","unstructured":"Growth reference data for 5-19 years: BMI-for-age (5-19 years). World Health Organization. URL: https:\/\/www.who.int\/tools\/growth-reference-data-for-5to19-years\/indicators\/bmi-for-age [Accessed 01-06-2025]"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","first-page":"5122","DOI":"10.1016\/j.ygeno.2020.09.020","article-title":"Machine learning method using position-specific mutation based classification outperforms one hot coding for disease severity prediction in haemophilia \u201cA\u201d","volume":"112","author":"Singh","journal-title":"Genomics"},{"key":"R23","unstructured":"Saudi diabetes clinical practice guidelines (SDCPG). Saudi Health Council; 2021. URL: https:\/\/shc.gov.sa\/ar\/Centers\/NDC\/Activities\/Documents\/Specialists\/Saudi%20Diabetes%20Clinical%20Practice%20Guidelines.pdf [Accessed 26-05-2025]"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","article-title":"A survey on feature selection methods","volume":"40","author":"Chandrashekar","journal-title":"Comput Electr Eng"},{"key":"R25","volume":"12","author":"Pedregosa","journal-title":"J Mach Learn Res"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/BF00116251","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","journal-title":"Mach Learn"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.artmed.2012.12.003","article-title":"Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach","volume":"57","author":"Bennett","journal-title":"Artif Intell Med"},{"issue":"1","key":"R28","first-page":"281","volume":"13","author":"Bergstra","journal-title":"J Mach Learn Res"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","journal-title":"PLoS One"},{"issue":"Supplement_1","key":"R30","doi-asserted-by":"publisher","DOI":"10.2337\/db24-1458-P","article-title":"1458-P: cardiovascular risk is higher in people with type 1 diabetes living with overweight or obesity\u2014insights from the SFDT1 cohort","volume":"73","author":"Salle","journal-title":"Diabetes"},{"issue":"6","key":"R31","doi-asserted-by":"publisher","first-page":"108747","DOI":"10.1016\/j.jdiacomp.2024.108747","article-title":"Body mass index\u2019s influence on arterial hypertension in type 1 diabetes - a brief report from IMI-SOPHIA study","volume":"38","author":"Petty","journal-title":"J Diabetes Complications"},{"issue":"2","key":"R32","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.nut.2012.07.003","article-title":"Obesity, systemic inflammation, and increased risk for cardiovascular disease and diabetes among adolescents: a need for screening tools to target interventions","volume":"29","author":"DeBoer","journal-title":"Nutrition"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.ecl.2010.05.003","article-title":"Hypoglycemia in type 1 diabetes mellitus","volume":"39","author":"Cryer","journal-title":"Endocrinol Metab Clin North Am"},{"issue":"Suppl 20","key":"R34","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1111\/pedi.12174","article-title":"ISPAD Clinical Practice Consensus Guidelines 2014. Assessment and management of hypoglycemia in children and adolescents with diabetes","volume":"15 Suppl 20","author":"Ly","journal-title":"Pediatr Diabetes"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.2337\/diacare.27.7.1554","article-title":"A randomized, prospective trial comparing the efficacy of continuous subcutaneous insulin infusion with multiple daily injections using insulin glargine","volume":"27","author":"Doyle","journal-title":"Diabetes Care"},{"issue":"Suppl 27","key":"R36","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1111\/pedi.12742","article-title":"ISPAD Clinical Practice Consensus Guidelines 2018: microvascular and macrovascular complications in children and adolescents","volume":"19 Suppl 27","author":"Donaghue","journal-title":"Pediatr Diabetes"},{"issue":"14","key":"R37","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1056\/NEJM199309303291401","article-title":"The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus","volume":"329","author":"The Diabetes Control and Complications Trial Research Group","journal-title":"N Engl J Med"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e81039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:14:42Z","timestamp":1782843282000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e81039"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":37,"URL":"https:\/\/doi.org\/10.2196\/81039","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]},"article-number":"v10i4e81039"}}