Artificial Intelligence for Diabetes Diagnosis and Prediction: Methods and Challenges

Yukang Wang

doi:10.54097/k4r5h255

Authors

Yukang Wang College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110819, China

DOI:

https://doi.org/10.54097/k4r5h255

Keywords:

Diabetes diagnosis and prediction; Machine learning; Deep learning; Artificial intelligence in healthcare; Clinical decision support.

Abstract

Diabetes Mellitus is a worldwide disease that affects the body’s metabolism and is considered a public health disaster resulting in great loss. Proper diagnosis and estimation of Diabetes Mellitus (DM) is crucial to enhance the patient’s diagnosis and upgrade the health care system. This review provides a systematic review of advances in diabetes diagnosis and prediction. This paper also talks about traditional diagnostic methods and risk prediction models and compares them clinically in both sensitivity and coverage, on the scale of application outside health. It further explores the application of artificial intelligence (AI) in clinical applications for DM patients. Open-ended questions in explainability and clinical translations are also discussed. Furthermore, this paper also discuss limitations in current presentation and conclude by suggesting future research agendas. These future agendas include but are not limited AI techniques in mathematical applications. The review discusses the potential use of Artificial intelligence in providing personalized diabetes care further aiding the DM patients as well as improving diagnosis. Artificial intelligence would tie together methodological excellence with clinical practice solutions.

Downloads

Download data is not yet available.

References

[1] Campanella S, Paragliola G, Cherubini V, Pierleoni P, Palma L. Towards personalized AI-based diabetes therapy: a review. IEEE Journal of Biomedical and Health Informatics, 2024, 28(11): 6944–6957. DOI: 10.1109/JBHI.2024.3443137. DOI: https://doi.org/10.1109/JBHI.2024.3443137

[2] Gregory G A, et al. Global incidence, prevalence, and mortality of type 1 diabetes in 2021 with projection to 2040: a modelling study. Lancet Diabetes & Endocrinology, 2022, 10(10): 741–760. DOI: 10.1016/S2213-8587(22)00218-2. DOI: https://doi.org/10.1016/S2213-8587(22)00218-2

[3] Guo H, Wu H, Li Z. The pathogenesis of diabetes. International Journal of Molecular Sciences, 2023, 24(8): 6978. DOI: 10.3390/ijms24086978. DOI: https://doi.org/10.3390/ijms24086978

[4] Lovic D, Piperidou A, Zografou I, Grassos H, Pittaras A, Manolis A. The growing epidemic of diabetes mellitus. Current Vascular Pharmacology, 2020, 18(2): 104–109. DOI: 10.2174/1570161117666190405165911. DOI: https://doi.org/10.2174/1570161117666190405165911

[5] Ortiz-Martínez M, González-González M, Martagón A J, Hlavinka V, Willson R C, Rito-Palomares M. Recent developments in biomarkers for diagnosis and screening of type 2 diabetes mellitus. Current Diabetes Reports, 2022, 22(3): 95–115. DOI: 10.1007/s11892-022-01453-4. DOI: https://doi.org/10.1007/s11892-022-01453-4

[6] ElSayed N A, et al. Classification and diagnosis of diabetes: standards of care in diabetes—2023. Diabetes Care, 2023, 46(Suppl. 1): S19–S40. DOI: 10.2337/dc23-S002. DOI: https://doi.org/10.2337/dc23-S002

[7] American Diabetes Association Professional Practice Committee. Diagnosis and classification of diabetes: standards of care in diabetes—2025. Diabetes Care, 2024, 48(Suppl. 1): S27–S49. DOI: 10.2337/dc25-S002. DOI: https://doi.org/10.2337/dc25-S002

[8] Arnardóttir E, Sigurðardóttir Á K, Graue M, Kolltveit B-C H, Skinner T. Using HbA1c measurements and the Finnish diabetes risk score to identify undiagnosed individuals and those at risk of diabetes in primary care. BMC Public Health, 2023, 23(1): 211. DOI: 10.1186/s12889-023-15122-y. DOI: https://doi.org/10.1186/s12889-023-15122-y

[9] Almutairi E S, Abbod M F. Machine learning methods for diabetes prevalence classification in Saudi Arabia. Modelling, 2023, 4(1): 37–55. DOI: 10.3390/modelling4010004. DOI: https://doi.org/10.3390/modelling4010004

[10] Thanikachalam V, Kabilan K, Erramchetty S K. Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema. BMC Medical Imaging, 2024, 24(1): 227. DOI: 10.1186/s12880-024-01406-1. DOI: https://doi.org/10.1186/s12880-024-01406-1

[11] CNN-based integrated framework for enhanced diabetic retinopathy detection. Recent Advances in Computer Science and Communications, 2025, 18(3). DOI: 10.2174/0126662558293742240925044450. DOI: https://doi.org/10.2174/0126662558293742240925044450

[12] Zhang W, Belcheva V, Ermakova T. Interpretable deep learning for diabetic retinopathy: a comparative study of CNN, ViT, and hybrid architectures. Computers, 2025, 14(5): 187. DOI: 10.3390/computers14050187. DOI: https://doi.org/10.3390/computers14050187

[13] Carvalho C F, Liang Z. Glucose prediction with long short-term memory (LSTM) models in three distinct populations. Engineering Proceedings, 2024, 82(1): 87. DOI: 10.3390/ecsa-11-20513. DOI: https://doi.org/10.3390/ecsa-11-20513

[14] Javed H, El-Sappagh S, Abuhmed T. Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications. Artificial Intelligence Review, 2024, 58(1): 12. DOI: 10.1007/s10462-024-11005-9. DOI: https://doi.org/10.1007/s10462-024-11005-9