DOI:
https://doi.org/10.64539/sjer.v2i1.2026.376Keywords:
Gestational diabetes mellitus, Type 2 diabetes mellitus, Deep learning, Bidirectional LSTM, Attention mechanism, Explainable artificial intelligence, Risk predictionAbstract
Women with gestational diabetes mellitus (GDM) face a 7-10 times elevated risk of developing Type 2 Diabetes Mellitus (T2DM), yet current predictive models demonstrate limited accuracy (AUC-ROC: 0.70-0.85) and insufficient interpretability for clinical adoption. This study addresses the critical need for accurate, transparent risk prediction tools by developing an interpretable deep learning framework integrating bidirectional long short-term memory (BiLSTM) networks with attention mechanisms and SHapley Additive exPlanations (SHAP). Using a synthetic dataset of 6,000 simulated post-GDM women with 28 clinical risk factors, the BiLSTM-Attention model was evaluated through stratified 10-fold cross-validation against five baseline models. The proposed model achieved exceptional performance with 98.45% accuracy, 98.80% precision, 98.30% recall, 98.55% F1-score, 96.85% MCC, and 0.9968 AUC-ROC, significantly outperforming all baselines (p < 0.05). SHAP analysis identified recurrent GDM history, elevated HbA1c, and impaired glucose tolerance as primary predictors, while highlighting modifiable factors including physical inactivity, dietary habits, and obesity as actionable intervention targets. This proof-of-concept demonstrates the methodological feasibility of combining high-performance deep learning with explainable AI for T2DM risk stratification. However, synthetic data represents a significant limitation; comprehensive real-world clinical validation across diverse populations is essential before clinical implementation. The publicly available computational framework enables future validation studies to advance this approach toward clinical utility.
References
[1] American Diabetes Association (ADA), “2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes—2018,” Diabetes Care, vol. 41, no. Supplement_1, pp. S13–S27, Jan. 2018, https://doi.org/10.2337/dc18-S002.
[2] International Diabetes Federation, “IDF DIABETES ATLAS: 463 million PEOPLE LIVING WITH DIABETES,” 2019.
[3] E. Vounzoulaki, K. Khunti, S. C. Abner, B. K. Tan, M. J. Davies, and C. L. Gillies, “Progression to type 2 diabetes in women with a known history of gestational diabetes: Systematic review and meta-analysis,” The BMJ, vol. 369, May 2020, https://doi.org/10.1136/bmj.m1361.
[4] S. R. Khan, H. Mohan, Y. Liu, B. Batchuluun, H. Gohil, D. A. Rijjal, Y. Manialawy, B. J. Cox, E. P. Gunderson, M. B. Wheeler, “The discovery of novel predictive biomarkers and early-stage pathophysiology for the transition from gestational diabetes to type 2 diabetes,” Diabetologia, vol. 62, no. 4, pp. 687–703, Apr. 2019, https://doi.org/10.1007/s00125-018-4800-2.
[5] A. Allalou, A. Nalla, K. J. Prentice, Y. Liu, M. Zhang, F. F. Dai, X. Ning, L. R. Osborne, B. J. Cox, E. P. Gunderson, M. B. Wheeler, “A Predictive Metabolic Signature for the Transition From Gestational Diabetes Mellitus to Type 2 Diabetes,” Diabetes, vol. 65, no. 9, pp. 2529–2539, Sep. 2016, https://doi.org/10.2337/db15-1720.
[6] M. V. Joglekar, W. K. M. Wong, F. K. Ema, H. M. Georgiou, A. Shub, A. A. Hardikar, M. Lappas, “Postpartum circulating microRNA enhances prediction of future type 2 diabetes in women with previous gestational diabetes,” Diabetologia, vol. 64, no. 7, pp. 1516–1526, Jul. 2021, https://doi.org/10.1007/s00125-021-05429-z.
[7] J. Prashanthan and A. Prashanthan, “Predicting the future risk of developing type 2 diabetes in women with a history of gestational diabetes mellitus using machine learning and explainable artificial intelligence,” Prim. Care Diabetes, Sep. 2025, https://doi.org/10.1016/j.pcd.2025.09.006.
[8] L.-W. Chen, S. E. Soh, M.-T. Tint, S. L. Loy, F. Yap, K. H. Tan, Y. S. Lee, L. P.-C. Shek, K. M. Godfrey, P. D.. Gluckman, J. G. Eriksson, Y.-S. Chong, S.-Y. Chan, “Combined analysis of gestational diabetes and maternal weight status from pre-pregnancy through post-delivery in future development of type 2 diabetes,” Sci. Rep., vol. 11, no. 1, p. 5021, Mar. 2021, https://doi.org/10.1038/s41598-021-82789-x.
[9] M. Kumar et al., “Machine Learning–Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study,” JMIR Diabetes, vol. 7, no. 3, p. e32366, Jul. 2022, https://doi.org/10.2196/32366.
[10] B. S. Fiskå, A. S. D. Pay, A. C. Staff, and M. Sugulle, “Gestational diabetes mellitus, follow-up of future maternal risk of cardiovascular disease and the use of eHealth technologies—a scoping review,” Syst. Rev., vol. 12, no. 1, p. 178, Sep. 2023, https://doi.org/10.1186/s13643-023-02343-w.
[11] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, https://doi.org/10.1038/nature14539.
[12] V. Gulshan, L. Peng, M. Coram, M. C. Stumpe, D. Wu, A. Narayanaswamy, S. Venugopalan, K. Widner, T. Madams, J. Cuadros, R. Kim, R. Raman, P. C. Nelson, J. L. Mega, D. R. Webster, “Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs,” JAMA, vol. 316, no. 22, p. 2402, Dec. 2016, https://doi.org/10.1001/jama.2016.17216.
[13] A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, S. Thrun, “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, Feb. 2017, https://doi.org/10.1038/nature21056.
[14] E. Choi, M. T. Bahadori, A. Schuetz, W. F. Stewart, and J. Sun, “Doctor AI: Predicting Clinical Events via Recurrent Neural Networks.,” JMLR Workshop Conf. Proc., vol. 56, pp. 301–318, Aug. 2016. https://proceedings.mlr.press/v56/Choi16.pdf.
[15] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, https://doi.org/10.1162/neco.1997.9.8.1735.
[16] I. K. Ihianle, A. O. Nwajana, S. H. Ebenuwa, R. I. Otuka, K. Owa, and M. O. Orisatoki, “A Deep Learning Approach for Human Activities Recognition From Multimodal Sensing Devices,” IEEE Access, vol. 8, pp. 179028–179038, 2020, https://doi.org/10.1109/ACCESS.2020.3027979.
[17] Z. C. Lipton, D. C. Kale, C. Elkan, and R. Wetzel, “Learning to Diagnose with LSTM Recurrent Neural Networks,” Mar. 2017. https://doi.org/10.48550/arXiv.1511.03677.
[18] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Transactions on Signal Processing, vol. 45, no. 11, pp. 2673–2681, 1997, https://doi.org/10.1109/78.650093.
[19] D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate,” May 2016. https://doi.org/10.48550/arXiv.1409.0473.
[20] J. Dodge, Q. V. Liao, Y. Zhang, R. K. E. Bellamy, and C. Dugan, “Explaining models,” in Proceedings of the 24th International Conference on Intelligent User Interfaces, New York, NY, USA: ACM, Mar. 2019, pp. 275–285. https://doi.org/10.1145/3301275.3302310.
[21] J. L. Katzman, U. Shaham, A. Cloninger, J. Bates, T. Jiang, and Y. Kluger, “DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network,” BMC Med. Res. Methodol., vol. 18, no. 1, p. 24, Dec. 2018, https://doi.org/10.1186/s12874-018-0482-1.
[22] S. M. Lundberg et al., “Explainable machine-learning predictions for the prevention of hypoxaemia during surgery,” Nat. Biomed. Eng., vol. 2, no. 10, pp. 749–760, Oct. 2018, https://doi.org/10.1038/s41551-018-0304-0.
[23] S. M. Lauritsen et al., “Explainable artificial intelligence model to predict acute critical illness from electronic health records.,” Nat. Commun., vol. 11, no. 1, p. 3852, Jul. 2020, https://doi.org/10.1038/s41467-020-17431-x.
[24] J. Prashanthan and A. Prashanthan, “Data for T2DM Risk prediction after GDM.” Accessed: Sep. 29, 2025. [Online]. Available: https://www.kaggle.com/datasets/prashanthana/gdm-risk-data-for-t2dm-prediction.
[25] M. Lamari, N. Azizi, N. E. Hammami, A. Boukhamla, S. Cheriguene, N. Dendani, N. E. Benzebouchi, “SMOTE–ENN-Based Data Sampling and Improved Dynamic Ensemble Selection for Imbalanced Medical Data Classification,” in Advances on Smart and Soft Computing, pp. 37–49, 2021. https://doi.org/10.1007/978-981-15-6048-4_4.
[26] D. Hosmer, R. Sturdivant, and S. Lemeshow, Applied Logistic Regression. John Wiley & Sons., 2013. https://books.google.co.id/books?id=bRoxQBIZRd4C.
[27] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, https://doi.org/10.1023/A:1010933404324.
[28] T. Chen and C. Guestrin, “XGBoost,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA: ACM, Aug. 2016, pp. 785–794. https://doi.org/10.1145/2939672.2939785.
[29] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 12, pp. 6999–7019, Dec. 2022, https://doi.org/10.1109/TNNLS.2021.3084827.
[30] S. Lundberg, “Commentary,” Ann. Emerg. Med., vol. 70, no. 1, pp. 30–31, Jul. 2017, https://doi.org/10.1016/j.annemergmed.2017.05.019.
[31] C. Molnar, G. Casalicchio, and B. Bischl, “Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges,” 2020, pp. 417–431. https://doi.org/10.1007/978-3-030-65965-3_28.
[32] D. Tchuente, J. Lonlac, and B. Kamsu-Foguem, “A methodological and theoretical framework for implementing explainable artificial intelligence (XAI) in business applications,” Comput. Ind., vol. 155, p. 104044, Feb. 2024, https://doi.org/10.1016/j.compind.2023.104044.
[33] H.-C. Lin, C.-T. Su, and P.-C. Wang, “An Application of Artificial Immune Recognition System for Prediction of Diabetes Following Gestational Diabetes,” J. Med. Syst., vol. 35, no. 3, pp. 283–289, Jun. 2011, https://doi.org/10.1007/s10916-009-9364-8.
[34] M. Lappas, P. A. Mundra, G. Wong, K. Huynh, D. Jinks, H. M. Georgiou, M. Permezel, P. J. Meikle, “The prediction of type 2 diabetes in women with previous gestational diabetes mellitus using lipidomics,” Diabetologia, vol. 58, no. 7, pp. 1436–1442, Jul. 2015, https://doi.org/10.1007/s00125-015-3587-7.
[35] M. Köhler, A. G. Ziegler, and A. Beyerlein, “Development of a simple tool to predict the risk of postpartum diabetes in women with gestational diabetes mellitus,” Acta Diabetol., vol. 53, no. 3, pp. 433–437, Jun. 2016, https://doi.org/10.1007/s00592-015-0814-0.
[36] W. Li, J. Leng, H. Liu, S. Zhang, L. Wang, G. Hu, J. Mi, “Nomograms for incident risk of post‐partum type 2 diabetes in Chinese women with prior gestational diabetes mellitus,” Clin. Endocrinol. (Oxf)., vol. 90, no. 3, pp. 417–424, Mar. 2019, https://doi.org/10.1111/cen.13863.
[37] M. Lai, Y. Liu, G. V. Ronnett, A. Wu, B. J. Cox, F. F. Dai, H. L. Röst , E. P. Gunderson, M. B. Wheeler, “Amino acid and lipid metabolism in post-gestational diabetes and progression to type 2 diabetes: A metabolic profiling study,” PLoS Med., vol. 17, no. 5, p. e1003112, May 2020, https://doi.org/10.1371/journal.pmed.1003112.
[38] B. Man, A. Schwartz, O. Pugach, Y. Xia, and B. Gerber, “A clinical diabetes risk prediction model for prediabetic women with prior gestational diabetes,” PLoS One, vol. 16, no. 6 June, Jun. 2021, https://doi.org/10.1371/journal.pone.0252501.
[39] O. Houri, Y. Gil, R. Chen, A. Wiznitzer, A. Hochberg, E. Hadar, A. Berezowsky, “Prediction of Type 2 Diabetes Mellitus According to Glucose Metabolism Patterns in Pregnancy Using a Novel Machine Learning Algorithm,” J. Med. Biol. Eng., vol. 42, no. 1, pp. 138–144, Feb. 2022, https://doi.org/10.1007/s40846-022-00685-9.
[40] L Ilari, A. Piersanti, C. Göbl, L. Burattini, A. Kautzky-Willer, A. Tura, M. Morettini, “Unraveling the Factors Determining Development of Type 2 Diabetes in Women With a History of Gestational Diabetes Mellitus Through Machine-Learning Techniques,” Front. Physiol., vol. 13, Feb. 2022, https://doi.org/10.3389/fphys.2022.789219.
[41] N. Periyathambi, D. Parkhi, Y. Ghebremichael-Weldeselassie, V. Patel, N. Sukumar, R. Siddharthan, L. Narlikar, P. Saravanan, “Machine learning prediction of non-attendance to postpartum glucose screening and subsequent risk of type 2 diabetes following gestational diabetes,” PLoS One, vol. 17, no. 3, p. e0264648, Mar. 2022, https://doi.org/10.1371/journal.pone.0264648.
[42] Y. Belsti et al., “Development of a risk prediction model for postpartum onset of type 2 diabetes mellitus, following gestational diabetes; the lifestyle InterVention in gestational diabetes (LIVING) study,” Clinical Nutrition, vol. 43, no. 8, pp. 1728–1735, Aug. 2024, https://doi.org/10.1016/j.clnu.2024.06.006.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Amirthanathan Prashanthan, Jenifar Prashanthan
This work is licensed under a Creative Commons Attribution 4.0 International License.
