Abstract
One common pregnancy problem is gestational diabetes mellitus (GDM), which affects 16% of pregnant women worldwide. However, as early and accurate GDM prediction may lower the disease's risk, it is preferred. Creating a smart healthcare monitoring model to analyze data, forecast disease, and identify fetal monitoring is the main goal of this endeavor. Hence, this work presents an IoT based GDM prediction using multi-modality data. In first step, the ultrasound images are enhanced by Contrast Adaptive Limited Histogram (CLAHE). Once the enhancement is done, next step is feature extraction. The features are extracted using pre-trained Inception-V3 model based on CNN. The GDM data obtained from the Kaggle repository is also gathered and pre-processed. The dataset is balanced, standardised, and outliers are removed during the pre-processing stage. Adaptive Golden Eagle Optimisation (AGEO) is used to choose the critical features required for the GDM prediction.
Keywords : Gestational Diabetes Mellitus, Convolutional Neural Network, Deep Learning
References
[1] Brand, J.S., West, J., Tuffnell, D., Bird, P.K., Wright, J., Tilling, K. and Lawlor, D.A., 2018. Gestational diabetes and ultrasound-assessed fetal growth in South Asian and White European women: findings from a prospective pregnancy cohort. BMC medicine, 16(1), pp.1-13.
[2] Scifres, C.M., Feghali, M., Dumont, T., Althouse, A.D., Speer, P., Caritis, S.N. and Catov, J.M., 2015. Large-for-gestational-age ultrasound diagnosis and risk for cesarean delivery in women with gestational diabetes mellitus. Obstetrics & Gynecology, 126(5), pp.978-986.
[3] Popova, P.V., Klyushina, A.A., Vasilyeva, L.B., Tkachuk, A.S., Vasukova, E.A., Anopova, A.D., Pustozerov, E.A., Gorelova, I.V., Kravchuk, E.N., Li, O. and Pervunina, T.M., 2021. Association of common genetic risk variants with gestational diabetes mellitus and their role in GDM prediction. Frontiers in endocrinology, 12, p.628582.
[4] Artzi, N.S., Shilo, S., Hadar, E., Rossman, H., Barbash-Hazan, S., Ben-Haroush, A., Balicer, R.D., Feldman, B., Wiznitzer, A. and Segal, E., 2020. Prediction of gestational diabetes based on nationwide electronic health records. Nature medicine, 26(1), pp.71-76.
[5] Zhang, X., Zhao, X., Huo, L., Yuan, N., Sun, J., Du, J., Nan, M. and Ji, L., 2020. Risk prediction model of gestational diabetes mellitus based on nomogram in a Chinese population cohort study. Scientific Reports, 10(1), pp.1-7.
[6] Amirian, A., Mahani, M.B. and Abdi, F., 2020. Role of interleukin-6 (IL-6) in predicting gestational diabetes mellitus. Obstetrics & Gynecology Science, 63(4), pp.407-416.
[7] El-Rashidy, N., ElSayed, N.E., El-Ghamry, A. and Talaat, F.M., 2022. Utilizing fog computing and explainable deep learning techniques for gestational diabetes prediction. Neural Computing and Applications, pp.1-20.
[8] Naseem, A., Habib, R., Naz, T., Atif, M., Arif, M. and Allaoua Chelloug, S., 2022. Novel Internet of Things Based Approach Towards Diabetes Prediction Using Deep Learning Models. Frontiers in Public Health, p.2848.
[9] Liu, Y., Wang, Y., Zhang, Y. and Cheng, R., 2021. Detection of Gestational Diabetes Mellitus and Influence on Perinatal Outcomes from B-Mode Ultrasound Images Using Deep Neural Network. Scientific Programming, 2021, pp.1-8.
[10] Davidson, S.J., Susan, J., Britten, F.L., Wolski, P., Sekar, R. and Callaway, L.K., 2021. Fetal ultrasound scans to guide management of gestational diabetes: Improved neonatal outcomes in routine clinical practice. Diabetes Research and Clinical Practice, 173, p.108696.