A Study on Adopting Machine Learning to Develop Predictive Models for Diabetes

Nafees Akhter Farooqui; Saquib Ali; Raza Abbas  Haidri; Mazhar Khaliq

doi:10.65890/race.v2i2.195

Authors

Nafees Akhter Farooqui Department of Computer Application, Integral University, Lucknow
Saquib Ali Department of Computer Science and Information Technology, Khwaja Moinuddin Chishti Language University, Lucknow, India
Raza Abbas Haidri Department of Computer Science and Information Technology, Khwaja Moinuddin Chishti Language University, Lucknow, India
Mazhar Khaliq Department of Computer Science and Information Technology, Khwaja Moinuddin Chishti Language University, Lucknow, India

DOI:

https://doi.org/10.65890/race.v2i2.195

Keywords:

Diabetes, Neural Network, LightGBM, LDE, KNN, Machine Learning, PCA, Predictive models

Abstract

High blood sugar can harm the body's organs over time. In addition to issues with the kidneys, eyes, mouth, feet, and nerves, blood vessel damage can lead to heart attacks and strokes. Therefore, using machine learning to anticipate diabetes can assist physicians in making final decisions and initiating therapy. Models such as LightGBM, LDA, KNN, and neural networks were developed during this study. After evaluation, the neural network model performed well, achieving 90% accuracy, a balanced F1 score, and the maximum possible KS statistic of 0.8074. The dataset was pre-processed using techniques such as PCA, random undersampling, standard scaling, label encoding, and manual encoding. GridSearchCV was used to tune the models during training. In addition, the study underscores the real-world implications of implementing machine-learning-based diabetes prediction models in healthcare settings. These models can be trained using various preprocessing techniques, feature selection, and hyperparameter optimization methods, which further improve prediction accuracy and create a scalable framework for clinical decision support systems. The evaluation shows that neural networks can learn the complex, non-linear relationships present in patient data and have demonstrated greater sensitivity to early signs of diabetes. The integration can help healthcare providers to monitor patients in a more proactive way, create more customized treatment plans, and intervene on time, all of which will lead to better health outcomes and minimize the possibility of long-term diabetes complications.

References

[1] A. Hasan, M. M. Islam, M. A. Alam, and M. R. Islam, “A weighted ensemble approach for diabetes prediction using machine learning techniques,” IEEE Access, vol. 8, pp. 152135–152146, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.2989857

[2] S. Sivaranjani and S. Sivakumar, “Prediction of diabetes using machine learning algorithms,” Procedia Computer Science, vol. 167, pp. 1415–1424, 2021.

[3] J. Khanam and S. Y. Foo, “A comparison of machine learning algorithms for diabetes prediction,” ICT Express, vol. 7, no. 4, pp. 432–439, 2021. DOI: https://doi.org/10.1016/j.icte.2021.02.004

[4] M. Khaleel and A. Al-Bakry, “Machine learning techniques for diabetes diagnosis using Pima Indian dataset,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 2, pp. 55–63, 2023.

[5] D. Choubey, S. Paul, and S. Kumar, “Classification techniques for diabetes prediction using PCA and LDA,” Journal of Medical Systems, vol. 44, no. 6, pp. 1–12, 2020.

[6] H. Yu, Y. Zhang, and X. Li, “Deep learning-based clinical prediction models for diabetes diagnosis,” Scientific Reports, vol. 13, no. 1, pp. 1–14, 2023.

[7] A. Swapna, S. Vinayakumar, and K. P. Soman, “Diabetes detection using deep learning algorithms,” ICT Express, vol. 4, no. 4, pp. 243–246, 2018. DOI: https://doi.org/10.1016/j.icte.2018.10.005

[8] S. Perveen, M. Shahbaz, A. Guergachi, and K. Keshavjee, “Performance analysis of data mining classification techniques to predict diabetes,” Procedia Computer Science, vol. 82, pp. 115–121, 2016. DOI: https://doi.org/10.1016/j.procs.2016.04.016

[9] R. Sisodia and S. Sisodia, “Prediction of diabetes using classification algorithms,” Procedia Computer Science, vol. 132, pp. 1578–1585, 2018. DOI: https://doi.org/10.1016/j.procs.2018.05.122

[10] M. Kavakiotis et al., “Machine learning and data mining methods in diabetes research,” Computational and Structural Biotechnology Journal, vol. 15, pp. 104–116, 2017. DOI: https://doi.org/10.1016/j.csbj.2016.12.005

[11] N. Nai-Arun and R. Moungmai, “Comparison of classifiers for the risk of diabetes prediction,” Procedia Computer Science, vol. 69, pp. 132–142, 2015. DOI: https://doi.org/10.1016/j.procs.2015.10.014

[12] J. A. Tigga and S. Garg, “Prediction of type 2 diabetes using machine learning classification methods,” Procedia Computer Science, vol. 167, pp. 706–716, 2020. DOI: https://doi.org/10.1016/j.procs.2020.03.336

[13] P. Sonar and K. JayaMalini, “Diabetes prediction using different machine learning approaches,” International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 9, pp. 2274–2279, 2019.

[14] A. Aljumah, M. G. Ahamad, and M. K. Siddiqui, “Application of data mining: Diabetes healthcare in young and old patients,” Journal of King Saud University-Computer and Information Sciences, vol. 25, no. 2, pp. 127–136, 2013. DOI: https://doi.org/10.1016/j.jksuci.2012.10.003

[15] A. Dinh, M. Miertschin, A. Young, and S. D. Mohanty, “A data-driven approach to predicting diabetes and cardiovascular disease with machine learning,” BMC Medical Informatics and Decision Making, vol. 19, no. 1, pp. 1–15, 2019. DOI: https://doi.org/10.1186/s12911-019-0918-5

[16] J. Wu, Y. Zhang, and W. Zhang, “Predictive modeling of diabetes using machine learning techniques,” Healthcare Analytics, vol. 2, pp. 100–112, 2022.

[17] S. Deo, “Machine learning in medicine,” Circulation, vol. 132, no. 20, pp. 1920–1930, 2015. DOI: https://doi.org/10.1161/CIRCULATIONAHA.115.001593

[18] A. Iyer, S. Jeyalatha, and R. Sumbaly, “Diagnosis of diabetes using classification mining techniques,” International Journal of Data Mining & Knowledge Management Process, vol. 5, no. 1, pp. 1–14, 2015. DOI: https://doi.org/10.5121/ijdkp.2015.5101

[19] H. Naz and S. Ahuja, “Deep learning approach for diabetes prediction using PIMA Indian dataset,” Journal of Diabetes & Metabolic Disorders, vol. 19, no. 1, pp. 391–403, 2020. DOI: https://doi.org/10.1007/s40200-020-00520-5

[20] M. Fatima and M. Pasha, “Survey of machine learning algorithms for disease diagnostic,” Journal of Intelligent Learning Systems and Applications, vol. 9, no. 1, pp. 1–16, 2017. DOI: https://doi.org/10.4236/jilsa.2017.91001

[21] T. M. Alam, M. A. Iqbal, Y. Ali, A. Wahab, M. Ijaz, and T. Imran, “A model for early prediction of diabetes,” Informatics in Medicine Unlocked, vol. 16, p. 100204, 2019. DOI: https://doi.org/10.1016/j.imu.2019.100204

[22] R. G. S. Prasad and Y. H. Rao, “Performance analysis of machine learning algorithms for diabetes prediction,” International Journal of Engineering and Advanced Technology, vol. 9, no. 3, pp. 150–156, 2020.

[23] M. Goyal and R. B. Knopp, “Artificial neural network-based diabetes prediction system,” Expert Systems with Applications, vol. 137, pp. 107–118, 2019.

[24] K. Polat and S. Güneş, “An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease,” Digital Signal Processing, vol. 17, no. 4, pp. 702–710, 2007. DOI: https://doi.org/10.1016/j.dsp.2006.09.005

[25] F. Zou, L. Shen, Z. Jie, W. Zhang, and W. Liu, “A sufficient condition for convergences of Adam and RMSProp,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11127–11135. DOI: https://doi.org/10.1109/CVPR.2019.01138

[26] N. A. Farooqui, R. Mehra, and A. Tyagi, “Prediction model for diabetes mellitus using machine learning techniques,” International Journal of Computer Sciences and Engineering, vol. 6, no. 3, pp. 292–296, 2018. DOI: https://doi.org/10.26438/ijcse/v6i3.292296

[27] Ahmed, R., Varshney, A., Ashraf, Z., Farooqui, N. A., & Pathak, R. S. (2024). Enhanced stroke risk prediction: a fusion of machine learning models for improved healthcare strategies. SN Computer Science, 5(8), 1078. DOI: https://doi.org/10.1007/s42979-024-03389-w

[28] Olisah, C. C., Smith, L., & Smith, M. (2022). Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective. Computer Methods and Programs in Biomedicine, 220, 106773. DOI: https://doi.org/10.1016/j.cmpb.2022.106773