LSTM Algorithm in Predicting Chronic Kidney Disease Optimized Using Genetic Algorithm

Brillyando Magathan Achmad; Siti Sa'adah; Isman Kurniawan

doi:10.30595/juita.v12i2.22965

Authors

Brillyando Magathan Achmad Telkom University
Siti Sa'adah Telkom University
Isman Kurniawan Telkom University

DOI:

https://doi.org/10.30595/juita.v12i2.22965

Keywords:

Long Short-Term Memory, Genetic Algorithm, chronic kidney disease

Abstract

Chronic Kidney Disease is a health condition in which the kidneys experience a progressive decline in function. Kidneys are vital organs that filter waste and excess blood fluids. CKD can lead to excess products in the body and cause various health issues, so early detection of CKD is necessary. While traditional machine learning techniques have performed well in predicting CKD in existing studies, this study investigates the potential of long short-term memory (LSTM) optimized with Genetic Algorithm to enhance predictive accuracy and efficiency by optimizing its hyperparameters, including number of units, hidden layers, activation function, recurrent activation, and dropout rate. The result demonstrates that the optimized LSTM slightly performs better than without optimization, achieving higher precision, recall, accuracy, and f1 score by 100% respectively. This outstanding result can be attributed to several key factors, such as ensuring rigorous data preprocessing and utilizing k-fold cross-validation to make the model more reliable. This indicates the hybrid approach can be a powerful method for the early detection of CKD, leading to better patient outcomes. Despite the promising performance, further research is suggested, specifically using a larger dataset to ensure applicability to more general population and exploring other optimization methods to reduce computational cost.

Author Biographies

Brillyando Magathan Achmad, Telkom University

Faculty of Informatics

Siti Sa'adah, Telkom University

Faculty of Informatics

Isman Kurniawan, Telkom University

Faculty of Informatics

References

[1] C. P. Kovesdy, “Epidemiology of chronic kidney disease: an update 2022,” Kidney Int Suppl (2011), vol. 12, no. 1, pp. 7–11, Apr. 2022, doi: 10.1016/j.kisu.2021.11.003.

[2] V. Singh, V. K. Asari, and R. Rajasekaran, “A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease.,” Diagnostics (Basel), vol. 12, no. 1, Jan. 2022, doi: 10.3390/diagnostics12010116.

[3] J. Radhakrishnan, G. Remuzzi, R. Saran, D.E. Williams, N. Rios-Burrows, N. Powe, CDC-CKD Surveillance Team, K. Brück, C. Wanner, V. S. Stel, European CKD Burden Consortium 6, S. K. Venuthurupalli, W. E. Hoy, H. G. Healy, A. Salisbury, R. G. Fasset, CKD.QLD group, D. O’Donoghue, P. Roderick, S. Matsuo, A. Hishida, E. Imai, and S. Iimuro, “Taming the chronic kidney disease epidemic: a global view of surveillance efforts,” Kidney Int, vol. 86, no. 2, pp. 246–250, Aug. 2014, doi: 10.1038/ki.2014.190.

[4] J. Radhakrishnan and S. Mohan, “KI Reports and World Kidney Day,” Kidney Int Rep, vol. 2, no. 2, pp. 125–126, Mar. 2017, doi: 10.1016/j.ekir.2017.01.014.

[5] K. J. Jager, C. Kovesdy, R. Langham, M. Rosenberg, V. Jha, and C. Zoccali, “A single number for advocacy and communication—worldwide more than 850 million individuals have kidney diseases,” Kidney Int, vol. 96, no. 5, pp. 1048–1050, Nov. 2019, doi: 10.1016/j.kint.2019.07.012.

[6] K. J. Foreman, N. Marques, A. Dolgert, K. Fukutaki, N. Fullman, M. McGaughey, M. A. Pletcher, A. E. Smith, K. Tang, C. Yuan, J. C. Brown, J. Friedman, J. He, K. R. Heuton, M. Holmberg, D. J. Patel, P. Reidy, A. Carter, K. Cercy, A. Chapin, D. Douwes-Schultz, T. Frank, F. Goettsch, P. Y. Liu, V. Nandakumar, M. B. Reitsma, V. Reuter, N. Sadat, R. J. D. Sorensen, V. Srinivasan, R. L. Updike, H. York, A. D. Lopez, R. Lozano, S. S. Lim, A. H. Mokdad, S. E. Vollset, and C. J. L. Murray, “Forecasting life expectancy, years of life lost, and all-cause and cause-specific mortality for 250 causes of death: reference and alternative scenarios for 2016–40 for 195 countries and territories,” The Lancet, vol. 392, no. 10159, pp. 2052–2090, Nov. 2018, doi: 10.1016/S0140-6736(18)31694-5.

[7] J. Neves, M. R. Martins, J. Vilhena, J. Neves, S. Gomes, A. Abelha, J. Machado, and H. Vicente, “A Soft Computing Approach to Kidney Diseases Evaluation,” J Med Syst, vol. 39, no. 10, p. 131, Oct. 2015, doi: 10.1007/s10916-015-0313-4.

[8] G. R. Vasquez-Morales, S. M. Martinez-Monterrubio, P. Moreno-Ger, and J. A. Recio-Garcia, “Explainable Prediction of Chronic Renal Disease in the Colombian Population Using Neural Networks and Case-Based Reasoning,” IEEE Access, vol. 7, pp. 152900–152910, 2019, doi: 10.1109/ACCESS.2019.2948430.

[9] C. Cortes and V. Vapnik, “Support-vector networks,” Mach Learn, vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.

[10] L. Breiman, “Random forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[11] N. Bhaskar and M. Suchetha, “A Computationally Efficient Correlational Neural Network for Automated Prediction of Chronic Kidney Disease,” IRBM, vol. 42, no. 4, pp. 268–276, Aug. 2021, doi: 10.1016/j.irbm.2020.07.002.

[12] S. Krishnamurthy, K. Ks, E. Dovgan, M. Luštrek, B. G. Piletič, K. Srinivasan, Y. J. Li, A. Gradišek, and S. Syed-Abdul, “Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan,” Healthcare, vol. 9, no. 5, p. 546, May 2021, doi: 10.3390/healthcare9050546.

[13] H. Ilyas, S. Ali, M. Ponum, O. Hasan, M. T. Mahmood, M. Iftikhar, and M. H. Malik, “Chronic kidney disease diagnosis using decision tree algorithms,” BMC Nephrol, vol. 22, no. 1, p. 273, Dec. 2021, doi: 10.1186/s12882-021-02474-z.

[14] J. C. T. Arroyo and A. J. P. Delima, “An Optimized Neural Network Using Genetic Algorithm for Cardiovascular Disease Prediction,” Journal of Advances in Information Technology, vol. 13, no. 1, 2022, doi: 10.12720/jait.13.1.95-99.

[15] X. Zang, J. Du, and Y. Song, “Early Prediction of Heart Disease via LSTM-XGBoost,” in Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence, New York, NY, USA: ACM, Mar. 2023, pp. 631–637. doi: 10.1145/3594315.3594383.

[16] P. Dileep, K. N. Rao, P. Bodapati, S. Gokuruboyina, R. Peddi, A. Grover, and Anu, “An automatic heart disease prediction using cluster-based bi-directional LSTM (C-BiLSTM) algorithm,” Neural Comput Appl, vol. 35, no. 10, pp. 7253–7266, Apr. 2023, doi: 10.1007/s00521-022-07064-0.

[17] Eswaran, L. R. P. S. (2015). Chronic kidney disease [Data set]. UCI Machine Learning Repository. doi: 10.24432/C5G020.

[18] S. K. Kwak and J. H. Kim, “Statistical data preparation: management of missing values and outliers,” Korean J Anesthesiol, vol. 70, no. 4, p. 407, 2017, doi: 10.4097/kjae.2017.70.4.407.

[19] G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artif Intell Rev, vol. 53, no. 8, pp. 5929–5955, Dec. 2020, doi: 10.1007/s10462-020-09838-1.

[20] D. Saif, A. M. Sarhan, and N. M. Elshennawy, “Deep-kidney: an effective deep learning framework for chronic kidney disease prediction,” Health Inf Sci Syst, vol. 12, no. 1, p. 3, Dec. 2023, doi: 10.1007/s13755-023-00261-8.

[21] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929–1958, 2014. https://dl.acm.org/doi/10.5555/2627435.2670313.

[22] S. Koçer and M. R. Canal, “Classifying Epilepsy Diseases Using Artificial Neural Networks and Genetic Algorithm,” J Med Syst, vol. 35, no. 4, pp. 489–498, Aug. 2011, doi: 10.1007/s10916-009-9385-3.

[23] P. R. V. Terlapu, D. Jayaram, S. Rakesh, M. V. Gopalachari, B. V. Ramana, N. Tangudu, and K. R. Kalidindi, “Optimizing Chronic Kidney Disease Diagnosis in Uddanam: A Smart Fusion of GA-MLP Hybrid and PCA Dimensionality Reduction,” Procedia Comput Sci, vol. 230, pp. 522–531, 2023, doi: 10.1016/j.procs.2023.12.108.