Exploring Deep Learning Approaches for Early Detection of Chronic Kidney Disease: Trends and Techniques

Abdus Samad; Mir Ahmad Khan; Aaqib Iqbal; Inam Ullah Khan; Arif Ali

Authors

Abdus Samad Department of Computer Science & IT Abasyn University Islamabad Campus
Mir Ahmad Khan Department of Computer Science & IT University of Lakki Marwat
Aaqib Iqbal Department of Mathematics Abdul Wali Khan University Mardan 23200, Pakistan
Inam Ullah Khan Department of Computer Science & IT University of Lakki Marwat
Arif Ali Department of Plant Sciences, Quaid-I-Azam University, Islamabad, 45320, Pakistan.

Keywords:

RNN, CKD, Deep Learning, ANN, LSTM, Performance Optimization, CNN

Abstract

This study investigates the application of deep learning models, namely CNN, RNNs, and MLP, for the early prediction of CKD. Early detection of CKD is critical for initiating timely treatment, as the disease can advance with few symptoms. The research leverages a preprocessed Kaggle dataset, divided for training and testing, to assess model performance. Among the models, CNN achieved an impressive 99% accuracy, highlighting its strong feature extraction capabilities. The RNN and MLP models also demonstrated high accuracy, reinforcing the potential of deep learning in enhancing CKD screening processes. This approach can support more personalized and preventive healthcare, potentially improving patient outcomes through earlier interventions.

Keywords: RNN, CKD, Deep Learning, CNN, ANN, LSTM, Performance Optimization

Abbreviation

Full Form

CKD

Chronic Kidney Disease

CNN

Convolutional Neural Network

RNN

Recurrent Neural Network

MLP

Multi-Layer Perceptron

ANN

Artificial Neural Network

LSTM

Long Short-Term Memory (a type of RNN)

References

S. K. P. and A. S. G. Shukla, G. Dhuriya, “CKD Prediction Using Machine Learning Algorithms and the Important Attributes for the Detection,” IEEE IAS Glob. Conf. Emerg. Technol. (GlobConET), London, United Kingdom, pp. 1–4, 2023, doi: 10.1109/GlobConET56651.2023.10149900.

and N. A. A. Rehman, T. Saba, H. Ali, N. Elhakim, “Hybrid machine learning model to predict CKDs using handcrafted features for early health rehabilitation,” Turkish J. Electr. Eng. Comput. Sci., vol. 31, 2023, doi: 10.55730/1300-0632.4028.

M. Z. H. B. P. Ghosh, Touhid Imam, Nishat Anjum, Md Tuhin Mia, Cynthia Ummay Siddiqua, Kazi Shaharair Sharif, Md Munsur Khan, Md Atikul Islam Mamun, “Advancing CKD Prediction: Comparative Analysis of Machine Learning Algorithms and a Hybrid Model,” J. Comput. Sci. Technol. Stud., vol. 6, no. 3, pp. 15–21, 2024, doi: https://doi.org/10.32996/jcsts.2024.6.3.2.

and V. N. R. Sawhney, A. Malik, S. Sharma, “A comparative assessment of artificial intelligence models used for early prediction and evaluation of CKD,” Decis. Anal. J., vol. 6, p. 100169, 2023, doi: https://doi.org/10.1016/j.dajour.2023.100169.

S. K. David SK, Rafiullah M, “Comparison of Different Machine Learning Techniques to Predict Diabetic Kidney Disease,” J Heal. Eng, 2022, doi: 10.1155/2022/7378307.

P. K. M. Swapnita Srivastava , Rajesh Kumar Yadav , Vipul Narayan, “An ensemble learning approach for CKD classification,” J. Pharm. Negat. Results, vol. 13, no. 10, 2022, doi: https://doi.org/10.47750/pnr.2022.13.S10.279.

and Z. A. H. Iftikhar, M. Khan, Z. Khan, F. Khan, H. M. Alshanbari, “A Comparative Analysis of Machine Learning Models: A Case Study in Predicting CKD,” Sustainability, vol. 15, no. 3, p. 2754, 2023, doi: 10.3390/su15032754.

and M. S. Q. H. Khalid, A. Khan, M. Zahid Khan, G. Mehmood, “Machine Learning Hybrid Model for the Prediction of CKD,” Comput. Intell. Neurosci., 2023, doi: 10.1155/2023/9266889.

X. C. Zheyi Dong, Qian Wang , Yujing Ke , Weiguang Zhang , Quan Hong , Chao Liu , Xiaomin Liu , Jian Yang , Yue Xi , Jinlong Shi , Li Zhang , Ying Zheng , Qiang Lv , Yong Wang , Jie Wu , Xuefeng Sun , Guangyan Cai , Shen Qiao , Chengliang Yin , Shibin Su, “Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records,” J. Transl. Med., vol. 20, no. 1, p. 143, 2022, doi: 10.1186/s12967-022-03339-1.

M. M. H. Muhammad Minoar Hossain, Reshma Ahmed Swarna, Rafid Mostafiz, Pabon Shaha, Lubna Yasmin Pinky, Mohammad Motiur Rahman, Wahidur Rahman, Md. Selim Hossain, Md. Elias Hossain, “Analysis of the performance of feature optimization techniques for the diagnosis of machine learning-based CKD,” Mach. Learn. with Appl., vol. 19, p. 100330, 2022, doi: https://doi.org/10.1016/j.mlwa.2022.100330.

R. R. Vijendra Singh, Vijayan K Asari, “A Deep Neural Network for Early Detection and Prediction of CKD,” Diagnostics, vol. 12, no. 1, p. 116, 2022, doi: 10.3390/diagnostics12010116.

J. C. Xin-Yue Ge , Zhong-Kai Lan , Qiao-Qing Lan , Hua-Shan Lin , Guo-Dong Wang, “Diagnostic accuracy of ultrasound-based multimodal radiomics modeling for fibrosis detection in CKD,” Eur Radiol, vol. 33, no. 4, pp. 2386–2398, 2023, doi: https://pubmed.ncbi.nlm.nih.gov/36454259/.

D. A. D. and T. M. Sitote, “CKD prediction using machine learning techniques,” J. Big Data, 2022, doi: https://doi.org/10.1186/s40537-022-00657-5.

M. A. H. Md Ariful Islam, Md Ziaul Hasan Majumder, “CKD prediction based on machine learning algorithms,” J Pathol Inf., vol. 14, p. 100189, 2023, doi: 10.1016/j.jpi.2023.100189.

and M. H. V. K. Venkatesan, M. T. Ramakrishna, I. Izonin, R. Tkachenko, “Efficient Data Preprocessing with Ensemble Machine Learning Technique for the Early Detection of CKD,” Appl. Sci., vol. 13, no. 5, p. 2885, 2023, doi: 10.3390/app13052885.

and S. M. N. E. C. Jang, Y. M. Park, H. W. Han, C. S. Lee, E. S. Kang, Y. H. Lee, “Machine-learning enhancement of urine dipstick tests for CKD detection,” J. Am. Med. Informatics Assoc., vol. 30, no. 1, 2023, doi: 10.1093/jamia/ocad051.

and R. U. Y. Dubey, P. Mange, Y. Barapatre, B. Sable, P. Palsodkar, “Unlocking precision medicine for prognosis of CKD using machine learning,” Diagnostics, vol. 13, no. 19, p. 3151, 2023, doi: https://doi.org/10.3390/diagnostics13193151.

S. M. K. and S. Z. B. Jame, “Comparing the Performance of Machine Learning Models in Predicting the Risk of CKD,” J. Arch. Mil. Med., vol. 11, no. 4, 2024, doi: 10.5812/jamm-140885.

M. M. E. Chi D Chu, Fang Xia , Yuxian Du , Rakesh Singh , Delphine S Tuot , Julio A Lamprea-Montealegre , Ralph Gualtieri , Nick Liao , Sheldon X Kong , Todd Williamson , Michael G Shlipak, “Estimated Prevalence and Testing for Albuminuria in US Adults at Risk for CKD,” JAMA Netw Open, vol. 6, no. 7, p. 2326230, 2023, doi: 10.1001/jamanetworkopen.2023.26230.

T. M. S. Dibaba Adeba Debal, “CKD prediction using machine learning techniques,” J. Big Data, 2022, doi: https://doi.org/10.1186/s40537-022-00657-5.

and J. H. M. M. Rahman, M. Al-Amin, “Machine learning models for CKD diagnosis and prediction,” Biomed. Signal Process. Control, vol. 87, p. 105368, 2024, doi: https://doi.org/10.1016/j.bspc.2023.105368.

K. S. and G. V. Krishna, “Prediction of CKD with Various Machine Learning Techniques: A Comparative Study,” Smart Technol. Data Sci. Commun., pp. 257–262, 2023, doi: 10.1007/978-981-19-6880-8_27.

and N. M. E. D. Saif, A. M. Sarhan, “Deep-kidney: an effective deep learning framework for CKD prediction,” Heal. Inf. Sci. Syst., vol. 12, no. 1, p. 3, 2023, doi: 10.1007/s13755-023-00261-8.

and Y. J. Y. Zhu, D. Bi, M. Saunders, “Prediction of CKD progression using RNN and electronic health records,” Sci. Rep., vol. 13, no. 1, 2023, doi: 10.1038/s41598-023-49271-2.

and N. G. M. A. Abdel-Fattah, N. A. Othman, and N. Goher[25] M. A. Abdel-Fattah, N. A. Othman, “Predicting CKD Using Hybrid Machine Learning Based on Apache Spark,” Comput. Intell. Neurosci., vol. 15, pp. 1–12, 2022, doi: 10.1155/2022/9898831.

and K. P. F. Chen, P. Kantagowit, T. Nopsopon, A. Chuklin, “Prediction and diagnosis of CKD development and progression using machine-learning: Protocol for a systematic review and meta-analysis of reporting standards and model performance,” PLoS One, vol. 18, no. 2, p. 0278729, 2023, doi: 10.1371/journal.pone.0278729.

and K. G. B. N. Swamy, R. Nakka, A. Sharma, S. P. Praveen, V. N. Thatha, “An Ensemble Learning Approach for detection of CKD ,” J. Intell. Syst. Internet Things, vol. 10, no. 2, pp. 38–48, 2023, doi: 10.54216/JISIoT.100204.

Y. L. Qiong Bai , Chunyan Su , Wen Tang, “Machine learning to predict end stage kidney disease in CKD,” Sci. Rep., vol. 12, no. 1, p. 8377, 2022, doi: 10.1038/s41598-022-12316-z.

E. A. and A. C. Öztürk, “CKD Prediction with Stacked Ensemble-Based Model,” Alpha J. Eng. Appl. Sci., vol. 1, no. 1, pp. 50–61, 2023, [Online]. Available: https://dergipark.org.tr/en/pub/ajeas/issue/82301/1397219

M. A. H. Md. Ariful Islam, Md. Ziaul Hasan Majumder, “CKD prediction based on machine learning algorithms,” J. Pathol. Inform., vol. 14, p. 100189, 2023, doi: https://doi.org/10.1016/j.jpi.2023.100189.

B. M. and S. P. Terdal, “A Review On Early Detection Of CKD,” J. Sci. Res. Technol., 2024, doi: 10.61808/jsrt96.

Y. G. Ye Zixiang, Shuoyan An, “The prediction of in-hospital mortality in CKD patients with coronary artery disease using machine learning models,” Eur. J. Med. Res., vol. 28, no. 1, 2023, doi: 10.1186/s40001-023-00995-x.

E. T. Nitasha Khan , Muhammad Amir Raza , Nayyar Hussain Mirjat , Neelam Balouch , Ghulam Abbas , Amr Yousef, “Unveiling the predictive power: a comprehensive study of machine learning model for anticipating CKD,” Front. Artif. Intell., vol. 6, p. 1339988, 2024, doi: 10.3389/frai.2023.1339988.