A Comparative Analysis of Lightweight Deep Learning Models for CT-Based Kidney Disease Classification to Support Early Detection in Geriatric Care
Downloads
Kidney diseases, including cysts, stones, and tumors, are common among older adults and often progress asymptomatically, leading to delayed diagnoses. Manual interpretation of CT images by clinicians is labor-intensive and can vary significantly between observers, especially in high-volume settings. This study aims to develop and evaluate an artificial intelligence–based decision support system for multiclass kidney disease classification with an emphasis on robustness, computational efficiency, and clinical feasibility in elderly healthcare environments. The study proposes a medical informatics evaluation framework that integrates standard performance metrics with learning dynamics, overfitting analysis, and error distribution assessments to ensure reliable model selection. Three architectures were evaluated: a conventional CNN, MobileNet-V2, and EfficientNet-B0. Experiments were conducted on a publicly available dataset containing 12,446 CT images across four classes (Normal, Cyst, Stone, and Tumor). Models were trained under varying epoch settings and evaluated using weighted accuracy, precision, recall, F1-score, AUC, learning curve analysis, and confusion matrix assessment. The results indicate that the conventional CNN achieved perfect numerical performance but exhibited rapid convergence and early metric saturation, limiting the interpretability of generalization under the current dataset configuration. EfficientNet-B0 showed stable yet conservative performance, whereas MobileNet-V2 achieved near-optimal accuracy with gradual convergence, minimal overfitting, and superior computational efficiency. At the optimal configuration (epoch 50), MobileNet-V2 achieved an accuracy of 1.00, precision of 1.00, recall of 1.00, F1-score of 1.00, and an AUC of 0.9997. These findings suggest that lightweight architectures, particularly MobileNet-V2, offer a practical solution for CT-based kidney disease decision support, while acknowledging the need for patient-level and multi-institutional validation.
[1] H. Bouarich, A. Chávez Guillén, and D. Rodríguez Puyol, “Kidney and hypertension in older adults,” Medicina Clínica (English Edition), vol. 157, no. 4, pp. 178–184, Aug. 2021, doi: 10.1016/j.medcle.2021.02.005.
[2] D. Mekahli et al., “Clinical practice recommendations for kidney involvement in tuberous sclerosis complex: a consensus statement by the ERKNet Working Group for Autosomal Dominant Structural Kidney Disorders and the ERA Genes & Kidney Working Group,” Nat. Rev. Nephrol., vol. 20, no. 6, pp. 402–420, Jun. 2024, doi: 10.1038/s41581-024-00818-0.
[3] G. Alfano et al., “Rethinking Chronic Kidney Disease in the Aging Population,” ., vol. 12, no. 11, p. 1724, Oct. 2022, doi: 10.3390/life12111724.
[4] Z. Chen et al., “Comprehensive 3D Analysis of the Renal System and Stones: Segmenting and Registering Non-Contrast and Contrast Computed Tomography Images,” Information Systems Frontiers, vol. 27, no. 1, pp. 97–111, Feb. 2025, doi: 10.1007/s10796-024-10485-y.
[5] G. Sharma, V. Anand, R. Chauhan, H. S. Pokhariya, S. Gupta, and G. Sunil, “Revolutionizing Kidney Disease Diagnosis: A Comprehensive CNN-Based Framework for Multi-Class CT Classification,” in 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE, Jun. 2024, pp. 1–6. doi: 10.1109/ICITEICS61368.2024.10624992.
[6] R. Kumar et al., “Intelligence Architectures and Machine Learning Applications in Contemporary Spine Care,” Bioengineering, vol. 12, no. 9, p. 967, Sep. 2025, doi: 10.3390/bioengineering12090967.
[7] M. N. Hossain, E. Bhuiyan, M. B. A. Miah, T. A. Sifat, Z. Muhammad, and M. F. Al Masud, “Detection and Classification of Kidney Disease from CT Images: An Automated Deep Learning Approach,” Technologies (Basel)., vol. 13, no. 11, p. 508, Nov. 2025, doi: 10.3390/technologies13110508.
[8] T. Biloborodova, B. Brosnan, I. Skarga-Bandurova, and D. J. Strauss, “Generalization Ability in Medical Image Analysis with Small-Scale Imbalanced Datasets: Insights from Neural Network Learning,” 2023, pp. 234–246. doi: 10.1007/978-3-031-49011-8_19.
[9] S. C. Haynes, P. Johnston, and E. Elyan, “Generalisation challenges in deep learning models for medical imagery: insights from external validation of COVID-19 classifiers,” Multimed. Tools Appl., vol. 83, no. 31, pp. 76753–76772, Feb. 2024, doi: 10.1007/s11042-024-18543-y.
[10] I. E. Tampu, A. Eklund, and N. Haj-Hosseini, “Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images,” Sci. Data, vol. 9, no. 1, p. 580, Sep. 2022, doi: 10.1038/s41597-022-01618-6.
[11] I. D. Mienye and T. G. Swart, “A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications,” Information, vol. 15, no. 12, p. 755, Nov. 2024, doi: 10.3390/info15120755.
[12] B. Almadani, H. Kaisar, I. R. Thoker, and F. Aliyu, “A Systematic Survey of Distributed Decision Support Systems in Healthcare,” Systems, vol. 13, no. 3, p. 157, Feb. 2025, doi: 10.3390/systems13030157.
[13] S. Sanchez-Martinez et al., “Machine Learning for Clinical Decision-Making: Challenges and Opportunities in Cardiovascular Imaging,” Front. Cardiovasc. Med., vol. 8, Jan. 2022, doi: 10.3389/fcvm.2021.765693.
[14] G. Menghani, “Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better,” ACM Comput. Surv., vol. 55, no. 12, pp. 1–37, Dec. 2023, doi: 10.1145/3578938.
[15] L. J. Basile, N. Carbonara, R. Pellegrino, and U. Panniello, “Business intelligence in the healthcare industry: The utilization of a data-driven approach to support clinical decision making,” Technovation, vol. 120, p. 102482, Feb. 2023, doi: 10.1016/j.technovation.2022.102482.
[16] A. S. Mahmoud, O. Lamouchi, and S. Belghith, “Advancements in Machine Learning and Deep Learning for Early Diagnosis of Chronic Kidney Diseases: A Comprehensive Review,” Babylonian Journal of Machine Learning, vol. 2024, pp. 149–156, Sep. 2024, doi: 10.58496/BJML/2024/015.
[17] M. Gharaibeh et al., “Radiology Imaging Scans for Early Diagnosis of Kidney Tumors: A Review of Data Analytics-Based Machine Learning and Deep Learning Approaches,” Big Data and Cognitive Computing, vol. 6, no. 1, p. 29, Mar. 2022, doi: 10.3390/bdcc6010029.
[18] G. Jeyalakshmi, F. V. Lloyd, K. Subbulakshmi, and G. Vinudevi, “A Deep Learning Approach for Predicting Chronic Kidney Disease in Electronic Health Records in Neural Nephrology,” 2024, pp. 197–216. doi: 10.4018/979-8-3693-8659-0.ch011.
[19] M. Rashid and M. Sharma, “AI‐Assisted Diagnosis and Treatment Planning A Discussion of How AI Can Assist Healthcare Professionals in Making More Accurate Diagnoses and Treatment Plans for Diseases,” in AI in Disease Detection, Wiley, 2025, pp. 313–336. doi: 10.1002/9781394278695.ch14.
[20] M. T. Islam, M. A. Rahman, Md. T. R. Mazumder, and S. H. Shourov, “COMPARATIVE ANALYSIS OF NEURAL NETWORK ARCHITECTURES FOR MEDICAL IMAGE CLASSIFICATION: EVALUATING PERFORMANCE ACROSS DIVERSE MODELS,” American Journal of Advanced Technology and Engineering Solutions, vol. 04, no. 01, pp. 01–42, Mar. 2024, doi: 10.63125/feed1x52.
[21] F. Mohr and J. N. van Rijn, “Learning curves for decision making in supervised machine learning: a survey,” Mach. Learn., vol. 113, no. 11–12, pp. 8371–8425, Dec. 2024, doi: 10.1007/s10994-024-06619-7.
[22] M. Aljaafari, S. E. El-Deep, A. A. Abohany, and S. E. Sorour, “Integrating Innovation in Healthcare: The Evolution of ‘CURA’s’ AI-Driven Virtual Wards for Enhanced Diabetes and Kidney Disease Monitoring,” IEEE Access, vol. 12, pp. 126389–126414, 2024, doi: 10.1109/ACCESS.2024.3451369.
[23] A. Padhi, A. Agarwal, S. K. Saxena, and C. D. S. Katoch, “Transforming clinical virology with AI, machine learning and deep learning: a comprehensive review and outlook,” Virusdisease, vol. 34, no. 3, pp. 345–355, Sep. 2023, doi: 10.1007/s13337-023-00841-y.
[24] K. Blagec, J. Kraiger, W. Frühwirt, and M. Samwald, “Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals,” J. Biomed. Inform., vol. 137, p. 104274, Jan. 2023, doi: 10.1016/j.jbi.2022.104274.
[25] D. Vrbaški, B. Vesin, and K. Mangaroska, “Machine Learning for Chronic Kidney Disease Detection from Planar and SPECT Scintigraphy: A Scoping Review,” Applied Sciences, vol. 15, no. 12, p. 6841, Jun. 2025, doi: 10.3390/app15126841.
[26] H. Bechinia, D. Benmerzoug, and N. Khlifa, “Approach Based Lightweight Custom Convolutional Neural Network and Fine-Tuned MobileNet-V2 for ECG Arrhythmia Signals Classification,” IEEE Access, vol. 12, pp. 40827–40841, 2024, doi: 10.1109/ACCESS.2024.3378730.
[27] E. Tasci, Y. Zhuge, K. Camphausen, and A. V. Krauze, “Bias and Class Imbalance in Oncologic DataTowards Inclusive and Transferrable AI in Large Scale Oncology Data Sets,” Cancers (Basel)., vol. 14, no. 12, p. 2897, Jun. 2022, doi: 10.3390/cancers14122897.
[28] A. Alsajri and A. V. Hacimahmud, “Review of deep learning: Convolutional Neural Network Algorithm,” Babylonian Journal of Machine Learning, vol. 2023, pp. 19–25, Apr. 2023, doi: 10.58496/BJML/2023/004.
[29] L. Shen, Y. Sun, Z. Yu, L. Ding, X. Tian, and D. Tao, “On Efficient Training of Large-Scale Deep Learning Models,” ACM Comput. Surv., vol. 57, no. 3, pp. 1–36, Mar. 2025, doi: 10.1145/3700439.
[30] H. Polat and H. Danaei Mehr, “Classification of Pulmonary CT Images by Using Hybrid 3D-Deep Convolutional Neural Network Architecture,” Applied Sciences, vol. 9, no. 5, p. 940, Mar. 2019, doi: 10.3390/app9050940.
[31] L. Zhao and Z. Zhang, “A improved pooling method for convolutional neural networks,” Sci. Rep., vol. 14, no. 1, p. 1589, Jan. 2024, doi: 10.1038/s41598-024-51258-6.
[32] I. Salehin and D.-K. Kang, “A Review on Dropout Regularization Approaches for Deep Neural Networks within the Scholarly Domain,” Electronics (Basel)., vol. 12, no. 14, p. 3106, Jul. 2023, doi: 10.3390/electronics12143106.
[33] J. Glory Precious, S. P. Angeline Kirubha, and I. Keren Evangeline, “Deployment of a Mobile Application Using a Novel Deep Neural Network and Advanced Pre-Trained Models for the Identification of Brain Tumours,” IETE J. Res., vol. 69, no. 10, pp. 6902–6914, Oct. 2023, doi: 10.1080/03772063.2022.2083027.
[34] M. Kia, S. Sadeghi, H. Safarpour, M. Kamsari, S. Jafarzadeh Ghoushchi, and R. Ranjbarzadeh, “Innovative fusion of VGG16, MobileNet, EfficientNet, AlexNet, and ResNet50 for MRI-based brain tumor identification,” Iran Journal of Computer Science, vol. 8, no. 1, pp. 185–215, Mar. 2025, doi: 10.1007/s42044-024-00216-6.
[35] M. Reyad, A. M. Sarhan, and M. Arafa, “A modified Adam algorithm for deep neural network optimization,” Neural Comput. Appl., vol. 35, no. 23, pp. 17095–17112, Aug. 2023, doi: 10.1007/s00521-023-08568-z.
[36] M. Reyad, A. M. Sarhan, and M. Arafa, “A modified Adam algorithm for deep neural network optimization,” Neural Comput. Appl., vol. 35, no. 23, pp. 17095–17112, Aug. 2023, doi: 10.1007/s00521-023-08568-z.
[37] R. Chandrasekaran, F. Asgareinjad, J. Morris, and T. Rosing, “Multi-Label Classification With Hyperdimensional Representations,” IEEE Access, vol. 11, pp. 108458–108474, 2023, doi: 10.1109/ACCESS.2023.3299881.
[38] N. Sampathila et al., “Customized Deep Learning Classifier for Detection of Acute Lymphoblastic Leukemia Using Blood Smear Images,” Healthcare, vol. 10, no. 10, p. 1812, Sep. 2022, doi: 10.3390/healthcare10101812.
[39] H. Li, G. K. Rajbahadur, D. Lin, C.-P. Bezemer, and Z. M. Jiang, “Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting,” IEEE Access, vol. 12, pp. 70676–70689, 2024, doi: 10.1109/ACCESS.2024.3402543.
[40] K. M. Sujon, R. Hassan, K. Choi, and M. A. Samad, “Accuracy, precision, recall, f1-score, or MCC? empirical evidence from advanced statistics, ML, and XAI for evaluating business predictive models,” J. Big Data, vol. 12, no. 1, p. 268, Dec. 2025, doi: 10.1186/s40537-025-01313-4.
[41] C. Mosquera, L. Ferrer, D. H. Milone, D. Luna, and E. Ferrante, “Class imbalance on medical image classification: towards better evaluation practices for discrimination and calibration performance,” Eur. Radiol., vol. 34, no. 12, pp. 7895–7903, Jun. 2024, doi: 10.1007/s00330-024-10834-0.
[42] J. Bernett et al., “Guiding questions to avoid data leakage in biological machine learning applications,” Nat. Methods, vol. 21, no. 8, pp. 1444–1453, Aug. 2024, doi: 10.1038/s41592-024-02362-y.
[43] M. Bausch et al., “Distinct neuronal populations in the human brain combine content and context,” Nature, vol. 650, no. 8102, pp. 690–700, Feb. 2026, doi: 10.1038/s41586-025-09910-2.
[44] A. M. Duhaim, N. S. Baqer, and M. A. Fadhel, “Developing a trustworthy and explainable framework for classifying skin lesions through transfer learning and attention mechanisms,” Comput. Biol. Chem., vol. 122, p. 108914, Jun. 2026, doi: 10.1016/j.compbiolchem.2026.108914.
[45] W. Obaid, A. Hussain, T. Rabie, D. H. Abd, and W. Mansoor, “Multi-model deep learning approach for the classification of kidney diseases using medical images,” Inform. Med. Unlocked, vol. 57, p. 101663, 2025, doi: 10.1016/j.imu.2025.101663.
[46] R. Hou, J. Y. Lo, J. R. Marks, E. S. Hwang, and L. J. Grimm, “Classification performance bias between training and test sets in a limited mammography dataset,” PLoS One, vol. 19, no. 2, p. e0282402, Feb. 2024, doi: 10.1371/journal.pone.0282402.
[47] N. Rachburee and W. Punlumjeak, “Lotus species classification using transfer learning based on VGG16, ResNet152V2, and MobileNetV2,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, p. 1344, Dec. 2022, doi: 10.11591/ijai.v11.i4.pp1344-1352.
[48] A. Mohi, L. Kareem, and A. A. Hassan, “EfficientNet-B0 Deep Learning Model for Accurate Classification of Intrabony Lesions in Dental Panoramic Radiographs,” May 05, 2025. doi: 10.21203/rs.3.rs-6207574/v1.
[49] L. K. Singh, M. Khanna, H. Monga, R. singh, and G. Pandey, “Nature-Inspired Algorithms-Based Optimal Features Selection Strategy for COVID-19 Detection Using Medical Images,” New Gener. Comput., vol. 42, no. 4, pp. 761–824, Nov. 2024, doi: 10.1007/s00354-024-00255-4.
[50] Y. Canbay, S. Adsiz, and P. Canbay, “Privacy-Preserving Transfer Learning Framework for Kidney Disease Detection,” Applied Sciences, vol. 14, no. 19, p. 8629, Sep. 2024, doi: 10.3390/app14198629.
[51] E. A. Refaee, “Digital transformation in healthcare: leveraging machine learning for predictive analytics in chronic kidney diseases prevention,” Journal of Innovative Digital Transformation, vol. 2, no. 3, pp. 217–232, Nov. 2025, doi: 10.1108/JIDT-03-2025-0012.
[52] S. D. Pande and R. Agarwal, “Multi-Class Kidney Abnormalities Detecting Novel System Through Computed Tomography,” IEEE Access, vol. 12, pp. 21147–21155, 2024, doi: 10.1109/ACCESS.2024.3351181.
[53] K. Eskandar, “Artificial Intelligence in CT Imaging: A Systematic Review of Diagnostic Accuracy, Clinical Decision–Support Impact, and Integration Pathways,” iRADIOLOGY, vol. 3, no. 6, pp. 434–445, Dec. 2025, doi: 10.1002/ird3.70046.
[54] R. Tenchov, J. M. Sasso, X. Wang, and Q. A. Zhou, “Aging Hallmarks and Progression and Age-Related Diseases: A Landscape View of Research Advancement,” ACS Chem. Neurosci., vol. 15, no. 1, pp. 1–30, Jan. 2024, doi: 10.1021/acschemneuro.3c00531.
[55] D. M. Connaughton and A. J. Mallett, “Models of Care for the Implementation of Genetic Testing in Nephrology,” Semin. Nephrol., vol. 45, no. 5, p. 151649, Sep. 2025, doi: 10.1016/j.semnephrol.2025.151649.
[56] M. S. Hossain, S. M. Nazmul Hassan, M. Al-Amin, Md. N. Rahaman, R. Hossain, and M. I. Hossain, “Kidney Disease Detection from CT Images using a customized CNN model and Deep Learning,” in 2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS), IEEE, Feb. 2023, pp. 1–6. doi: 10.1109/AICAPS57044.2023.10074314.
[57] F. E. Ekpar, “Image-based Chronic Kidney Disease Diagnosis Using 2D Convolutional Neural Networks in the Context of a Comprehensive Artificial Intelligence-Driven Healthcare System,” MOLECULAR SCIENCES AND APPLICATIONS, vol. 4, pp. 135–143, Nov. 2024, doi: 10.37394/232023.2024.4.13.
[58] M. N. Hossain, E. Bhuiyan, M. B. A. Miah, T. A. Sifat, Z. Muhammad, and M. F. Al Masud, “Detection and Classification of Kidney Disease from CT Images: An Automated Deep Learning Approach,” Technologies (Basel)., vol. 13, no. 11, p. 508, Nov. 2025, doi: 10.3390/technologies13110508.
Copyright (c) 2026 Ardha Ardhana Putra Agustavada, Aji Prasetya Wibawa, Abdullah Sholum, Dafa Fadhilah Hilmi, Felix Andika Dwiyanto (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
