Evaluation of the effectiveness of a deep learning model based on EfficientNetB3 for differential diagnosis of Alzheimer's disease stages

The purpose of the research is evaluation of the effectiveness of the modified EfficientNetB3 architecture based on transfer deep learning and early stopping methods in medical decision support systems for differential diagnosis of Alzheimer's disease stages.

Methods. To conduct experimental studies, a training dataset was generated, normalized, and augmented. A modified EfficientNetB3 neural network architecture was implemented using transfer learning and early stopping methods in Python. The neural network model was trained.

Results. The classification performance of the trained neural network model was assessed using the Recall, Precision, Specificity, F1-score, and AUC-ROC metrics. Analysis of these metrics revealed that the results achieved by the modified EfficientNetB3 architecture are characterized by significant asymmetry, indicating the highly specialized nature of this model. On the one hand, the model proved to be an effective tool for diagnosing moderate dementia, demonstrating the highest possible AUC value. On the other hand, classification performance for the remaining classes was significantly lower (AUC values for the "No Dementia," "Very Mild Dementia," and "Mild Dementia" classes were 0,87, 0,86, and 0,95, respectively).

Conclusion. Based on the results of the analysis, it can be concluded that the primary practical value of this modification of the EfficientNetB3 architecture lies in its use in heterogeneous ensembles or cascaded diagnostic systems for verifying a specific stage of Alzheimer's disease – moderate dementia – in order to improve the overall system efficiency. This points to the potential for further research in the area of creating highly specialized architectures capable of solving specific subproblems with high accuracy, surpassing general-purpose but less focused approaches.

1. Tkachuk E.A., Astakhova T.A., Rychkova L.V., Bugun O.V. Features of the clinical course of neurodegenerative brain disease caused by mutations in the neurofascyte and succinate dehydrogenase gene: a clinical case. Meditsinskii sovet = Medical Advice. 2023;17(21):122–127. (In Russ.) https://doi.org/10.21518/ms2023-414

2. Bagetta G., Bano D., Scuteri D. Basic, Translational, and Clinical Research on Dementia. International Journal of Molecular Sciences. 2024;25(13):1–6. https://doi.org/10.3390/ijms25136861

3. Zorkina Ya.A., Morozova I.O., Abramova O.V., et al. Application of modern classification systems for the complex diagnosis of Alzheimer's disease. Zhurnal nevrologii i psikhiatrii im. S. S. Korsakova = Journal of Neurology and Psychiatry named after S. S. Korsakov. 2024;124(1):121–127. (In Russ.) https://doi.org/10.17116/jnevro2024124011121

4. Ternovykh I.K., Vorobyov S.V., Yanishevsky S.N., et al. Possibilities and prospects of the magnetic resonance morphometry method in the diagnosis of dementia. Meditsinskii sovet = Medical Council. 2024;18(12):22–30. (In Russ.) https://doi.org/10.21518/ms2024-289

5. Brezhnev A.V., Tomakova R.A., Chernykh E.V. Information system for predicting recurrence of myocardial infarction, implemented as a mobile application. Informatsionnoe obshchestvo = Information Society. 2023;(1):116–126. (In Russ.) https://doi.org/10.52605/16059921_2023_01_116

6. Tomakova R.A., Dzyubin I.A., Brezhnev A.V. A method and algorithm for learning a convolutional neural network designed for an intelligent melanoma recognition system. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2022;12(1):65–83. (In Russ.) https://doi.org/10.21869/2223-1536-2022-12-1-65-83

7. Kiselev A.V., Kuleshova E.A., Tanygin M.O., et al. An analysis of the effectiveness of the U-net architecture for classification and segmentation of glioma on MRI images. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2024;14(3):104–120. (In Russ.) https://doi.org/10.21869/2223-1536-2024-14-3-104-120

8. Patel V. AI-Driven Alzheimer’s Detection Performance Analysis of Pretrained CNN Models on MRI Data. International Journal for Research in Applied Science and Engineering Technology. 2025;13:776–784. https://doi.org/10.22214/ijraset.2025.68354

9. Agarwal P., Jaga-wat V., Jathiswar B., Poonkodi M. Diagnosis of Alzheimer’s Disease Using CNN on MRI Data. Advances in Science and Technology. 2023;124:277–284. https://doi.org/10.4028/p-z04kn

10. Naidu G., Zuva T., Sibanda E. M. A review of evaluation metrics in machine learning algorithms. In: Artificial Intelligence Application in Networks and Systems: Pro-ceedings of 12th Computer Science On-line Conference 2023. Cham: Springer; 2023.

11. Knapińska Z., Mulawka J. Patient-Tailored Dementia Diagnosis with CNN-Based Brain MRI Classification. Applied Sciences. 2025;15. https://doi.org/10.3390/app15094652

12. Azarnova T.V., Pozdnyakov D.A. Application of deep learning methods for classification of Alzheimer's stage based on MRI of the brain. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyi analiz i informatsionnye tekhnologii = Bulletin of Voronezh State University. Series: System analysis and information technologies. 2024;(1):94–103. (In Russ.) https://doi.org/10.17308/sait/1995-5499/2024/1/94-103

13. Jack C.R., Arani A., Borowski B.J., et al. Overview of ADNI MRI. Alzheimer's Dement. 2024;20:7350–7360. https://doi.org/10.1002/alz.14166

14. Ghosh K., Bellinger C., Corizzo R., et al. The class imbalance problem in deep learning. Mach Learn. 2024;113:4845–4901. https://doi.org/10.1007/s10994-022-06268-8

15. Oza P., Sharma P., Patel S., et al. Image Augmentation Techniques for Mammogram Analysis. J. Imaging. 2022;8(141). https://doi.org/10.3390/jimaging8050141

16. Salehi A.W., Khan S., Gupta G., et al.A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Chal-lenges, Future Scope. Sustainability. 2023;(15):5930. https://doi.org/10.3390/su15075930

17. Kiselev A.V., Brusentsev N.S., Kuleshova E.A., Ermakov D.A. A method of access control and safety monitoring at energy facilities of enterprises based on a conveyor neural network model. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2024;14(4):28–46. (In Russ.) https://doi.org/10.21869/2223-1536-2024-14-4-28-46

18. Mishin I.O., Tanygin M.O., Kiselyov A.V., et al. Method of analysis of digitized chest X-rays for differential diagnosis of infectious diseases of the respiratory system. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyi analiz i informatsionnye tekhnologii = Bulletin of Voronezh State University. Series: System analysis and Information technologies. 2024;(4):143–155. (In Russ.) https://doi.org/10.17308/sait/1995-5499/2024/4/143-155

19. Khalid A., Senan E.M., Al-Wagih K., et al. Automatic Analysis of MRI Images for Early Prediction of Alzheimer’s Disease Stages Based on Hybrid Features of CNN and Handcrafted Features. Diagnostics (Basel). 2023;13(9):1654. https://doi.org/10.3390/diagnostics13091654

20. Odusami M., Maskeliūnas R., Damaševičius R., Krilavičius T. Analysis of Features of Alzheimer's Disease: Detection of Early Stage from Functional Brain Changes in Magnetic Resonance Images Using a Finetuned ResNet18 Network. Diagnostics (Basel). 2021;11(6):1071. https://doi.org/10.3390/diagnostics11061071