Enhancing Alzheimer’s Disease Diagnosis: Insights from MLP and 1D CNN Models
Resumo
Context: Alzheimer’s Disease (AD) is a complex neurodegenerative disorder that requires early diagnosis to improve patient outcomes. Recent advances in computational intelligence have sparked interest in leveraging machine learning to enhance diagnostic accuracy and efficiency. These innovations are crucial for transforming decision-making within Information Systems in clinical settings. Problem: Traditional methods like PET-scans and cerebrospinal fluid collection are highly accurate but costly and invasive, limiting accessibility. Developing data-driven, non-invasive solutions that retain diagnostic accuracy while handling complex biomedical data, such as plasma protein concentrations, remains a challenge. Solution: This study utilizes neural networks, specifically Multi-Layer Perceptron (MLP) and One-Dimensional Convolutional Neural Network (1D CNN). Preprocessing included Recursive Feature Elimination (RFE) for feature selection and Synthetic Minority Oversampling Technique (SMOTE) for data augmentation, addressing class imbalance. SI Theory: Grounded in Complexity Theory, the study examines how machine learning models can enhance data-driven medical systems by efficiently managing critical, highly sensitive datasets. Method: An experimental quantitative approach was used to evaluate binary and multiclass classifiers on a dataset with 120 protein features from 259 patients. Summary of Results: The MLP exhibited strong performance in specific subsets, achieving superior metrics in the binary classification after feature selection and data augmentation. Meanwhile, the 1D CNN excelled in multiclass classification, leveraging its convolutional layers to extract critical features from subtle protein variations, improving accuracy and robustness. Contributions and Impact on IS Field: This research enhances medical information systems by proposing machine learning models that can be integrated for accurate diagnostics, supporting clinical decision-making and advancing healthcare practices.
Referências
A. Arora, J. E. Alderman, J. Palmer, S. Ganapathi, E. Laws, M. D. McCradden, L. Oakden-Rayner, S. R. Pfohl, M. Ghassemi, F. McKay, D. Treanor, N. Rostamzadeh, B. Mateen, J. Gath, A. O. Adebajo, S. Kuku, R. Matin, K. Heller, E. Sapey, N. J. Sebire, et al. 2023. The value of standards for health datasets in artificial intelligence-based applications. Nature Medicine 29, 11 (2023), 2929–2938. DOI: 10.1038/s41591-023-02608-w
B.M. Bai, N. Mangathayaru, and B.P. Rani. 2015. An Approach to Find Missing Values in Medical Datasets. In International Conference on Engineering & MIS (ICEMIS ’15). ACM, 1–7. DOI: 10.1145/2832987.283308
M-M. Bouamrane, C. Tao, and I. N. Sarkar. 2015. Managing interoperability and complexity in health systems. In Methods of Information in Medicine, Vol. 54. 01–04.
N.V. Chawla, K.W. Bowyer, L.O. Hall, and W.P. Kegelmeyer. 2002. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16 (2002), 321–357.
T. Chen and C. J. Lin. 2021. Feature Selection for Support Vector Machines: An Application to Medical Diagnosis. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 41, 4 (2021), 729–741.
D. Dablain, B. Krawczyk, and N. V. Chawla. 2023. DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data. In Proceedings of the IEEE Transactions on Neural Networks and Learning Systems, Vol. 34. 6390–6404. DOI: 10.1109/TNNLS.2021.3136503
A.P. Dalmagro, C.A. Cazarin, and F.S. Zenaide. 2020. An Update about the Biochemical and Molecular Basis of Alzheimer’s Disease. Brazilian Applied Science Review 4, 1 (2020), 118–130.
L. Dantas and M. Valença. 2013. Utilizando Reservoir Computing para Realizar Diagnóstico Precoce de Mal de Alzheimer. In BRICS Symposium on Biocomputing (SBIC).
H. Davtyan, A. Hovakimyan, and S. et al. Kiani Shabestari. 2019. Testing a MultiTEP-Based Combination Vaccine to Reduce Beta and Tau Pathology in Tau22/5xfad Bigenic Mice. Alzheimer’s Research & Therapy 11 (2019), 107.
Y. Ding, J.H. Sohn, and M.G. et al. Kawczynski. 2018. A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain. Radiology 290, 2 (2018), 456–464.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press.
Forat Falih Hasan and Muhamad Shahbani Abu Bakar. 2021. An Approach for Data Transformation In Homogeneous and Heterogeneous Information Systems. In 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA). 1–5. DOI: 10.1109/HORA52670.2021.9461287
S. Haykin. 2022. Neural Networks and Learning Machines (4th ed.). Pearson.
S. Kiranyaz, O. Avcı, O. Abdeljaber, T. Ince, M. Gabbouj, and D.J. Inman. 2019. 1D Convolutional Neural Networks and Applications: A Survey. arXiv preprint arXiv:1905.03554 (2019). Available at [link].
X. Li and Y. Chen. 2023. Attention-guided CNN for Early Alzheimer’s Detection Using Neuroimaging Data. IEEE Transactions on Medical Imaging 42 (2023), 145–157. DOI: 10.1109/TMI.2023.10898765
Anthony Lins. 2018. Aplicação de Aprendizagem de Máquina no Diagnóstico de Declínio Cognitivo e Demência de Alzheimer Baseado em Testes Cognitivos e Marcadores Genéticos. Ph.D. Dissertation. Universidade Federal Rural de Pernambuco (UFRPE), Recife.
Savanna Machado, Jorge Luis Barbosa, João Tavares, and Márcio Martins. 2021. DCARE: Um Modelo Computacional para Acompanhamento de Pessoas com Doença de Alzheimer baseado na Análise de Históricos de Contextos. In Anais do XVII Simpósio Brasileiro de Sistemas de Informação (Uberlândia). SBC, Porto Alegre, RS, Brasil. [link]
S. Palmqvist, S. Janelidze, and Y.T. et al. Quiroz. 2020. Discriminative Accuracy of Plasma Phospho-Tau217 for Alzheimer Disease vs Other Neurodegenerative Disorders. JAMA 324, 8 (2020), 772–781.
R. S. Rajasree and S. B. Rajakumari. 2024. Exploring Impact of Feature Selection on Classification Models for Detection of Alzheimer’s Disease. In Proceedings of the International Conference on Knowledge Engineering and Communication Systems (ICKECS). Chikkaballapur, India, 1–6.
M.G. Ravetti and P. Moscato. 2008. Identification of a 5-Protein Biomarker Molecular Signature for Predicting Alzheimer’s Disease. PLOS ONE 3 (2008), e3111.
S. Ray, M. Britschgi, C. Herbert, and Y. et al. Takeda-Uchimura. 2007. Classification and Prediction of Clinical Alzheimer’s Diagnosis Based on Plasma Signaling Proteins. Nature Medicine 13 (2007), 1359–1362.
I.R.R. Silva, G.S.L. Silva, R.G. de Souza,W.P. dos Santos, and R.A.A. Fagundes. 2019. Model Based on Deep Feature Extraction for Diagnosis of Alzheimer’s Disease. In International Joint Conference on Neural Networks (IJCNN). IEEE, Budapest, Hungary, 14–19.
A. A. Tahami Monfared, M. J. Byrnes, L. A. White, andQ. Zhang. 2022. Alzheimer’s Disease: Epidemiology and Clinical Progression. Neurology and Therapy 11 (2022), 553–569. DOI: 10.1007/s40120-022-00338-8
M. Timmers, I. Tesseur, J. Bogert, H. Zetterberg, K. Blennow, A. Börjesson-Hanson, M. Baquero, M. Boada, C. Randolph, and L. Tritsmans. 2019. Relevance of the Interplay Between Amyloid and Tau for Cognitive Impairment in Early Alzheimer’s Disease. Neurobiology of Aging 79 (2019), 131–141. DOI: 10.1016/j.neurobiolaging.2019.03.016
M. S. Uddin, A. Al Mamun, M. Rahman, T. Behl, A. Perveen, A. Hafeez, M. N. Bin-Jumah, M. M. Abdel-Daim, and G. M. Ashraf. 2020. Emerging Proof of Protein Misfolding and Interactions in Multifactorial Alzheimer’s Disease. Current Topics in Medicinal Chemistry 20 (2020), 2380–2390. DOI: 10.2174/1568026620666200601161703
World Health Organization (WHO). 2020. WHO Reveals Leading Causes of Death and Disability Worldwide: 2000-2019. World Health Organization, Switzerland. Available at [link].
T. Xia, T. Dang, J. Han, L. Qendro, and C. Mascolo. 2024. Uncertainty-Aware Health Diagnostics via Class-Balanced Evidential Deep Learning. In Proceedings of the IEEE Journal of Biomedical and Health Informatics, Vol. 28. 6417–6428. DOI: 10.1109/JBHI.2024.3360002
