Comparative Evaluation of Feature Extraction Methods for GWAS-Based Alzheimer’s Disease Classification
Resumo
Genome-Wide Association Studies (GWAS) generate high-dimensional genetic data that challenge machine learning models and increase susceptibility to overfitting. This study compares linear, nonlinear, and deep learning-based feature extraction methods for Alzheimer’s disease classification using ADNI data. Latent representations combined with demographic risk factors were evaluated via a Random Forest classifier under cross-validation and independent test subsets. Results show that the non-linear Diffusion Maps technique achieved the highest dimensionality reduction while maintaining predictive performance comparable to the baseline model, preserving the essential predictive variance of the original SNP matrix.
Referências
Al-Shoukry, S., Rassem, T. H., and Makbol, N. M. (2020). Alzheimer’s Diseases Detection by Using Deep Learning Algorithms: A Mini-Review. IEEE Access, 8:116122–116133. DOI: 10.1109/ACCESS.2020.2989396.
Alatrany, A. S., Hussain, A. J., Mustafina, J., and Al-Jumeily, D. (2022). Machine Learning Approaches and Applications in Genome Wide Association Study for Alzheimer’s Disease: A Systematic Review. IEEE Access, 10:62402–62423. DOI: 10.1109/ACCESS.2022.3182543.
Berahmand, K., Daneshfar, F., Salehi, E. S., Li, Y., and Xu, Y. (2024). Autoencoders and their applications in machine learning: a survey. Artificial Intelligence Review, 57(3):1–38.
Borah, K., Das, H. S., Seth, S., Mallick, K., Rahaman, Z., and Mallik, S. (2024). A review on advancements in feature selection and feature extraction for high-dimensional NGS data analysis. Functional & Integrative Genomics, 24(5):155. DOI: 10.1007/s10142-024-01415-x.
Bro, R., Acar, E., and Kolda, T. G. (2008). Resolving the sign ambiguity in the singular value decomposition. Journal of Chemometrics, 22(2):135–140. DOI: 10.1002/cem.1122.
Coifman, R. R. and Lafon, S. (2006). Diffusion maps. Applied and Computational Harmonic Analysis, 21(1):5–30. DOI: 10.1016/j.acha.2006.04.003.
Dehbozorgi, P., Ryabchykov, O., and Bocklitz, T. W. (2025). A comparative study of statistical, radiomics, and deep learning feature extraction techniques for medical image classification in optical and radiological modalities. Computers in Biology and Medicine, 186:109768.
Fridman, C., Gregório, S. P., Neto, E. D., and Élida P. Benquique Ojopi (2004). Alterações genéticas na doença de Alzheimer. Arch. Clin. Psychiatry (São Paulo), 31(1):19–25. DOI: 10.1590/S0101-60832004000100004.
Khanal, S., Chen, J., Jacobs, N., and Lin, A.-L. (2021). Alzheimer’s Disease Classification Using Genetic Data. In Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 1112–1117. DOI: 10.1109/BIBM52615.2021.9669730.
Kingma, D. P. and Welling, M. (2014). Auto-encoding variational bayes. In Proceedings of the International Conference on Learning Representations (ICLR), pages 1–14. arXiv preprint arXiv:1312.6114. Disponível em: [link].
Labory, J., Njomgue-Fotso, E., and Bottini, S. (2024). Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data. Computational and Structural Biotechnology Journal, 23:1274–1287. DOI: 10.1016/j.csbj.2024.03.016.
Lee, D. D. and Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755):788–791. DOI: 10.1038/44565.
Malik, I., Iqbal, A., Gu, Y. H., and Al-antari, M. A. (2024). Deep learning for Alzheimer’s Disease Prediction: A Comprehensive Review. Diagnostics, 14(12):1281. DOI: 10.3390/diagnostics14121281.
Marees, A. T., de Kluiver, H., Stringer, S., Vorspan, F., Curis, E., Marie-Claire, C., and Derks, E. M. (2018). A tutorial on conducting genome-wide association studies: Quality control and statistical analysis. International Journal of Methods in Psychiatric Research, 27(2):e1608. DOI: 10.1002/mpr.1608.
Najar, J., van der Lee, S. J., Joas, E., Wetterberg, H., Hardy, J., Guerreiro, R., Bras, J., Waern, M., Kern, S., Zetterberg, H., Blennow, K., Skoog, I., and Zettergren, A. (2021). Polygenic risk score for alzheimer’s disease is related to dementia risk in individuals with negative apoe ε4 allele. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring, 13(1):e12142. PMCID: PMC7821873, PMID: 33532541.
Nasr, M. K., König, E., Fuchsberger, C., Ghasemi, S., , et al. (2025). Removing array-specific batch effects in GWAS mega-analyses by applying a two-step imputation workflow. Bioinformatics Advances, 6(1):vbaf317. DOI: 10.1093/bioadv/vbaf317.
Pölsterl, S., Conjeti, S., Navab, N., and Katouzian, A. (2016). Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection. Artificial Intelligence in Medicine, 72:1–11. DOI: 10.1016/j.artmed.2016.07.004.
Saykin, A. J., Shen, L., Yao, X., Kim, S., Nho, K., Risacher, S. L., Ramanan, V. K., Foroud, T. M., Faber, K. M., Sarwar, N., Munsie, L. M., Hu, X., Soares, H. D., Potkin, S. G., Thompson, P. M., Kauwe, J. S. K., Kaddurah-Daouk, R., Green, R. C., Toga, A. W., and Weiner, M. W. (2015). Genetic studies of quantitative MCI and AD phenotypes in ADNI: Progress, Opportunities, and Plans. Alzheimers Dement., 11(7):792–814.
Scheltens, P., De Strooper, B., Kivipelto, M., Holstege, H., Chételat, G., Teunissen, C. E., Cummings, J., and van der Flier, W. M. (2021). Alzheimer’s disease. The Lancet, 397(10284):1577–1590. DOI: 10.1016/S0140-6736(20)32205-4.
Schölkopf, B., Smola, A., and Müller, K.-R. (1998). Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation, 10(5):1299–1319. DOI: 10.1162/089976698300017467.
Smid, J., Studart-Neto, A., César-Freitas, K. G., Dourado, M. C. N., Kochhann, R., Barbosa, B. J. A. P., Schilling, L. P., Balthazar, M. L. F., Frota, N. A. F., de Souza, L. C., Caramelli, P., Bertolucci, P. H. F., Chaves, M. L. F., Brucki, S. M. D., Nitrini, R., de Paula França Resende, E., and Vale, F. A. C. (2022). Declínio cognitivo subjetivo, comprometimento cognitivo leve e demência - diagnóstico sindrômico: recomendações do Departamento Científico de Neurologia Cognitiva e do Envelhecimento da Academia Brasileira de Neurologia. Dement. neuropsychol., 16(3 suppl 1):1–16. DOI: 10.1590/1980-5764-DN-2022-S101PT.
Squillario, M., Abate, G., Tomasi, F., Tozzo, V., Barla, A., and Uberti, D. (2020). A telescope GWAS analysis strategy, based on SNPs-genes-pathways ensamble and on multivariate algorithms, to characterize late onset Alzheimer’s disease. Scientific Reports, 10(1):12063. DOI: 10.1038/s41598-020-67699-8.
Zou, H., Hastie, T., and Tibshirani, R. (2006). Sparse Principal Component Analysis. Journal of Computational and Graphical Statistics, 15(2):265–286. DOI: 10.1198/106186006X113430.
Alatrany, A. S., Hussain, A. J., Mustafina, J., and Al-Jumeily, D. (2022). Machine Learning Approaches and Applications in Genome Wide Association Study for Alzheimer’s Disease: A Systematic Review. IEEE Access, 10:62402–62423. DOI: 10.1109/ACCESS.2022.3182543.
Berahmand, K., Daneshfar, F., Salehi, E. S., Li, Y., and Xu, Y. (2024). Autoencoders and their applications in machine learning: a survey. Artificial Intelligence Review, 57(3):1–38.
Borah, K., Das, H. S., Seth, S., Mallick, K., Rahaman, Z., and Mallik, S. (2024). A review on advancements in feature selection and feature extraction for high-dimensional NGS data analysis. Functional & Integrative Genomics, 24(5):155. DOI: 10.1007/s10142-024-01415-x.
Bro, R., Acar, E., and Kolda, T. G. (2008). Resolving the sign ambiguity in the singular value decomposition. Journal of Chemometrics, 22(2):135–140. DOI: 10.1002/cem.1122.
Coifman, R. R. and Lafon, S. (2006). Diffusion maps. Applied and Computational Harmonic Analysis, 21(1):5–30. DOI: 10.1016/j.acha.2006.04.003.
Dehbozorgi, P., Ryabchykov, O., and Bocklitz, T. W. (2025). A comparative study of statistical, radiomics, and deep learning feature extraction techniques for medical image classification in optical and radiological modalities. Computers in Biology and Medicine, 186:109768.
Fridman, C., Gregório, S. P., Neto, E. D., and Élida P. Benquique Ojopi (2004). Alterações genéticas na doença de Alzheimer. Arch. Clin. Psychiatry (São Paulo), 31(1):19–25. DOI: 10.1590/S0101-60832004000100004.
Khanal, S., Chen, J., Jacobs, N., and Lin, A.-L. (2021). Alzheimer’s Disease Classification Using Genetic Data. In Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 1112–1117. DOI: 10.1109/BIBM52615.2021.9669730.
Kingma, D. P. and Welling, M. (2014). Auto-encoding variational bayes. In Proceedings of the International Conference on Learning Representations (ICLR), pages 1–14. arXiv preprint arXiv:1312.6114. Disponível em: [link].
Labory, J., Njomgue-Fotso, E., and Bottini, S. (2024). Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data. Computational and Structural Biotechnology Journal, 23:1274–1287. DOI: 10.1016/j.csbj.2024.03.016.
Lee, D. D. and Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755):788–791. DOI: 10.1038/44565.
Malik, I., Iqbal, A., Gu, Y. H., and Al-antari, M. A. (2024). Deep learning for Alzheimer’s Disease Prediction: A Comprehensive Review. Diagnostics, 14(12):1281. DOI: 10.3390/diagnostics14121281.
Marees, A. T., de Kluiver, H., Stringer, S., Vorspan, F., Curis, E., Marie-Claire, C., and Derks, E. M. (2018). A tutorial on conducting genome-wide association studies: Quality control and statistical analysis. International Journal of Methods in Psychiatric Research, 27(2):e1608. DOI: 10.1002/mpr.1608.
Najar, J., van der Lee, S. J., Joas, E., Wetterberg, H., Hardy, J., Guerreiro, R., Bras, J., Waern, M., Kern, S., Zetterberg, H., Blennow, K., Skoog, I., and Zettergren, A. (2021). Polygenic risk score for alzheimer’s disease is related to dementia risk in individuals with negative apoe ε4 allele. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring, 13(1):e12142. PMCID: PMC7821873, PMID: 33532541.
Nasr, M. K., König, E., Fuchsberger, C., Ghasemi, S., , et al. (2025). Removing array-specific batch effects in GWAS mega-analyses by applying a two-step imputation workflow. Bioinformatics Advances, 6(1):vbaf317. DOI: 10.1093/bioadv/vbaf317.
Pölsterl, S., Conjeti, S., Navab, N., and Katouzian, A. (2016). Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection. Artificial Intelligence in Medicine, 72:1–11. DOI: 10.1016/j.artmed.2016.07.004.
Saykin, A. J., Shen, L., Yao, X., Kim, S., Nho, K., Risacher, S. L., Ramanan, V. K., Foroud, T. M., Faber, K. M., Sarwar, N., Munsie, L. M., Hu, X., Soares, H. D., Potkin, S. G., Thompson, P. M., Kauwe, J. S. K., Kaddurah-Daouk, R., Green, R. C., Toga, A. W., and Weiner, M. W. (2015). Genetic studies of quantitative MCI and AD phenotypes in ADNI: Progress, Opportunities, and Plans. Alzheimers Dement., 11(7):792–814.
Scheltens, P., De Strooper, B., Kivipelto, M., Holstege, H., Chételat, G., Teunissen, C. E., Cummings, J., and van der Flier, W. M. (2021). Alzheimer’s disease. The Lancet, 397(10284):1577–1590. DOI: 10.1016/S0140-6736(20)32205-4.
Schölkopf, B., Smola, A., and Müller, K.-R. (1998). Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation, 10(5):1299–1319. DOI: 10.1162/089976698300017467.
Smid, J., Studart-Neto, A., César-Freitas, K. G., Dourado, M. C. N., Kochhann, R., Barbosa, B. J. A. P., Schilling, L. P., Balthazar, M. L. F., Frota, N. A. F., de Souza, L. C., Caramelli, P., Bertolucci, P. H. F., Chaves, M. L. F., Brucki, S. M. D., Nitrini, R., de Paula França Resende, E., and Vale, F. A. C. (2022). Declínio cognitivo subjetivo, comprometimento cognitivo leve e demência - diagnóstico sindrômico: recomendações do Departamento Científico de Neurologia Cognitiva e do Envelhecimento da Academia Brasileira de Neurologia. Dement. neuropsychol., 16(3 suppl 1):1–16. DOI: 10.1590/1980-5764-DN-2022-S101PT.
Squillario, M., Abate, G., Tomasi, F., Tozzo, V., Barla, A., and Uberti, D. (2020). A telescope GWAS analysis strategy, based on SNPs-genes-pathways ensamble and on multivariate algorithms, to characterize late onset Alzheimer’s disease. Scientific Reports, 10(1):12063. DOI: 10.1038/s41598-020-67699-8.
Zou, H., Hastie, T., and Tibshirani, R. (2006). Sparse Principal Component Analysis. Journal of Computational and Graphical Statistics, 15(2):265–286. DOI: 10.1198/106186006X113430.
Publicado
19/10/2026
Como Citar
CARVALHO, Bruna B. F. de; OLIVEIRA, Arysson S. de; OLIVEIRA, Rodrigo F. A. P. de; BEZERRA, Diego de F..
Comparative Evaluation of Feature Extraction Methods for GWAS-Based Alzheimer’s Disease Classification. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 3095-3106.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.31153.
