Detecting Schizophrenia: Low vs High Dimensional Brain Imaging Features
Keywords:
Schizophrenia; feature dimensionality; machine learning; brain grey matter; voxel-based morphometryAbstract
Early detection of schizophrenia is critical to minimize its long-term effects. This study investigates the impact of low-dimensional (Regions of Interest) and high-dimensional features (Voxel-based morphometry) on models’ predictive performance for schizophrenia detection. Using the brain imaging data provided by RAMP, the study investigates the performance of a regularized linear, ensemble, and non-linear models combined with different cross-validation strategies on the low- and high-dimensional feature sets. The results show that the regularized linear model consistently outperforms the ensemble and non-linear models across both feature sets in terms of ROC-AUC, balanced accuracy, and computational efficiency. Our study also reveals that the choice of feature dimensionality does indeed impact schizophrenia detection as the low-dimensional features outperform high-dimensional features across all metrics and models. This suggests that the Regions of Interests, despite their reduced dimensionality and complexity, contain sufficient discriminative information for identifying schizophrenia, whereas the additional detail provided by the Voxel-based morphometry features does not necessarily enhance model performance. Overall, regularized linear model, combined with low-dimensional features and standard cross-validation, offers the most promising results. Using an interpretability tool, we obtained the features that have the most impact on schizophrenia detection with right pallidum grey matter volume being the most influential factor.
Downloads
References
Shanarova, Nadezhda, Marina Pronina, Mikhail Lipkovich, Valery Ponomarev, Andreas Müller, and Juri Kropotov. 2023. "Application of Machine Learning to Diagnostics of Schizophrenia Patients Based on Event-Related Potentials" Diagnostics 13, no. 3: 509. https://doi.org/10.3390/diagnostics13030509
"World Health Organization on schizophrenia", [online] Available: https://www.who.int/news-room/fact-sheets/detail/schizophrenia.
M. Tanveer, J. Jangir, M. A. Ganaie, I. Beheshti, M. Tabish and N. Chhabra, "Diagnosis of Schizophrenia: A Comprehensive Evaluation," in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 3, pp. 1185-1192, March 2023, doi: 10.1109/JBHI.2022.3168357.
Sadeghi, D., Shoeibi, A., Ghassemi, N., Moridian, P., Khadem, A., Alizadehsani, R., ... & Acharya, U. R. (2022). An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works. Computers in Biology and Medicine, 105554.
Febles ES, Ortega MO, Sosa MV, Sahli H (2022) Machine learning techniques for the diagnosis of schizophrenia based on event related potentials. medRxiv
De Rosa A, Fontana A, Nuzzo T, Garofalo M, Di Maio A, Punzo D, Copetti M, Bertolino A, Errico F, Rampino A (2022) Machine learning algorithm unveils glutamatergic alterations in the post-mortem schizophrenia brain. Schizophrenia 8(1):1–16
Sutcubasi B, Metin SZ, Erguzel TT, Metin B, Tas C, Arikan MK, Tarhan N (2019) Anatomical connectivity changes in bipolar disorder and schizophrenia investigated using whole-brain tract-based spatial statistics and machine learning approaches. Neural Comput Appl 31(9):4983–4992
Lei D, Pinaya WH, Young J, van Amelsvoort T, Marcelis M, Donohoe G, Mothersill DO, Corvin A, Vieira S, Huang X (2020) Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual. Hum Brain Mapping 41(5):1119–1135
Yassin W, Nakatani H, Zhu Y, Kojima M, Owada K, Kuwabara H, Gonoi W, Aoki Y, Takao H, Natsubori T (2020) Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis. Transl Psychiatry 10(1):1–11
Edouard D., Antoine G., and Benoît D. (2023). RAMP Challenge - Predict schizophrenia using brain anatomy. Université Paris-Saclay.
Arafa, A., Radad, M., Badawy, M., & El-Fishawy, N. (2021, July). Regularized logistic regression model for cancer classification. In 2021 38th National Radio Science Conference (NRSC) (Vol. 1, pp. 251-261). IEEE.
Kolluri, J., Kotte, V. K., Phridviraj, M. S. B., & Razia, S. (2020, June). Reducing overfitting problem in machine learning using novel L1/4 regularization method. In 2020 4th International Conference on Trends in Electronics and Informatics (ICOEI)(48184) (pp. 934-938). IEEE.
Liu, S., & Hu, T. (2018, November). Parallel random forest algorithm optimization based on maximal information coefficient. In 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) (pp. 1083-1087). IEEE.
Abinaya, S., & Devi, M. K. (2022). Enhancing crop productivity through autoencoder-based disease detection and context-aware remedy recommendation system. In Application of Machine Learning in Agriculture (pp. 239-262). Academic Press.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
Idowu, J. A. (2024). Debiasing Education Algorithms. International Journal of Artificial Intelligence in Education, 1-31.
Thölke, P., Mantilla Ramos, Y. J., Abdelhedi, H., Maschke, C., Dehgan, A., Harel, Y., ... & Jerbi, K. (2022). Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data. bioRxiv, 2022-07.
Schnack, H. G. (2019). Improving individual predictions: machine learning approaches for detecting and attacking heterogeneity in schizophrenia (and other psychiatric diseases). Schizophrenia research, 214, 34-42.
Wang, K. Z., Bani-Fatemi, A., Adanty, C., Harripaul, R., Griffiths, J., Kolla, N., ... & De Luca, V. (2020). Prediction of physical violence in schizophrenia with machine learning algorithms. Psychiatry research, 289, 112960.
Bracher-Smith, M., Rees, E., Menzies, G., Walters, J. T., O'Donovan, M. C., Owen, M. J., ... & Escott-Price, V. (2022). Machine learning for prediction of schizophrenia using genetic and demographic factors in the UK biobank. Schizophrenia research, 246, 156-164.
Tandon, N., & Tandon, R. (2019). Using machine learning to explain the heterogeneity of schizophrenia. Realizing the promise and avoiding the hype. Schizophrenia Research, 214, 70-75
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
