IITM LOGO V17 FILE 1

IITM Journal of Information Technology

ISSN (P) 2395-5457 | Single Blind Peer Reviewed Journal

Published By
INSTITUTE OF INNOVATION IN TECHNOLOGY & MANAGEMENT
Affiliated to GGSIPU, NAAC Grade ‘A’, ISO 14001:2015, 17020:2012, 21001:2018 & 50001:2018 Certified,
A Grade by GNCTD, A++ Grade by SFRC

Next-Gen Healthcare: Generative AI for Personalized Neurodegenerative Disease Intervention

Akella Subhadra
Associate Professor, Department of Computer Science,
Institute of Innovation in Technology and Management Janakpuri, New Delhi 

Abstract: The rising rates of neurodegenerative disorders like Alzheimer’s and Parkinson’s necessitate the adoption of intelligent, personalized, scalable, and adaptable systems of healthcare to meet the growing demand. This paper examines the attempt to apply precision medicine with multi modal generative artificial intelligence (AI) for the proactive and ongoing assessment of neurodegenerative disorders. From a machine learning perspective, our work analyzes how basic clinical tools such as cognitive assessment tests including Mini-Mental State Examination (MMSE) can enhance performance of health predictive models of AI based systems when used alongside other demographic variables like age, gender and educational level. We conducted a statistical analysis on data that was divided into the following four categories: healthy subjects, subjects with mild neurocognitive impairment, moderate neurocognitive impairment, and severe neurocognitive impairment. Analysis of variance revealed a strong negative relationship between the mean MMSE scores and the severity of the condition with mean scores significantly decreasing across stages. Age was shown to strongly negatively influence (r = -0.72) MMSE scores, confirming that older age is a prominent risk factor. Higher levels of education were positively correlated with cognitive scores supporting the cognitive reserve hypothesis while gender did not statistically influence MMSE performance. The study confirms the possibilities associated with simpler computational techniques mean, standard deviation, Pearson correlation evaluation to generate clinically useful information. This chapter concludes by emphasizing the need for more holistic datasets, responsible model building, ethical algorithms, and the embedded computing stream of neural networks that encompass cognitive, behavioral, social, and biological data within generative AI paradigms.

Keywords: Multimodal Generative AI, Neurodegenerative Disease Management, Precision Healthcare, Cognitive Assessment (MMSE), AI in Medical Diagnostics

References:

  1. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," Advances in Neural Information Processing Systems, vol. 27, pp. 2672-2680, 2014.
  2. T. Zhou, M. Liu, K. H. Thung, and D. Shen, "Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease," Neurolmage, vol. 222, p. 117252, 2020, doi: 10.1016/j.neuroimage.2020.117252.
  3. D. Ravi, C. Wong, F. Deligianni, M. Berthelot, J. Andreu-Perez, B. Lo, and G. Z. Yang, "Deep learning for health informatics," IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 1, pp. 4-21, 2017, doi:10.1109/JBHI.2016.2636665.
  4. T. Nguyen, T. Tran, N. Wickramasinghe, and S. Venkatesh, "Multimodal deep learning for early detection of Parkinson's disease," Artificial Intelligence in Medicine, vol. 125, 102144, 2022, doi: 10.1016/j.artmed.2022.102144.
  5. B. Q. Huynh, N. Antropova, M. L. Giger, and K. Suzuki, "Deep learning-based synthetic MR image generation for improved classification of Alzheimer's disease," Medical Physics, vol. 45, no. 8, pp. 3638-3647, 2018, doi: 10.1002/mp.13027.
  6. H. Suresh and J. V. Guttag, "A framework for understanding unintended consequences of machine learning," Communications of the ACM, vol. 64, no. 3, pp. 62-71, 2021, doi:10.1145/3430368.
  7. Y. Wang, Y. Zhou, Z. Tang, C. Li, Y. Wang, and D. Shen, "Cross-modality synthesis of PET images from MRI using CycleGAN," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 5, pp. 2010-2022, 2021, doi:10.1109/TNNLS.2020.2992327.
  8. Z. Che, S. Purushotham, K. Cho, D. Sontag, and Y. Liu, "Recurrent variational autoencoder for multimodal disease progression modeling," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 1, pp. 454-462, 2021, doi:10.1609/aaai.v35i1.16011.
  9. J. Xu, B. S. Glicksberg, C. Su, P. Walker, and R. Chen, "Federated learning for healthcare informatics," Journal of the American Medical Informatics Association, vol. 27, no. 3, pp. 377-386, 2020, doi: 10.1093/jamia/ocz192.
  10. Y. Li, X. Huang, and D. Gifford, "Diffusion-based generative models for simulating disease progression in longitudinal data," Nature Machine Intelligence, vol. 4, pp. 353-362, 2022, doi: 10.1038/s42256-022-00480-w.
  11. Y. Park, G. P. Jackson, M. A. Foreman, and G. E. Rosenthal, "Digital biomarkers in neurodegenerative disease: Implications for multimodal AI in healthcare," NPJ Digital Medicine, vol. 2, Art. no. 96, 2019, doi:10.1038/s41746-019-0181-3.
  12. P. Rajpurkar et al., "Foundation models for generalist medical AI," Nature, vol. 616, pp. 259-265, 2023, doi:10.1038/s41586-023-05840-0.
  13. E. E. Bron et al., "Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge," Neurolmage, vol. 111, pp. 562-579, 2015, doi: 10.1016/j.neuroimage.2015.01.048.
  14. A. Ezzati, M. J. Katz, A. R. Zammit, M. L. Lipton, and R. B. Lipton, "Predicting amyloid status in Alzheimer's disease using machine learning and MRI data," Journal of Alzheimer's Disease, vol. 69, no. 3, pp. 1065-1072, 2019, doi: 10.3233/JAD-181169.
  15. W. H. L. Pinaya, A. Mechelli, and J. R. Sato, "Using deep generative models to generate synthetic structural MRI data for brain disorder classification," Computerized Medical Imaging and Graphics, vol. 89, p. 101882, 2021, doi: 10.1016/j.compmedimag.2021.101882.
  16. D. Bzdok and A. Meyer-Lindenberg, "Machine learning for precision psychiatry: Opportunities and challenges," Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, vol. 3, no. 3, pp. 223-230, 2018, doi: 10.1016/j.bpsc.2017.11.007.
  17. Y. Qiu, S. Zhang, H. Xu, F. Wang, and J. Zhao, "Personalized prediction of Parkinson's disease progression using variational recurrent neural networks," Artificial Intelligence in Medicine, vol. 123, p. 102205, 2022, doi: 10.1016/j.artmed.2021.102205.
  18. C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. J. Cardoso, "Probabilistic segmentation propagation using deep learning for Alzheimer's disease imaging biomarkers," Neurolmage, vol. 199, pp. 93-104, 2019, doi: 10.1016/j.neuroimage.2019.05.016.
  19. L. Zhang, Y. Zhang, Y. Qiao, and Y. Yuan, "Synthesizing PET images from MRI scans using CycleGAN for Alzheimer's disease classification," IEEE Access, vol. 8, pp. 102282-102292, 2020, doi: 10.1109/ACCESS.2020.2999276.
  20. S. Faghih-Roohi, E. Freeman, and P. Tino, "Multimodal deep learning for ALS progression using behavioral and biosignal data," Frontiers in Neurology, vol. 12, p. 624369, 2021, doi: 10.3389/fneur.2021.624369.
  21. S. Sarraf and G. Tofighi, "DeepAD: Alzheimer's disease classification via deep convolutional neural networks using MRI and fMRI," arXiv preprint, arXiv: 1602.05691, 2016, doi: 10.48550/arXiv.1602.05691.
  22. T. Sethi, V. M. P. Namboodiri, and P. Biswas, "FedGAN: Federated adversarial learning for multi-institutional medical data," IEEE Transactions on Medical Imaging, vol. 42, no. 5, pp. 1231-1243, 2023, doi:10.1109/TMI.2023.3247261.
Scroll to Top