Authors : Ajeet Singh; Akash Tiwari; Dr. Manju Pandey; Dr. Avneesh Kumar; Shubham Goutam; Dr. Devendra Kumar Rawat; Vinay Vipin Tripathi

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/45kycbz4

Scribd : https://tinyurl.com/yw448p54

DOI : https://doi.org/10.38124/ijisrt/25dec048

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Mild Cognitive Impairment (MCI) is in an intermediate state between normal aging and dementia, the early detection of which is particularly important for early treatment and better prognosis. Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) have indeed considerably improved the capabilities of detecting subtle cognitive, behavioral and neurobiological alterations linked to MCI. In this comprehensive review, we analyze the recent AI and ML methods employed in predicting MCI as well as detecting MCI and cover implementations of artificial intelligence assisted disease detection from supervised learning, unsupervised learning to deep learning models across various heterogeneous datasets like neuroimaging, cognitive assessment scores, speech patterns, genetic biomarkers data a-3 nd digital behavioral data. Mild Cognitive Impairment (MCI) is in an intermediate state between normal aging and dementia, the early detection of which is particularly important for early treatment and better prognosis. Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) have indeed considerably improved the capabilities of detecting subtle cognitive, behavioral and neurobiological alterations linked to MCI. In this comprehensive review, we analyse the recent AI and ML methods employed in predicting MCI as well as detecting MCI and cover implementations of artificial intelligence assisted disease detection from supervised learning, unsupervised learning to deep learning models across various heterogeneous datasets like neuroimaging, cognitive assessment scores, speech patterns, genetic biomarkers data a- 3 nd digital behavioral data. This review also points out obstacles—such as data inconsistency, small dataset sizes, bias in algorithms, and difficulty in interpreting models—that impede clinical application. Nonetheless, existing trends suggest significant potential for AI- driven systems to assist healthcare providers, improve screening processes, and facilitate real-time monitoring via digital health instruments. In the end, AI and machine learning present hopeful opportunities for early identification, prognosis, and prevention of mild cognitive impairment, aiding in more effective long-term management of cognitive health.

Keywords : Artificial Intelligence, Machine Learning, Mild Cognitive Impairment, Early Detection, Prediction Models, Neuroimaging.

References :

1. Petersen, R. C. (2004). Mild cognitive impairment as a diagnostic entity. Journal of Internal Medicine, 256(3), 183–194.
2. Petersen, R. C., Smith, G. E., Waring, S. C., Ivnik, R. J., Tangalos, E. G., & Kokmen, E. (1999). Mild cognitive impairment: clinical characterization and outcome. Archives of Neurology, 56(3), 303–308.
3. Jack, C. R., Jr., Bennett, D. A., Blennow, K., Carrillo, M. C., Dunn, B., Haeberlein, S. B., ... & Sperling, R. (2018). NIA-AA Research Framework: Toward a biological definition of Alzheimer’s disease. Alzheimer’s & Dementia, 14(4), 535–562.
4. Mueller, S. G., Weiner, M. W., Thal, L. J., Petersen, R. C., Jack, C., Jagust, W., ... & Beckett, L. (2005). The Alzheimer’s Disease Neuroimaging Initiative. Neuroimaging Clinics of North America, 15(4), 869–877.
5. Venugopalan, J., Tong, L., Hassanzadeh, B., & Damaraju, E. (2021). Multimodal deep learning models for early detection of Alzheimer’s disease using MRI and PET. Scientific Reports, 11, 1–14.
6. Weiner, M. W., Veitch, D. P., Aisen, P. S., Beckett, L. A., Cairns, N. J., Green, R. C., ... & Trojanowski, J. Q. (2013). The Alzheimer’s Disease Neuroimaging Initiative: A review of papers published since its inception. Alzheimer’s & Dementia, 9(5), e111–e194.
7. Sperling, R. A., Rentz, D. M., Johnson, K. A., Karlawish, J., Donohue, M., Salmon, D. P., & Aisen, P. S. (2014). The A4 study: Stopping AD before symptoms begin? Science Translational Medicine, 6(228), 228fs13.
8. Jack, C. R., Jr., Knopman, D. S., Jagust, W. J., Petersen, R. C., Weiner, M. W., Aisen, P. S., ... & Trojanowski, J. Q. (2013). Tracking pathophysiological processes in Alzheimer’s disease: An updated hypothetical model of dynamic biomarkers. The Lancet Neurology, 12(2), 207–216.
9. Blennow, K., Zetterberg, H., & Fagan, A. M. (2012). Fluid biomarkers in Alzheimer disease. Cold Spring Harbor Perspectives in Medicine, 2(9), a006283.
10. Frisoni, G. B., Fox, N. C., Jack, C. R., Jr., Scheltens, P., & Thompson, P. M. (2010). The clinical use of structural MRI in Alzheimer disease. Nature Reviews Neurology, 6(2), 67–77.
11. Small, G. W., et al. (2006). PET of brain amyloid and tau in mild cognitive impairment. The New England Journal of Medicine, 354(3), 250–260.
12. Bevilacqua, R., et al. (2023). Radiomics and artificial intelligence for the diagnosis and prognosis of Alzheimer's disease: A systematic review. Journal of Clinical Medicine, 12(16), 5432.
13. Singh, S. G., et al. (2024). Early Alzheimer’s disease detection: a review of machine learning approaches. Diagnostics, 14(16), 1759.
14. Mohammed, E. M., et al. (2024). Detection of Alzheimer’s disease using deep learning models — systematic review. Heliyon / Data Science Reviews
15. Odusami, M., et al. (2023). Explainable deep-learning-based diagnosis of Alzheimer’s disease. Biomedical Engineering Letters, 13(3), 463–480.
16. Jiao, F., et al. (2023). Tau PET radiomics analysis for predicting progression from MCI to AD. Journal of Nuclear Medicine / Radiology Research.
17. Zhang, Y., et al. (2025). Radiomics of PET using neural networks for prediction in Alzheimer’s disease. Statistics in Medicine.
18. Venkatraman, V., et al. (2019). Deep learning in neuroimaging: A review of recent advances and future directions. Frontiers in Neuroscience, 13, 1–19.
19. Huang, Y., Xu, J., Zhou, Y., & Zhuang, X. (2019). Diagnosis of Alzheimer’s disease via multi-modality 3D convolutional neural network using ADNI. arXiv preprint arXiv:1902.09904.
20. Beare, R., et al. (2020). Graph neural networks for brain network classification in Alzheimer’s disease. NeuroImage, 223, 117352.
21. Li, Y., et al. (2025). A radiomics model predicts progression from MCI to AD: large-scale validation using ADNI. Scientific Reports.
22. Gao, H., et al. (2025). Comparison of radiomics and conventional SUVR methods for Aβ PET analysis. Frontiers in Neurology.
23. Kale, M., et al. (2024). AI-driven innovations in Alzheimer’s disease: Integrating multi-modal biomarkers and clinical data. Artificial Intelligence in Medicine, 132, 102--- (review).
24. AlHarkan, K., et al. (2024). Artificial intelligence approaches for early detection of mild cognitive impairment and dementia: A review. Journal of Clinical Neuroscience / PMC.
25. Rasi, R., et al. (2024). Predicting amyloid positivity from FDG-PET using radiomics and machine learning. European Journal of Nuclear Medicine and Molecular Imaging.
26. Hao, J., et al. (2024). Early detection of dementia through retinal imaging and deep learning (Eye-AD). NPJ Digital Medicine.
27. Lohner, V., et al. (2025). Machine learning approaches to vascular neuroimaging and cognitive impairment. Alzheimer’s Research & Therapy.
28. Quek, L. J. V., et al. (2023). Use of artificial intelligence techniques for detection of mild cognitive impairment: A scoping review. Journal of Clinical Nursing.
29. Odusami, M., et al. (2021). Explainable deep-learning-based diagnosis: methods and clinical applicability for AD and MCI. IEEE Transactions on Medical Imaging.
30. Christodoulou, R., et al. (2025). AI-Based classification of MCI and cognitively normal individuals using ADNI data. Journal of Clinical Medicine.
31. Liu, H., et al. (2025). Machine learning applied to mild cognitive impairment: trends and bibliometric analysis. Frontiers in Neurology
32. Gaser, C., et al. (2013). BrainAGE in MCI and AD: accelerated brain aging as a biomarker. NeuroImage, 63(3), 1363–1373.
33. Suk, H.-I., Lee, S.-W., & Shen, D. (2014). Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage, 101, 569–582.
34. Eskildsen, S. F., et al. (2013). Prediction of AD conversion in MCI patients using structural MRI and machine learning. NeuroImage: Clinical, 3, 452–461.
35. Lebedev, A. V., et al. (2014). Random forest classification of AD and MCI from MRI features: what matters most? PLoS ONE.
36. Ding, Y., Sohn, J. H., Kawczynski, M. G., Trivedi, H., Harnish, R., Jenkins, N. W., ... & McCurtain, B. (2019). A deep learning model to predict a diagnosis of Alzheimer disease by using 18F-FDG PET of the brain. Radiology, 290(2), 456–464.
37. Korolev, S., Safiullin, A., Belyaev, M., & Dodonova, Y. (2017). Residual and plain convolutional neural networks for 3D brain MRI classification. Proceedings of the International Conference on Information Technology and Data Science.
38. Sarraf, S., & Tofighi, G. (2016). DeepAD: Alzheimer’s disease classification via deep convolutional neural networks using MRI and fMRI. bioRxiv.
39. Zhang, D., Shen, D., & the ADNI. (2012). Multi-modal classification of Alzheimer’s disease and MCI. NeuroImage, 55(3), 856–867.
40. Dukart, J., Mueller, K., & Barthel, H. (2013). The importance of partial-volume correction for PET-based quantification in Alzheimer’s disease research. NeuroImage, 59(1), 357–368.
41. Tong, T., et al. (2017). Prediction of conversion from MCI to AD with longitudinal and multimodal biomarkers. Scientific Reports, 7, 1–12.
42. Jo, T., Nho, K., Saykin, A. J., & the ADNI. (2019). Deep learning in Alzheimer's disease: Diagnostic classification and prognostic prediction using neuroimaging and clinical data. Alzheimer’s Research & Therapy.
43. Basaia, S., et al. (2019). Automated classification of Alzheimer’s disease and mild cognitive impairment using MRI: An ensemble deep learning framework. NeuroImage: Clinical, 21, 101602.
44. Noh, Y., et al. (2014). Using pattern recognition to detect early AD in MRI scans. Proceedings of MICCAI.
45. Korolev, I., et al. (2016). Predicting progression from MCI to AD using machine learning on structural MRI: Comparison of classifiers and features. Neuroinformatics.
46. Hao, X., et al. (2020). EEG-based detection of MCI using deep learning: a systematic review and meta-analysis. Frontiers in Aging Neuroscience.
47. Knight, R. A., et al. (2021). Blood-based biomarkers and machine learning models for early detection of MCI and AD: A systematic review. Alzheimer’s Research & Therapy.
48. O’Bryant, S. E., et al. (2017). A blood protein signature for early detection of Alzheimer disease. Neurology.
49. Raamana, P. R., et al. (2015). Machine learning models to predict cognitive decline: Methods, pitfalls, and opportunities. Frontiers in Neuroinformatics.
50. Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence. (Background on deep learning methods)
51. Lundervold, A., & Lundervold, A. (2019). An overview of deep learning in medical imaging focusing on MRI. Z. Med Phys. (methodological review)
52. Jack, C. R., Jr., et al. (2010). Hypothetical model of dynamic biomarkers of the Alzheimer’s pathological cascade. The Lancet Neurology, 9(1), 119–128.
53. McKhann, G. M., et al. (2011). The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups. Alzheimer’s & Dementia, 7(3), 263–269.
54. Sperling, R. A., et al. (2011). Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging and the Alzheimer’s Association. Alzheimer’s & Dementia, 7(3), 280–292.
55. Jack, C. R., Jr., et al. (2009). Serial MRI and CSF biomarkers in MCI to predict progression to AD. Neurology.
56. Kermany, D., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. (illustrative example of medical imaging DL success)
57. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. (methodological foundation)
58. Beach, T. G., et al. (2012). Correlates of AD neuropathology in MCI patients: Clinicopathologic studies. Journal of Alzheimer’s Disease.
59. Donohue, M. C., et al. (2014). The preclinical Alzheimer cognitive composite: Measuring subtle cognitive decline in preclinical AD. JAMA Neurology.
60. Frost, S., et al. (2020). Wearable sensors and digital biomarkers for early detection of cognitive impairment: opportunities and challenges for ML. Journal of Medical Internet Research.