Enhancing Dementia by Classifying and Monitoring the Diagnosed Patients

Abstract

Machine learning is a transformative technology that enables systems to autonomously learn and improve from experience without being explicitly programmed. It leverages algorithms to identify patterns, make decisions, and predict outcomes by analysing large datasets. The existing system is predicting the Dementia by analysing sleep disturbances in older adults using machine learning algorithms. The system uses a datasetfromtheSwedishNationalStudyon Aging and Care in Blekinge (SNAC-B), involving older adults aged 60 and above. The dataset includes personal and sleep- related featureswith five machine learning algorithms—gradient boosting, logistic regression, Gaussian naive Bayes, random forest, and support vector machine—are used to analyse the data. The existing system only has the feature of predicting Dementiain olderadultsbyanalysingtheir sleepdisturbancebutlagginginclassifying thediseasecondition, real-time monitoring and care for the affected patients. To overcome these shortcomings, we have proposedtodevelopanandroidapplication that is used for classifying Dementia and monitoring the diagnosed patient and to provide care.

Introduction

Dementia Overview:
Dementia is a progressive neurological disorder causing decline in memory, reasoning, language, and problem-solving, severe enough to disrupt daily life. It mainly affects older adults and includes subtypes such as Alzheimer’s Disease, Vascular Dementia, Lewy Body Dementia, and Frontotemporal Dementia. MRI scans reveal brain abnormalities like hippocampal atrophy and white matter hyperintensities associated with dementia.

Machine Learning in Dementia Diagnosis:
Advanced machine learning (ML) models, especially those using transfer learning and hybrid architectures combining Convolutional Neural Networks (CNN) with ResNet (e.g., ResNet-34 or ResNet-101), have been employed to classify dementia stages from MRI scans with high accuracy. These models automatically extract complex features from neuroimaging data and improve diagnostic precision. Key datasets used include ADNI and OASIS.

Literature Highlights:

• Deep learning models like VGG, DenseNet, and InceptionResNet have shown promising accuracy for vascular dementia detection.

• ML techniques combining clinical, imaging, and voice data improve dementia prediction.

• Gradient-boosted trees and survival analysis methods effectively predict dementia progression.

• Support vector machines and CNNs aid early detection of progression from mild cognitive impairment to Alzheimer’s.

Proposed System:
The proposed system integrates CNNs with ResNet-101 to accurately classify dementia into mild, moderate, and non-dementia stages. Preprocessing includes resizing, normalization, noise reduction, and data augmentation for better generalization. The system is supported by a mobile app built with React Native for real-time patient monitoring via GPS tracking, medication reminders, and alerts to caregivers, enhancing patient safety and care adherence.

Implementation Details:

• Secure role-based login system for patients and caregivers.

• Caregiver module supports location tracking, notifications, medication management, and feedback monitoring.

• Patient module offers easy navigation for viewing medication schedules, alerts, feedback, and location.

Results:

• The model achieved 92.5% accuracy, 91.2% precision, 93.0% recall, and a 92.1% F1 score, indicating strong performance in dementia detection with balanced handling of false positives and negatives.

• The system showed reliable, real-time operation of the app modules with smooth user experience and secure access.

Conclusion

The dementia care application has successfully integrated key features aimed at improving the well-being of dementia patients and streamlining the caregiving process. By providing separate modules for patients and caretakers, the app ensures that each user has access to the tools and information most relevant to their role. The patient module offers a user-friendly interface that allows patients to track their medication times, receive reminders, view their profiles, and submit feedback. The caretaker module provides real-time location tracking, medication management, and easy access to the patient’s feedback, ensuring caregivers can provide timely support. The dementia classification model incorporated in the system further contributes to early detection and accurate diagnosis, using machine learning to identify potential dementia cases. The system has shown strong performance in usability, real-time data processing, and accurate predictions, proving its effectiveness in a practical setting. Overall, this project offers a significant advancement in dementia care by combining technology and healthcare to provide more efficient, personalized, and supportive care.

References

[1] Ashir Javeed, Ana Luiza Dallora, Johan Sanmartin Berglund, Arif Ali3, Liaqata Ali, Peter Anderberg, “Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions”, Article in Journal of Medical Systems, February 2023. Available at: https://doi.org/10.1007/s10916-023-01906- 7 [2] Hina Tufail, Abdul Ahad, Mustahsan Hammad Naqvi, Rahman Maqsood, Ivan Miguel Pires, “Classification of Vascular Dementia on Magnetic Resonance Imaging Using Deep Learning Architectures”, Article in Intelligent Systems with Applications, May 2024. Available at: https://doi.org/10.1016/j.iswa.2024.200388 [3] Sergio Grueso and Raquel ViejoSobera, “Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer’s disease dementia:”, Article in Alzheimer\'s Research & Therapy, 2021. Available at: https://doi.org/10.1186/s13195-021-00900-w [4] Annette Spooner, Emily Chen, Arcot Sowmya, Perminder Sachdev, Nicole A. Kochan, Julian Trollor, Henry Brodaty, “A Comparison of Machine Learning Methods for Survival Analysis of High-Dimensional Clinical Data for Dementia Prediction”, Article in Scientific Reports, 2020. Available at: https://www.nature.com/articles/s41598- 020-77220-w [5] Janice M. Ranson, Magda Bucholc, Donald Lyall, Danielle Newby, Laura Winchester, Neil P. Oxtoby, Michele Veldsman, Timothy Rittman, Sarah Marzi, Nathan Skene, Ahmad Al Khleifat, Isabelle F. Foote, Vasiliki Orgeta, Andrey Kormilitzin, Ilianna Lourida, David J. Llewellyn, “Harnessing the Potential of Machine Learning and Artificial Intelligence for Dementia Research”, Article in Brain Informatics, 2023. Available at: https://braininformatics.springeropen.c om/articles/10.1186/s40708-022-00183-3 33 [6] Charlotte James, PhD; Janice M. Ranson, PhD; Richard Everson, PhD; David J. Llewellyn, PhD, “Performance of Machine Learning Algorithms for Predicting Progression to Dementia in Memory Clinic Patients”, Article in JAMA Network Open. 2021;4(12):e2136553. Available at: https://jamanetwork.com/journals/jama networkopen/fullarticle/2787228 [7] Sara Dhakala, Sami Azama, Khan Md. Hasibb, Asif Karima, Mirjam Jonkmana, A S M Farhan Al Haquee, “Dementia prediction using Machine Learning”, Article in Health and Social Care Information Systems and Technologies 2022. Available at: https://doi.org/10.1016/j.procs.2023.01.4 14. [8] Emma L. Twait, Constanza L. Andaur Navarro1, Vilmunur Gudnason, YiHan Hu, Lenore J. Launer and Mirjam Geerlings, “Dementia prediction in the general population using clinically accessible variable”, Article in BMC Medical Informatics and Decision Making, Available at: https://doi.org/10.1186/s12911-023- 02244-x. [9] Sophie A. Martin, Florence J. Townend, Frederik Barkhof1, James H. Cole, “Interpretable machine learning for dementia”, Published on 03 February 2023, Available at: https://doi.org/10.1002/alz.12948. [10] Joel Nyholm, Ahmad Nauman Ghazi, Sarah Nauman Ghazi, Johan Sanmartin Berglund, \"Prediction of Dementia Based on Older Adults’ Sleep Disturbances Using Machine Learning,\" Computers in Biology and Medicine, 171 (2024) 108126. Available at: https://doi.org/10.1016/j.compbiomed.2024.108126 [11] Jack, C.R., Jr., Bennett, D.A., Blennow, K., Carrillo, M.C., Dunn, B., Haeberlein, S.B., Holtzman, D.M., Jagust, W., Jessen, F., Karlawish, J., et al., “NIA-AA research framework: Toward a biological definition of Alzheimer’s disease”, Alzheimer’s & Dementia, 2018, 14, 535–562. Available at: https://doi.org/10.1016/j.jalz.2018.02.018 [12] McKhann, G.M., Knopman, D.S., Chertkow, H., Hyman, B.T., Jack, C.R., Jr., Kawas, C.H., Klunk, W.E., Koroshetz, W.J., Manly, J.J., Mayeux, R., et al., “The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease”, Alzheimer’s & Dementia, 2011, 7, 263–269. Available at: https://doi.org/10.1016/j.jalz.2011.03.005 [13] Simrén, J., Leuzy, A., Karikari, T.K., Hye, A., Benedet, A.L., Lantero-Rodriguez, J., Mattsson-Carlgren, M., Schöll, M., Mecocci, P., Vellas, B., et al., “The diagnostic and prognostic capabilities of plasma biomarkers in Alzheimer’s disease”, Alzheimer’s & Dementia, 2021, 17, 1145–1156. Available at: https://doi.org/10.1002/alz.12283 [14] Nakamura, A., Kaneko, N., Villemagne, V.L., Kato, T., Doecke, J., Doré, V., Fowler, C., Li, Q.-X., Martins, R., Rowe, C., et al., “High performance plasma amyloid-? biomarkers for Alzheimer’s disease”, Nature, 2018, 554, 249–254. Available at: https://doi.org/10.1038/nature25456 [15] Palmqvist, S., Janelidze, S., Stomrud, E., Zetterberg, H., Karl, J., Zink, K., Bittner, T., Mattsson, N., Eichenlaub, U., Blennow, K., et al., “Performance of fully automated plasma assays as screening tests for Alzheimer disease–related ?-amyloid status”, JAMA Neurology, 2019, 76, 1060–1069. Available at: https://doi.org/10.1001/jamaneurol.2019.1632 [16] Oeckl, P., Halbgebauer, S., Anderl-Straub, S., Steinacker, P., Huss, A.M., von Arnim, C.A.F., Diehl-Schmid, J., Grimmer, T., Kornhuber, J., Lewczuk, P., et al., “Glial fibrillary acidic protein in serum is increased in Alzheimer’s disease and correlates with cognitive impairment”, Journal of Alzheimer’s Disease, 2019, 67, 481–488. Available at: https://doi.org/10.3233/JAD-180842 [17] Mattsson, N., Cullen, N.C., Andreasson, U., Zetterberg, H., Blennow, K., “Association between longitudinal plasma neurofilament light and neurodegeneration in patients with Alzheimer disease”, JAMA Neurology, 2019, 76, 791–799. Available at: https://doi.org/10.1001/jamaneurol.2019.0765 [18] Ashton, N., Janelidze, S., Khleifat, A.A., Leuzy, A., van der Ende, E., Karikari, T., Benedet, A.L., Pascoal, T.A., Lleó, A., Parnetti, L., et al., “Diagnostic value of plasma neurofilament light: A multicentre validation study”, Nature Communications, 2021, 12, 3400. Available at: https://doi.org/10.1038/s41467-021-23620-z [19] Pathak, D., Sriram, K., “Neuron-astrocyte omnidirectional signaling in neurological health and disease”, Frontiers in Molecular Neuroscience, 2023, 16. Available at: https://doi.org/10.3389/fnmol.2023.1169320 [20] Karikari, T.K., Benedet, A.L., Ashton, N.J., Rodriguez, J.L., Snellman, A., Suárez-Calvet, M., Saha-Chaudhuri, P., Lussier, F., Kvartsberg, H., Rial, A.M., et al., “Diagnostic performance and prediction of clinical progression of plasma phospho-tau181 in the Alzheimer’s Disease Neuroimaging Initiative”, Molecular Psychiatry, 2021, 26, 429–442. Available at: https://doi.org/10.1038/s41380-020-00923-z [21] Schindler, S.E., Bollinger, J.G., Ovod, V., Mawuenyega, K.G., Li, Y., Gordon, B.A., Holtzman, D.M., Morris, J.C., Benzinger, T.L., Xiong, C., et al., “High-precision plasma ?-amyloid 42/40 predicts current and future brain amyloidosis”, Neurology, 2019, 93, e1647–e1659. Available at: https://doi.org/10.1212/WNL.0000000000008081 [22] Kim, J., Cheon, S., Lim, J., “IoT-Based Unobtrusive Physical Activity Monitoring System for Predicting Dementia”, IEEE Access, 2022, 10, 26078–26089. Available at: https://doi.org/10.1109/ACCESS.2022.3156246 [23] Stripelis, D., Dhinagar, N.J., Romero, R.V.S., Thomopoulos, S.I., Thompson, P.M., Ambite, J.L., “Federated Deep Learning for Detecting Alzheimer’s Disease in Multi-Cohort Brain MRI”, Alzheimer’s & Dementia, 2023, 19, e065998. Available at: https://doi.org/10.1002/alz.065998 [24] Lei, B., Zhu, Y., Liang, E., Yang, P., Chen, S., Hu, H., Xie, H., Wei, Z., Hao, F., Song, X., et al., “Federated Domain Adaptation via Transformer for Multi-site Alzheimer’s Disease Diagnosis”, IEEE Transactions on Medical Imaging, 2023. Online ahead of print. Available at: https://doi.org/10.1109/TMI.2023.3292273 [25] Yao, Z., Wang, H., Yan, W., Wang, Z., Zhang, W., Wang, Z., Zhang, G., “Artificial Intelligence-based Diagnosis of Alzheimer’s Disease with Brain MRI Images”, European Journal of Radiology, 2023, 165, 110934. Available at: https://doi.org/10.1016/j.ejrad.2023.110934

Copyright

Copyright © 2025 Mr. T. Rajan Babu, Dr. R.G. Suresh Kumar, Mr. Mohamed Aadil D, Mr. Ravi Sankar S, Mr. Manikandan J, Mr. Vignesh S.. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.