A Sequential Model for Identifying Cognitive Impairment Using Accelerometer Data

• Vitória C. dos S. Camelo UFPB
• Clauirton de A. Siebra UFPB

DOI: https://doi.org/10.5753/sbcas.2025.6300

Abstract

The progression of certain cognitive impairments can be slowed when identified early. However, current diagnostic methods are costly and not widely accessible to the general population. This paper presents a sequence model that leverages accelerometer data to characterize behavioural routines, enabling the differentiation between cognitively impaired and mentally healthy individuals. The raw data, collected at 80 Hz, was consolidated into 24-hours time windows and represented by 13 features. The final dataset (N = 2934) with 429,912 hours of data was used to train a Conv1D-based sequence model, which achieved significantly higher AUC-ROC (0.90 ± 0.01) than cross-sectional models (0.59 ± 0.02).

References

Addae, S. et al. (2024) “Smart Solutions for Detecting, Predicting, Monitoring, and Managing Dementia in the Elderly: A Survey”, IEEE Access, vol. 12, pp. 26-56.

Alharbi, E., Alomainy, A. and Jones, J. M. (2020) “Detecting cognitive decline in early Alzheimer’s patients using wearable technologies”, IEEE International Conference on Healthcare Informatics (ICHI), pp. 1-4.

Ardle, R., Del Din, Galna, B., Thomas, A. and Rochester, L. (2020) “Differentiating dementia disease subtypes with gait analysis: feasibility of wearable sensors?”, Gait & posture, vol.76, pp. 372-376.

Ausó, E., Gómez-Vicente, V. and Esquiva, G. (2020). “Biomarkers for Alzheimer’s disease early diagnosis”, Journal of Personalized Medicine, vol. 10, n. 3, pp. 114.

Brody, D. J et al. (2019) “Cognitive performance in adults aged 60 and over: National Health and Nutrition Examination Survey, 2011–2014”.

Clark, L. et al. (2009) “Longitudinal verbal fluency in normal aging, preclinical and prevalent Alzheimer’s disease”, American Journal of Alzheimer’s Disease and Other Dementia, vol. 24, pp. 461-468.

Gaur, P., et al. (2024) “Continuous Monitoring of Heart Rate Variability in Free-Living Conditions Using Wearable Sensors: Exploratory Observational Study”, JMIR Formative Research, vol. 8, e53977.

Gornet, M. and Maxwell, W. (2024) “The European approach to regulating AI through technical standards”, Internet Policy Review, vol. 13, n. 3, pp. 1-27.

Jahan, Z., Khan, S. B. and Saraee, M. (2024) “Early dementia detection with speech analysis and machine learning techniques”, Discover Sustainability, vol. 5, n. 1, pp. 1-18.

John, D., Tang, Q., Albinali, F., and Intille, S. (2019) “An open-source monitor-independent movement summary for accelerometer data processing”, Journal for the Measurement of Physical Behaviour,vol. 2, n.4, pp. 268-281.

Ma, X. et al. (2023) “Developing and validating a nomogram for cognitive impairment in the older people based on the NHANES”, Front Neurosci, vol. 17, n. 17, pp. 1195570.

Marvi, F., Chen, Y. H. and Sawan, M. (2024) “Alzheimer's Disease Diagnosis in the Preclinical Stage: Normal Aging or Dementia”, IEEE Reviews in Biomedical Engineering, pp. 1-18.

Metz, C. (1978) “Basic principles of ROC analysis”, Seminars in Nuclear Medicine, vol. 8, n. 4, pp. 283-298.

Morris, J. C. et al. (1989) “The Consortium to Establish a Registry for Alzheimer’s disease (CERAD). Part 1. Clinical and neuropsychological assessment of Alzheimer’s disease”, Neurology, vol. 39, pp. 1159-1165.

Moyle, W., Jones, C., Murfield, J., Thalib, L., & Beattie, E. (2021) “Effect of a robotic pet on agitation and quality of life in individuals with dementia: a cluster-randomized controlled trial”, Journal of the American Medical Directors Association, 22(5), 933–939.e1.

Phillips, K. et al. (2020) “A theory-based model of cumulative activity,” Scientific reports, vol. 12, n. 1, p. 15635.

Rykov, Y.G., Patterson, M.D., Gangwar, B.A., et al. (2024) “Predicting cognitive scores from wearable-based digital physiological features using machine learning: data from a clinical trial in mild cognitive impairment”, BMC Medicine, 22, 36.

Shi, Y., Wang, H., Zhu, Z., Ye, Q., Lin, F. and Cai. G. (2023) “Association between exposure to phenols and parabens and cognitive function in older adults in the United States: a cross-sectional study”, Sci. Total Environ,vol. 858, pp. 160129.

Siebra, C. and Wac, K. (2025) “A correlation analysis between passively assessed gait initiation signal data and brain tumours progress”, Biomedical Signal Processing and Control, vol. 99, pp. 106858.

Tao, M., Liu, J. and Cervantes, D. (2022) “Association between magnesium intake and cognition in US older adults: National Health and Nutrition Examination Survey (NHANES) 2011 to 2014”, Alzheimers Dement (N Y), vol. 8, n. 1, pp. e12250.

Tsanousa, A. et al. (2020) “A novel feature selection method based on comparison of correlations for human activity recognition problems”, Journal of Ambient Intelligence and Humanized Computing, vol. 11, pp. 5961-5975, 2020.

Wechsle, D. (1997) WAIS Manual – 3rd Edition. New York: Psychological Corporation.

Weizman, Y. et al. (2021) “Gait assessment using wearable sensor-based devices in people living with dementia: a systematic review”, International Journal of Environmental Research and Public Health, vol. 18, n. 23, pp. 12735.

Whelan, R. et al. (2022) “Developments in scalable strategies for detecting early markers of cognitive decline”, Translational Psychiatry, vol. 12, pp. 473.

Wittenberg, R. et al. (2019) “Economic impacts of introducing diagnostics for mild cognitive impairment Alzheimer's disease patients”, Alzheimer's & Dementia: Translational Research & Clinical Interventions, vol. 5, pp. 382-387.