Project Summary

Desktop computer software for passive monitoring and identification of Alzheimer’s disease and Mild Cognitive Impairment through data mining and natural language processing.

Funding

EPSRC
Research Associate (2014-16)

Collaborators

  • Pete Sawyer [PI]
  • Paul Rayson
  • Alistair Sutcliffe

View more collaborators

Links

The SAMS project (Software Architecture for Mental health Self-management) aimed to detect early markers of mild cognitive impairment and neurodegenerative diseases, such as Alzheimer’s disease, through participants’ computer use [1,2]. The aim is to enable earlier treatment and better quality of life for patients. This is achieved through a variety of novel data capture techniques (for low-level mouse and keyboard interactions, as well as higher-level contextual information). This is then analysed to determine patterns of usage through data mining [3] and natural language processing (NLP) [4], particularly Propositional Idea Density.

We found that passive monitoring of computer use behaviours can indicate early cognitive impairment [in submission]. Significant work also explored the requirements engineering aspects of working in such as a sensitive context [5,6,7]. My main responsibilities were the design and development of the secure data capture software, the design and development of an NLP tool, coordination of development activities with Manchester University, ethical transmission and storage of participant data, project support software, and the NLP of participant data.

References

  1. Gemma Stringer et al. Can you detect early dementia from an email? A proof of principle study of daily computer use to detect cognitive and functional decline. In: International Journal of Geriatric Psychiatry 33.7 (2018), pp. 867–874. | DOI
  2. Gemma Stringer et al. Assessment of non-directed computer-use behaviours in the home can indicate early cognitive impairment: A proof of principle longitudinal study. In: Aging & Mental Health 27.1 (2022), pp. 193-202. | DOI PDF
  3. Ann Gledson et al. Combining Mouse and Keyboard Events with Higher Level Desktop Actions to Detect Mild Cognitive Impairment. In: Proceedings of the International Conference on Healthcare Informatics (ICHI ‘16). IEEE, 2016, pp. 139–145. | DOI
  4. Christopher Bull et al. Combining data mining and text mining for detection of early stage dementia: the SAMS framework. In: Resources and ProcessIng of linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric impairments (RaPID ’16) workshop at the 10th International Conference on Language Resources and Evaluation (LREC ’16). Portorož, Slovenia: ELRA, 2016. | PDF
  5. Alistair Sutcliffe et al. Known and unknown requirements in healthcare. In: Requirements Engineering 25.1 (2020), pp. 1–20. | DOI
  6. Pete Sawyer et al. Dementia and Social Sustainability: Challenges for Software Engineering. In: Proceedings of the 37th International Conference on Software Engineering (ICSE ‘15). Florence, Italy: IEEE, May 2015, pp. 527–530. | DOI
  7. Alistair Sutcliffe et al. Discovering Affect-Laden Requirements to Achieve System Acceptance. In: Proceedings of the 22nd IEEE International Requirements Engineering Conference (RE’14). Karlskrona, Sweden: IEEE, 2014, pp. 173–182. | DOI