Raphael Thys
  • About
Contact me
Digital Transformation and Digital Products at the age of AI
LinkedInInstagramFacebookXSpotify
Futurist · Keynote Speaker · AI Coach
Futurist · Keynote Speaker · AI Coach
/
AI-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge

AI-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge

First page of “AI-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge”

First page of “AI-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge”

Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies

https://doi.org/10.5220/0009369108450853

‣

One of the health clinic challenges is rehabilitation therapy cognitive impairment that can happen after brain injury, dementia and in normal cognitive decline due to aging. Current cognitive rehabilitation therapy has been shown to be the most effective way to address this problem. However, a) it is not adaptive for every patient, b) it has a high cost, and c) it is usually implemented in clinical environments. The Task Generator (TG) is a free tool for the generation of cognitive training tasks. However, TG is not designed to adapt and monitor the cognitive progress of the patient. Hence, we propose in the BRaNT project an enhancement of TG with belief revision and machine learning techniques, gamification and remote monitoring capabilities to enable health professionals to provide a long-term personalized cognitive rehabilitation therapy at home. The BRaNT is an interdisciplinary effort that addresses scientific limitations of current practices as well as provides solutions towards the sustainability of health systems and contributes towards the improvement of quality of life of patients. This paper proposes the AI-Rehab framework for the BRaNT, explains profiling challenge in the situation of insufficient data and presents an alternate AI solutions which might be applicable once enough data is available.

‣

Figure 1: The AI-Rehab framework for the BRaNT project. Al-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge

Figure 1: The AI-Rehab framework for the BRaNT project. Al-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge
‣

This work aims at providing a tool for supporting cognitive rehabilitation. This is a wide field, that includes a variety of diseases and related clinical pictures; for this reason the need arises to have a tool available that overcomes the difficulties entailed by what currently is the most common approach, that is, the so-called pen and paper rehabilitation. Methods: We first organized a big number of stimuli in an ontology that represents concepts, attributes and a set of relationships among concepts. Stimuli may be words, sounds, 2D and 3D images. Then, we developed an engine that automatically generates exercises by exploiting that ontology. The design of exercises has been carried on in synergy with neuropsychologists and speech therapists. Solutions have been devised aimed at personalizing the exercises according to both patients' preferences and performance. Results: Exercises addressed to rehabilitation of executive functions and aphasia-related diseases have been implemented. The system has been tested on both healthy volunteers (n 1⁄4 38) and patients (n 1⁄4 9), obtaining a favourable rating and suggestions for improvements. Conclusions: We created a tool able to automate the execution of cognitive rehabilitation tasks. We hope the variety and personalization of exercises will allow to increase compliance, particularly from elderly people, usually neither familiar with technology nor particularly willing to rely on it. The next step involves the creation of a telerehabilitation tool, to allow therapy sessions to be undergone from home, thus guaranteeing continuity of care and advantages in terms of time and costs for the patients and the National Healthcare System (NHS) • Cognitive impairments can greatly impact an individual' s existence, appreciably reducing his abilities and autonomy, as well as sensibly lowering his quality of life. Cognitive rehabilitation can be used to restore lost brain function or slow down degenerative diseases. • Computerization of rehabilitation entails many advantages, but patients -especially elderlypeople -might be less prone to the use of technology and consequently reluctant towards this innovative therapeutic approach. • Our software system, CoRe, supports a therapist during the administration of rehabilitation sessions: exercises can be generated dynamically, thus reducing repetitivity, and patients' performance trends automatically analysed to facilitate the assessment of their progress.

Cognitive rehabilitation aims to remediate or alleviate the cognitive deficits appearing after an episode of Acquired Brain Injury (ABI). The purpose of this work is to describe the tele-rehabilitation platform called Guttmann Neuro Personal Trainer (GNPT) which provides new strategies for cognitive rehabilitation, improving efficiency and access to treatments, and to increase knowledge generation from the process. Cognitive rehabilitation process has been modeled to design and develop the system, which allows neuropsychologists to configure and schedule rehabilitation sessions, consisting of set of personalized computerized cognitive exercises grounded on neuroscience and plasticity principles. It provides remote continuous monitoring of patient's performance, by an asynchronous communication strategy. An automatic knowledge extraction method has been used to implement a decision support system, improving treatment customization. GNPT has been implemented in 27 rehabilitation centers and in 83 patients' homes, facilitating the access to the treatment. In total, 1660 patients have been treated. Usability and cost analysis methodologies have been applied to measure the efficiency in real clinical environments. The usability evaluation reveals a System Usability Score higher than 70 for all target users. The cost efficiency study results show a relation of 1 to 20 compared to faceto-face rehabilitation. GNPT enables brain-damaged patients to continue and further extend rehabilitation beyond the hospital, improving the efficiency of the rehabilitation process. It allows customized therapeutic plans, providing information to further development of clinical practice guidelines.

Cognitive rehabilitation aims to remediate or alleviate the cognitive deficits appearing after an episode of acquired brain injury (ABI). The purpose of this work is to describe the telerehabilitation platform called Guttmann Neuropersonal Trainer (GNPT) which provides new strategies for cognitive rehabilitation, improving efficiency and access to treatments, and to increase knowledge generation from the process. A cognitive rehabilitation process has been modeled to design and develop the system, which allows neuropsychologists to configure and schedule rehabilitation sessions, consisting of set of personalized computerized cognitive exercises grounded on neuroscience and plasticity principles. It provides remote continuous monitoring of patient's performance, by an asynchronous communication strategy. An automatic knowledge extraction method has been used to implement a decision support system, improving treatment customization. GNPT has been implemented in 27 rehabilitation c...

Advances in Industrial Design, 2021

Activities for rehabilitation and prevention are often lengthy and associated with pain and frustration. Their playful enrichment (hereafter: gamification) can counteract this, resulting in so-called “exergames”. However, in contrast to games designed solely for entertainment, the increased motivation and immersion in gamified training can lead to a reduced perception of pain and thus to health deterioration. Therefore, it is necessary to monitor activities continuously. However, only an AI-based system able to generate autonomous interventions could vacate the therapists’ costly time and allow better training at home. An automated adjustment of the movement training’s difficulty as well as individualized goal setting and control are essential to achieve such autonomy. This article’s contribution is two-fold: (1) We portray the potentials of gamification in the health area. (2) We present a framework for smart rehabilitation and prevention training allowing autonomous, dynamic, and gamified interactions.

  1. Alchourrón, C. E., Gärdenfors, P., and Makinson, D. (1985). On the logic of theory change: Partial meet contraction and revision functions. The journal of symbolic logic, 50(2):510-530.
  2. Bergeron, M. F., Landset, S., Tarpin-Bernard, F., Ashford, C. B., Khoshgoftaar, T. M., and Ashford, J. W. (2019). Episodic-memory performance in machine learning modeling for predicting cognitive health status classi- fication. Journal of Alzheimer's Disease, 70(1):277- 286. Bermúdez i Badia, S., Fluet, G. G., Llorens, R., and Deutsch, J. E. (2016). Virtual reality for sensorimo- tor rehabilitation post stroke: Design principles and evidence. In Neurorehabilitation technology, pages 573-603. Springer.
  3. Booth, R., Meyer, T., Varzinczak, I., and Wassermann, R. (2010). Contraction core for horn belief change: pre- liminary report. Unpublished manuscript.
  4. Bott, N. T. and Kramer, A. (2017). Cognitive rehabilitation. Encyclopedia of Geropsychology, pages 544-551.
  5. Carod-Artal, J., Egido, J. A., González, J. L., and Varela de Seijas, E. (2000). Quality of life among stroke sur- vivors evaluated 1 year after stroke: experience of a stroke unit. Stroke, 31(12):2995-3000.
  6. Chi, C.-L., Zeng, W., Oh, W., Borson, S., Lenskaia, T., Shen, X., and Tonellato, P. J. (2017). Personalized long-term prediction of cognitive function: Using se- quential assessments to improve model performance. Journal of biomedical informatics, 76:78-86.
  7. Cicerone, K. D., Dahlberg, C., Kalmar, K., Langenbahn, D. M., Malec, J. F., Bergquist, T. F., Felicetti, T., Gi- acino, J. T., Harley, J. P., Harrington, D. E., et al. (2000). Evidence-based cognitive rehabilitation: rec- ommendations for clinical practice. Archives of phys- ical medicine and rehabilitation, 81(12):1596-1615.
  8. Cicerone, K. D., Dahlberg, C., Malec, J. F., Langenbahn, D. M., Felicetti, T., Kneipp, S., Ellmo, W., Kalmar, K., Giacino, J. T., Harley, J. P., et al. (2005). Evidence- based cognitive rehabilitation: updated review of the literature from 1998 through 2002. Archives of physi- cal medicine and rehabilitation, 86(8):1681-1692.
  9. Cicerone, K. D., Langenbahn, D. M., Braden, C., Malec, J. F., Kalmar, K., Fraas, M., Felicetti, T., Laatsch, L., Harley, J. P., Bergquist, T., et al. (2011). Evidence- based cognitive rehabilitation: updated review of the literature from 2003 through 2008. Archives of physi- cal medicine and rehabilitation, 92(4):519-530.
  10. Cumming, T. B., Marshall, R. S., and Lazar, R. M. (2013). Stroke, cognitive deficits, and rehabilitation: still an incomplete picture. International Journal of stroke, 8(1):38-45.
  11. Delgrande, J. and Wassermann, R. (2010). Horn clause contraction functions: Belief set and belief base ap- proaches. In Twelfth International Conference on the Principles of Knowledge Representation and Reason- ing.
  12. Delgrande, J. P. (2008). Horn clause belief change: Con- traction functions. In KR, pages 156-165.
  13. Delgrande, J. P. and Schaub, T. (2003). A consistency- based approach for belief change. Artificial Intelli- gence, 151(1-2):1-41.
  14. Faria, A. L. and Bermúdez i Badia, S. (2015). Development and evaluation of a web-based cognitive task gener- ator for personalized cognitive training: a proof of concept study with stroke patients. In Proceedings of the 3rd 2015 Workshop on ICTs for improving Pa- tients Rehabilitation Research Techniques, pages 1-4. ACM. Faria, A. L., Pinho, M. S., and Bermúdez i Badia, S. (2018). Capturing expert knowledge for the personalization of cognitive rehabilitation: Study combining com- putational modeling and a participatory design strat- egy. JMIR rehabilitation and assistive technologies, 5(2):e10714.
  15. Fermé, E. and Hansson, S. O. (2011). Agm 25 years. Jour- nal of Philosophical Logic, 40(2):295-331.
  16. Fermé, E. and Hansson, S. O. (2018). Belief Change: In- troduction and Overview. Springer.
  17. Fernández-Delgado, M., Cernadas, E., Barro, S., and Amorim, D. (2014). Do we need hundreds of classi- fiers to solve real world classification problems? The Journal of Machine Learning Research, 15(1):3133- 3181.
  18. Fernández-Delgado, M., Sirsat, M., Cernadas, E., Alawadi, S., Barro, S., and Febrero-Bande, M. (2018). An extensive experimental survey of regression methods. Neural Networks.
  19. Freitas, S., Batista, S., Afonso, A. C., Simões, M. R., de Sousa, L., Cunha, L., and Santana, I. (2018). The montreal cognitive assessment (moca) as a screening test for cognitive dysfunction in multiple sclerosis. Applied Neuropsychology: Adult, 25(1):57-70.
  20. Freitas, S., Prieto, G., Simões, M. R., and Santana, I. (2014). Psychometric properties of the montreal cog- nitive assessment (moca): an analysis using the rasch model. The Clinical Neuropsychologist, 28(1):65-83.
  21. Freitas, S., Prieto, G., Simões, M. R., and Santana, I. (2015). Scaling cognitive domains of the montreal cognitive assessment: an analysis using the partial credit model. Archives of Clinical Neuropsychology, 30(5):435-447.
  22. Freitas, S., Simões, M. R., Alves, L., Duro, D., and Santana, I. (2012a). Montreal cognitive assessment (moca): validation study for frontotemporal dementia. Journal of Geriatric Psychiatry and Neurology, 25(3):146- 154.
  23. Freitas, S., Simões, M. R., Alves, L., and Santana, I. (2011). Montreal cognitive assessment (moca): normative study for the portuguese population. Journal of clin- ical and experimental neuropsychology, 33(9):989- 996.
  24. Freitas, S., Simões, M. R., Alves, L., and Santana, I. (2013). Montreal cognitive assessment: validation study for mild cognitive impairment and alzheimer disease. Alzheimer Disease & Associated Disorders, 27(1):37-43.
  25. Freitas, S., Simoes, M. R., Alves, L., Vicente, M., and Santana, I. (2012b). Montreal cognitive assessment (moca): validation study for vascular dementia. Jour- nal of the International Neuropsychological Society, 18(6):1031-1040.
  26. Freitas, S., Simoes, M. R., Marôco, J., Alves, L., and San- tana, I. (2012c). Construct validity of the montreal cognitive assessment (moca). Journal of the Interna- tional Neuropsychological Society, 18(2):242-250.
  27. George, D. R. and Whitehouse, P. J. (2011). Marketplace of memory: what the brain fitness technology industry says about us and how we can do better. The Geron- tologist, 51(5):590-596.
  28. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The el- ements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media.
  29. Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., and Wang, Y. (2017). Arti- ficial intelligence in healthcare: past, present and fu- ture. Stroke and vascular neurology, 2(4):230-243.
  30. Katsuno, H. and Mendelzon, A. O. (1991). Propositional knowledge base revision and minimal change. Artifi- cial Intelligence, 52(3):263-294.
  31. Ko, H., Ihm, J.-J., Kim, H.-G., Initiative, A. D. N., et al. (2019). Cognitive profiling related to cerebral amy- loid beta burden using machine learning approaches. Frontiers in aging neuroscience, 11.
  32. LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learn- ing. nature, 521(7553):436-444.
  33. Morris, K., Hacker, V., and Lincoln, N. B. (2012). The validity of the addenbrooke's cognitive examination- revised (ace-r) in acute stroke. Disability and rehabil- itation, 34(3):189-195.
  34. Nakamura, J. and Csikszentmihalyi, M. (2009). Flow the- ory and research. Handbook of positive psychology, pages 195-206.
  35. Nasreddine, Z. S., Phillips, N. A., Bédirian, V., Charbon- neau, S., Whitehead, V., Collin, I., Cummings, J. L., and Chertkow, H. (2005). The montreal cognitive as- sessment, moca: a brief screening tool for mild cogni- tive impairment. Journal of the American Geriatrics Society, 53(4):695-699.
  36. Pagnucco, M. (2006). Knowledge compilation for belief change. In Australasian Joint Conference on Artificial Intelligence, pages 90-99. Springer.
  37. Parsons, T. D. (2015). Ecological validity in virtual reality- based neuropsychological assessment. In Encyclope- dia of Information Science and Technology, Third Edi- tion, pages 1006-1015. IGI Global.
  38. Paulino, T., i Badia, S. B., and Cameirão, M. (2019). Us- ability evaluation of an integrative exergaming system for the senior population. In 2019 5th Experiment In- ternational Conference (exp. at'19), pages 286-291. IEEE.
  39. Paulino, T., Muñoz, J., Bermúdez i Badia, S., and Cameirão, M. S. (2018). Design of an integrative system for con- figurable exergames targeting the senior population. In International Conference on Human Systems Engi- neering and Design: Future Trends and Applications, pages 287-292. Springer.
  40. Peppas, P. and Williams, M.-A. (2016). Kinetic consistency and relevance in belief revision. In European Confer- ence on Logics in Artificial Intelligence, pages 401- 414. Springer.
  41. Schwind, N., Inoue, K., Konieczny, S., Lagniez, J.-M., and Marquis, P. (2019). What has been said? identifying the change formula in a belief revision scenario. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 1865-1871. International Joint Conferences on Artifi- cial Intelligence Organization.
  42. Solana, J., Cáceres, C., García-Molina, A., Opisso, E., Roig, T., Tormos, J. M., and Gómez, E. J. (2014). Im- proving brain injury cognitive rehabilitation by per- sonalized telerehabilitation services: Guttmann neu- ropersonal trainer. IEEE journal of biomedical and health informatics, 19(1):124-131.
  43. Williams, M.-A. and Sims, A. (2000). Saten: An object- oriented web-based revision and extraction engine. arXiv preprint cs/0003059.
  44. Wilson, A. and McDonagh, J. (2013). Application of the principles of gamification to facilitate acquisition of self-management skills in young people with long- term medical conditions. In European Conference on Games Based Learning, page 579. Academic Confer- ences International Limited.
  45. Zhuang, Z. Q., Pagnucco, M., and Meyer, T. (2007). Imple- menting iterated belief change via prime implicates. In Australasian Joint Conference on Artificial Intelli- gence, pages 507-518. Springer.
Related to MASTER TAG DATABASE (Related to SOURCES (MTags))
Artificial intelligenceArtificial intelligenceNeurosciencesNeurosciences
Link
https://www.academia.edu/104421763/AI_Rehab_A_Framework_for_AI_Driven_Neurorehabilitation_Training_The_Profiling_Challenge