| Title:
|
AI in Cognitive Rehabilitation: NeuroAIreh@b for Adaptive Personalized Interventions
|
| Author(s):
|
1
|
| Subject:
|
Personalized Interventions and Diagnosis of Complex Neurological Disorders
|
|
|
|
Presenter Author:
|
|
| Name:
|
Amirreza Davodi
|
|
|
|
Author:
|
|
| Name 1:
|
Amirreza Davodi - Corresponding - Presenter
|
| Affiliation 1:
|
Master’s Student in Occupational Therapy, Department of Occupational Therapy, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
|
|
|
| Name 2:
|
|
| Affiliation 2:
|
|
|
|
| Name 3:
|
|
| Affiliation 3:
|
|
|
|
| Name 4:
|
|
| Affiliation 4:
|
|
|
|
| Name 5:
|
|
| Affiliation 5:
|
|
|
|
| Name 6:
|
|
| Affiliation 6:
|
|
|
|
| Name 7:
|
|
| Affiliation 7:
|
|
|
|
| Name 8:
|
|
| Affiliation 8:
|
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
Cognitive impairments stemming from various conditions, including acquired brain injury (ABI), dementia, and the aging process, pose a severe threat to individuals' functional independence. Traditional neurorehabilitation often struggles with limitations such as its reliance on resource-intensive human input and its inability to dynamically adapt to a patient's progress rate or shifting motivational states. These challenges necessitate a new paradigm to deliver flexible, data-driven, and scalable interventions that can transcend the clinical setting and generalize to the home environment.
|
|
Methods:
|
This paper introduces NeuroAIreh@b as a four-stage computational methodology designed to optimize the prescription process for cognitive training. NeuroAIreh@b employs an Artificial Intelligence (AI) framework that integrates data from Neuropsychological Assessments (NPA) with adaptive computational models to derive a precise overview of the patient's cognitive capabilities. The methodology emphasizes ensuring optimal patient engagement through mechanisms for automatic adjustment of task difficulty during exercise execution. The framework is built around four core components: cognitive profiling, strategic training selection, adaptive session execution, and periodic system calibration. To enhance ecological validity, training tasks are delivered as Virtual Reality (VR) simulations related to Activities of Daily Living (ADLs).
|
|
Results:
|
To establish the practical feasibility and safety of the methodology, a Pilot Study was conducted involving 10 chronic stroke survivors presenting with mild-to-moderate cognitive deficits. These participants completed an eight-session intervention program featuring four types of ADL-based Cognitive Training Tasks (CTTs), including exercises requiring selective attention (cancellation tasks) in a kitchen environment and problem-solving (calculation tasks) in a supermarket setting. Post-intervention analysis revealed statistically significant improvements in overall general cognition (measured by the MoCA scale) and, crucially, significant gains in everyday functional abilities (measured by the IAFAI). These findings conclusively affirm the capacity of the AI-driven NeuroAIreh@b approach to drive functional efficiency improvements and demonstrate its high potential as an adaptive platform with a high rate of personalization.
|
|
Conclusion:
|
The NeuroAIreh@b methodology offers a cost-effective and scalable therapeutic solution to address the lack of adaptability in traditional rehabilitation, setting a precedent for cognitive training independent of the clinical environment. The observed potential for generalization to real-life functioning justifies the need for future larger, multi-center Randomized Controlled Trials (RCTs) to fully validate this innovative AI-driven approach.
|
| Attachment:
|
|
| Keywords:
|
"NeuroAIreh@b", "neurorehabilitation", "artificial intelligence in health", "AI-driven framework"
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
