Technological advancements in health monitoring have transformed the ability to track and improve human well-being, particularly by enhancing diagnostic precision and rehabilitation strategies. This project is concerned with advancing fine motor skills and cognitive functions assessment, which are fundamental to human independence and quality of life, particularly for individuals affected by neurological conditions such as stroke, multiple sclerosis, Parkinson’s disease, and pediatric developmental disorders. The Nine-Hole Peg Test (NHPT) is a well-established clinical tool for assessing manual dexterity, widely used in both research and clinical settings due to its simplicity and reproducibility. However, despite its widespread adoption, the NHPT is currently limited to manually recorded completion times, neglecting critical aspects of motor function such as movement fluidity, grip precision, and cognitive contributions to task execution. We aim to develop SmartNHPT, a sensor-enhanced version that will provide a more comprehensive, automated assessment of fine motor and cognitive skills. The SmartNHPT will address several drawbacks of the standard NHPT. For instance, the latter involves manual timing, and execution protocols vary between evaluators, which introduces inter-rater variability, reducing consistency across different evaluators and studies. Besides, manual test administration places a substantial burden on healthcare professionals, reducing efficiency and limiting its potential for large-scale deployment or home-based monitoring. Moreover, the NHPT solely measures the total time taken to complete the test, disregarding the characterization of subtle motor impairments that could provide early indicators of neurodegenerative progression or rehabilitation success. Additionally, the absence of cognitive assessment further restricts its utility, despite strong evidence that cognitive functions play a crucial role in task execution. These issues collectively underscore the urgent need for an advanced, standardized, and minimally-supervised version of the NHPT. The SmartNHPT will leverage sensor integration, computer vision, and machine learning to address these limitations and introduce novel capabilities. A custom-designed camera module and deep learning algorithms will enable precise tracking of hand and finger motion, providing objective data on movement trajectories, tremors, and phase completion accuracy. Furthermore, cognitive assessments will be incorporated by using color-coded pegs and predefined insertion sequences, allowing simultaneous evaluation of motor and cognitive function. Through automation, the SmartNHPT will reduce clinician workload while increasing test consistency and accessibility. It will be designed for both clinical and home use, empowering patients to monitor disease progression or rehabilitation progress in real time. This project will deliver a fully functional SmartNHPT device, complete with advanced motor and cognitive assessment capabilities, a minimally supervised execution system, and a comprehensive validation study across healthy and diseased populations. The project will also establish normative values for fine motor and cognitive metrics in adult and pediatric population, ensuring the SmartNHPT’s applicability across various clinical and research settings. With at least five peer-reviewed publications anticipated, this study will significantly contribute to the emerging field of technologically-assisted neurological assessment and rehabilitation. The SmartNHPT represents a crucial step toward digitalizing clinical assessments, addressing long-standing limitations, and empowering both clinicians and patients with precise, reliable, and accessible motor and congnitive function monitoring tools, ultimately improving early diagnosis, patient monitoring, and personalized treatment strategies.
