Assistive Technology Research

KEY FINDING: Self-surveys, in-clinic measurements, and remote tracking are used to assess community mobility and participation in manual wheelchair users.

KEY FINDING: The review of five randomized trials (n = 122) showed varied results due to differences in treatment protocols and outcome measures. However, the included studies demonstrated high methodological quality.

KEY FINDING: The machine learning method showed high accuracy in detecting the type of wheelchair propulsion, with an F1 score of 0.886 when using both frame and wheel sensors.

KEY FINDING: The primary outcome will be measured with the Japanese Orthopaedic Association (JOA) cervical myelopathy evaluation scale.

KEY FINDING: Significant improvement in lower limb function (Fugl Meyer Assessment-FMA < 0.001) was observed after the intervention.

KEY FINDING: Patients with motor incomplete SCI experienced clinically meaningful improvements in walking function, particularly in the outpatient setting.

KEY FINDING: Eighty percent of issues were rated to be of moderate to high significance, 83% were rated as being feasible to address, and 75% were rated as addressable using existing project resources.

KEY FINDING: The developed neural network model exhibits an average time error of less than 11.51 ms across all walking conditions, indicating its suitability for real-time applications.

KEY FINDING: Novel nanomaterial-based sensor designs improve skin conformality, reduce noise, and enhance breathability.

KEY FINDING: Participants consistently maintained normal blood pressure responses between seated and standing positions throughout the training sessions.