Development of Intelligent Model to Determine Favorable Wheelchair Tilt and Recline Angles for People with Spinal Cord Injury

The study aims to develop an individualized clinical guideline on wheelchair tilt and recline usage for people with spinal cord injury (SCI). Current practice uses uniform settings, but individual responses vary. The goal is to develop an intelligent model using artificial neural networks (ANNs) to predict favorable wheelchair settings based on neurological functions and SCI history, to reduce pressure ulcer risk. The intelligent model significantly outperforms the traditional statistical approach in accurately classifying favorable wheelchair tilt and recline settings, demonstrating the feasibility of using ANN for individualized guidance.

• 1
  Traditional statistical analysis of skin blood flow response to wheelchair tilt and recline usage is not satisfying, with a classification accuracy rate of only 59.38%.
• 2
  The ANN model, trained with core attributes (level of injury, duration of injury, age) and gender, achieved a 75% accuracy rate with 10-fold cross-validation, outperforming the traditional method.
• 3
  The study identifies 'level of injury', 'duration of injury', 'age', and 'gender' as relevant attributes for predicting favorable wheelchair tilt and recline settings to enhance skin perfusion.