Using Machine Learning to Match Assistive Technology to People with Disabilities.

Area of Science:

• Assistive Technology
• Machine Learning
• Disability Studies

Background:

• Individuals with intellectual and developmental disabilities (I/DD) often require tailored technology solutions.
• Matching individuals with appropriate assistive technology can significantly improve quality of life and independence.
• Existing methods for technology recommendation for this population are limited.

Purpose of the Study:

• To develop and evaluate an initial machine learning-based recommender system.
• To personalize technology product recommendations for people with I/DD.
• To optimize the selection of technology based on user characteristics and desired outcomes.

Main Methods:

• Utilized a large dataset encompassing information on individuals with I/DD, their technology usage, and achieved outcomes.
• Applied machine learning algorithms to identify patterns and correlations.
• Developed a system to predict suitable technology products for specific user profiles.

Main Results:

• The initial results demonstrate the feasibility of using machine learning for technology recommendations in this domain.
• The system shows potential in identifying relevant technology products for individuals with I/DD.
• Preliminary data suggests improved matching accuracy compared to traditional methods.

Conclusions:

• Machine learning offers a promising approach to enhance technology matching for individuals with I/DD.
• Further development and validation are needed to refine the recommender system.
• This work lays the foundation for data-driven assistive technology selection.