: An AI-Based Application to Enable Just-in-Time Generation of Topic-Specific Displays for Persons Who Are Minimally Speaking.

Journal: International journal of environmental research and public health
PMID:

Abstract

As artificial intelligence (AI) makes significant headway in various arenas, the field of speech-language pathology is at the precipice of experiencing a transformative shift towards automation. This study introduces , an AI-driven application designed to generate topic-specific displays from photographs in a "just-in-time" manner. Using , this study aimed to (a) determine which of two AI algorithms (NLG-AAC and GPT-3.5) results in greater specificity of vocabulary (i.e., percentage of vocabulary kept/deleted by clinician relative to vocabulary generated by ; percentage of vocabulary modified); and to (b) evaluate perceived usability of among practicing speech-language pathologists. Results revealed that the GPT-3.5 algorithm consistently resulted in greater specificity of vocabulary and that speech-language pathologists expressed high user satisfaction for the application. These results support continued study of the implementation of in clinical practice and demonstrate the possibility of utilizing topic-specific displays as just-in-time supports.

Authors

  • Christina Yu
    Boston Children's Hospital, Waltham, MA 02453, USA.
  • Ralf W Schlosser
    Boston Children's Hospital, Waltham, MA 02453, USA.
  • MaurĂ­cio Fontana de Vargas
    School of Information Studies, McGill University, Montreal, QC H3A 0G4, Canada.
  • Leigh Anne White
    Boston Children's Hospital, Waltham, MA 02453, USA.
  • Rajinder Koul
    Department of Speech, Language, and Hearing Sciences, University of Texas at Austin, Austin, TX 78712, USA.
  • Howard C Shane
    Boston Children's Hospital, Waltham, MA 02453, USA.