{"title":"Clinical Application of Large Language Models for Intervention Plan Development in Speech-Language Pathology.","authors":"Namhee Kim, Mercy Homer, Hyeju Jang","doi":"10.1044/2025_AJSLP-24-00464","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>This study investigates the speech and language intervention plan outputs generated by six different artificial intelligence (AI) tools powered by large language models (LLMs), currently available for clinical writing in the field of speech-language pathology. This study aims to evaluate the potential applications and limitations of these AI tools, as well as their ability to provide relevant and reliable information for developing intervention plans.</p><p><strong>Method: </strong>Using a mixed design including both quantitative and qualitative analyses, this study compared the performance outputs of the six AI tools across three fictional clinical cases, each involving different types of speech and language disorders in 5-year-old children. Two types of command prompts, each with three levels of input specificity, were used to generate AI outputs.</p><p><strong>Results: </strong>Results revealed that the intervention plans generated by these AI tools were rated between <i>Needs Improvement</i> and <i>Meets Expectations</i> in terms of clinical knowledge and competency. Detailed and structured command prompts than general prompts yielded outputs with higher ratings, while the specificity of case information did not consistently influence the outputs. Each AI tool demonstrated unique strengths and limitations in supporting the development of intervention plans.</p><p><strong>Conclusion: </strong>The results of this study may serve as foundational data to provide insights into how clinicians, educators, and students in the field of speech-language pathology can appropriately and responsibly utilize existing AI resources when implementing these technologies into the development of intervention plans.</p>","PeriodicalId":49240,"journal":{"name":"American Journal of Speech-Language Pathology","volume":" ","pages":"1-17"},"PeriodicalIF":2.3000,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Speech-Language Pathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1044/2025_AJSLP-24-00464","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUDIOLOGY & SPEECH-LANGUAGE PATHOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: This study investigates the speech and language intervention plan outputs generated by six different artificial intelligence (AI) tools powered by large language models (LLMs), currently available for clinical writing in the field of speech-language pathology. This study aims to evaluate the potential applications and limitations of these AI tools, as well as their ability to provide relevant and reliable information for developing intervention plans.
Method: Using a mixed design including both quantitative and qualitative analyses, this study compared the performance outputs of the six AI tools across three fictional clinical cases, each involving different types of speech and language disorders in 5-year-old children. Two types of command prompts, each with three levels of input specificity, were used to generate AI outputs.
Results: Results revealed that the intervention plans generated by these AI tools were rated between Needs Improvement and Meets Expectations in terms of clinical knowledge and competency. Detailed and structured command prompts than general prompts yielded outputs with higher ratings, while the specificity of case information did not consistently influence the outputs. Each AI tool demonstrated unique strengths and limitations in supporting the development of intervention plans.
Conclusion: The results of this study may serve as foundational data to provide insights into how clinicians, educators, and students in the field of speech-language pathology can appropriately and responsibly utilize existing AI resources when implementing these technologies into the development of intervention plans.
期刊介绍:
Mission: AJSLP publishes peer-reviewed research and other scholarly articles on all aspects of clinical practice in speech-language pathology. The journal is an international outlet for clinical research pertaining to screening, detection, diagnosis, management, and outcomes of communication and swallowing disorders across the lifespan as well as the etiologies and characteristics of these disorders. Because of its clinical orientation, the journal disseminates research findings applicable to diverse aspects of clinical practice in speech-language pathology. AJSLP seeks to advance evidence-based practice by disseminating the results of new studies as well as providing a forum for critical reviews and meta-analyses of previously published work.
Scope: The broad field of speech-language pathology, including aphasia; apraxia of speech and childhood apraxia of speech; aural rehabilitation; augmentative and alternative communication; cognitive impairment; craniofacial disorders; dysarthria; fluency disorders; language disorders in children; speech sound disorders; swallowing, dysphagia, and feeding disorders; and voice disorders.