Large Language Models for Stuttering Assessment and Therapy
Alignment of Large Language Model Responses on Stuttering Definition, Assessment, and Therapy With Clinical Practice Guidelines: A Multi-Model Comparison
This observational study aims to compare the quality of responses generated by four large language models (ChatGPT, Claude, Google Gemini, and Grok-4.20) to questions about stuttering. The study focuses on three main areas: general information about stuttering, clinical assessment, and therapy. A total of nine questions were developed based on evidence-based clinical practice guidance, including the American Speech-Language-Hearing Association (ASHA) Practice Portal. Each question is presented to each language model in separate sessions, and the generated responses are recorded for evaluation.
Five speech-language therapists with clinical experience in stuttering independently evaluate the model-generated responses. Each response is rated for relevance, accuracy, clarity, completeness, and consistency using a 5-point Likert scale. The responses are also compared with guideline-based reference information. The study does not involve any clinical intervention or treatment of patients. The aim is to determine how closely large language model responses align with current clinical practice guidance and to identify their potential strengths and limitations when used as informational or clinical support tools in the field of stuttering.
Обзор исследования
Статус
Условия
Тип исследования
Регистрация (Действительный)
Контакты и местонахождение
Места учебы
-
-
Istanbul
-
Istanbul, Istanbul, Турция (Туркие), 34310
- Istanbul Gelisim University
-
-
Критерии участия
Критерии приемлемости
Возраст, подходящий для обучения
Принимает здоровых добровольцев
Полы, имеющие право на обучение
Метод выборки
Исследуемая популяция
The study population consisted of adult speech-language therapists in Türkiye who were actively working in the field of stuttering and fluency disorders. Five speech-language therapists with clinical experience in stuttering were purposively selected to independently evaluate responses generated by four large language models to standardized questions concerning stuttering information, assessment, and therapy.
Описание
Inclusion Criteria:
- Having an undergraduate or postgraduate degree in speech and language therapy.
- Actively practicing clinically in the field of stuttering/fluency disorders.
- Voluntarily agreeing to participate in the study.
- Completing the evaluation form in full.
Exclusion Criteria:
- Not having active clinical experience in the field of stuttering.
- Incomplete completion of the evaluation form.
- Withdrawal of voluntary participation during the evaluation process.
Учебный план
Как устроено исследование?
Детали дизайна
- Наблюдательные модели: OTHER
- Временные перспективы: CROSS_SECTIONAL
Когорты и вмешательства
Группа / когорта |
Вмешательство/лечение |
|---|---|
|
Expert Speech-Language Therapists
Five speech-language therapists with clinical experience in stuttering independently evaluated responses generated by four large language models (ChatGPT, Claude, Google Gemini, and Grok-4.20). The responses addressed nine questions covering general information about stuttering, clinical assessment, and therapy. Each response was rated for relevance, accuracy, clarity, completeness, and consistency using a 5-point Likert scale. |
ChatGPT responses to nine standardized questions on stuttering information, assessment, and therapy were generated in separate sessions and recorded for independent expert evaluation. Questions were repeated under comparable conditions to allow assessment of response consistency. Claude responses to nine standardized questions on stuttering information, assessment, and therapy were generated in separate sessions and recorded for independent expert evaluation. Questions were repeated under comparable conditions to allow assessment of response consistency. Google Gemini responses to nine standardized questions on stuttering information, assessment, and therapy were generated in separate sessions and recorded for independent expert evaluation. Questions were repeated under comparable conditions to allow assessment of response consistency. Grok-4.20 responses to nine standardized questions on stuttering information, assessment, and therapy were generated in separate sessions and recorded for independent expert evaluation. Questions were repeated under comparable conditions to allow assessment of response consistency. |
Что измеряет исследование?
Первичные показатели результатов
Мера результата |
Мера Описание |
Временное ограничение |
|---|---|---|
|
Expert-Rated Quality of Large Language Model Responses
Временное ограничение: During the single cross-sectional expert evaluation conducted over approximately 1 month
|
Responses generated by four large language models (ChatGPT, Claude, Google Gemini, and Grok-4.20) to nine standardized questions about stuttering were independently evaluated by five speech-language therapists with clinical experience in stuttering. Each response was rated using a 5-point Likert scale (1 = strongly disagree to 5 = strongly agree) across five criteria: relevance, accuracy, clarity, completeness, and consistency. Responses were evaluated against guideline-based reference information derived from evidence-based clinical practice guidance. Higher scores indicate better response quality and closer alignment with clinical practice guidance. Mean scores were calculated for each large language model and each evaluation criterion. |
During the single cross-sectional expert evaluation conducted over approximately 1 month
|
Соавторы и исследователи
Спонсор
Даты записи исследования
Изучение основных дат
Начало исследования (Действительный)
Первичное завершение (Действительный)
Завершение исследования (Действительный)
Даты регистрации исследования
Первый отправленный
Впервые представлено, что соответствует критериям контроля качества
Первый опубликованный (Действительный)
Обновления учебных записей
Последнее опубликованное обновление (Действительный)
Последнее отправленное обновление, отвечающее критериям контроля качества
Последняя проверка
Дополнительная информация
Термины, связанные с этим исследованием
Дополнительные соответствующие термины MeSH
Другие идентификационные номера исследования
- LLM-STUTTER-2026
Информация о лекарствах и устройствах, исследовательские документы
Изучает лекарственный продукт, регулируемый FDA США.
Изучает продукт устройства, регулируемый Управлением по санитарному надзору за качеством пищевых продуктов и медикаментов США.
Эта информация была получена непосредственно с веб-сайта clinicaltrials.gov без каких-либо изменений. Если у вас есть запросы на изменение, удаление или обновление сведений об исследовании, обращайтесь по адресу register@clinicaltrials.gov. Как только изменение будет реализовано на clinicaltrials.gov, оно будет автоматически обновлено и на нашем веб-сайте. .