โก Quick Summary
This study explored the role of Artificial Intelligence (AI), specifically ChatGPT-4o, in Speech and Language Therapy (SLT) by comparing its clinical reasoning with that of experienced speech-language therapists (SLTs). The findings revealed substantial overlap in core practices, yet highlighted the nuanced and individualized approaches that human therapists provide.
๐ Key Details
- ๐ฅ Participants: 10 experienced SLTs with โฅ10 years of experience
- ๐ Methodology: Semi-structured interviews and standardized prompts for ChatGPT-4o
- ๐ Duration: Evaluated over five consecutive days
- ๐ Focus: Assessment, diagnosis, and therapy plans for hypothetical vignettes
๐ Key Takeaways
- ๐ค AI’s Role: ChatGPT-4o can approximate expert-like reasoning in structured scenarios.
- ๐ Overlap: Significant overlap in core practices between SLTs and ChatGPT-4o.
- ๐งฉ Limitations: ChatGPT-4o lacks the clinical nuance and contextual adaptation of human therapists.
- ๐ Standardization: AI responses were more standardized compared to the individualized approaches of SLTs.
- ๐ฉโโ๏ธ Clinical Support: ChatGPT-4o may serve as a clinical decision support aid but cannot replace human therapists.
- ๐ Cultural Sensitivity: SLTs utilize locally normed assessment tools, emphasizing cultural relevance.
- ๐ก Future Potential: AI could enhance clinical decision-making in SLT, but human expertise remains essential.

๐ Background
The integration of Artificial Intelligence into healthcare is rapidly evolving, with large language models like ChatGPT entering clinical practice. However, the implications of AI in specialized fields such as Speech and Language Therapy are still being explored. Understanding how AI compares to human expertise is crucial for determining its role in patient care.
๐๏ธ Study
This qualitative comparative study involved ten experienced SLTs who participated in semi-structured interviews. They provided assessments, diagnoses, and therapy plans based on three hypothetical vignettes. Simultaneously, ChatGPT-4o was presented with standardized Turkish prompts over five consecutive days to evaluate its consistency in clinical reasoning.
๐ Results
The analysis revealed that both ChatGPT-4o and the SLTs exhibited substantial overlap in core practices, including case history and diagnostic labels. However, SLTs demonstrated a broader use of locally normed assessment tools and offered more flexible, individualized therapy approaches. ChatGPT-4o’s responses were consistent across days but lacked the clinical nuance and contextual adaptation that characterize human therapists’ reasoning.
๐ Impact and Implications
The findings of this study highlight the potential for AI to serve as a clinical decision support aid in Speech and Language Therapy. While AI can approximate expert reasoning in structured scenarios, it cannot replace the culturally grounded and person-specific assessments that experienced SLTs provide. This underscores the importance of human expertise in delivering effective therapy and the need for further research into the integration of AI in clinical settings.
๐ฎ Conclusion
This study illustrates the promising role of AI in enhancing clinical decision-making within Speech and Language Therapy. While ChatGPT-4o can provide valuable insights and support, the nuanced understanding and individualized care offered by human therapists remain irreplaceable. Continued exploration of AI’s capabilities and limitations will be essential as we navigate the future of healthcare.
๐ฌ Your comments
What are your thoughts on the integration of AI in Speech and Language Therapy? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
Artificial Intelligence in Speech and Language Therapy: A Qualitative Comparative Analysis of Clinical Applications and Outcomes.
Abstract
Large language models (LLMs) such as ChatGPT are entering clinical practice, yet how their clinical reasoning compares with speech-language therapists (SLTs) is not well understood. This comparative multi-case qualitative study used 3 hypothetical vignettes. Ten experienced SLTs (โฅ10โyears) participated in semi-structured interviews, providing assessment, diagnosis and therapy plans for each vignette. ChatGPT-4o was presented with identical, standardized Turkish prompts over fiveโconsecutive days to evaluate the model’s temporal consistency in clinical reasoning. All outputs were analyzed with content analysis, and day-to-day consistency of ChatGPT themes was examined. ChatGPT-4o and SLTs showed substantial overlap in core practices such as case history, spontaneous speech analysis, key diagnostic labels, and emphasis on generalization and caregiver involvement. However, SLTs utilized broader, locally normed assessment tools and offered more flexible, individualized and context-sensitive therapy approaches. ChatGPT-4o’s responses were more standardized and showed stable thematic patterns across days, yet they did not reflect the clinical nuance or contextual adaptation observed in SLTs’ reasoning. ChatGPT-4o can approximate expert-like reasoning in structured scenarios and may serve as a clinical decision support aid. Nonetheless, it does not replace experienced SLTs, particularly for culturally grounded, person-specific assessment and intervention planning.
Author: [‘Yaลa ฤฐC’, ‘Dรถlek M’, ‘Eyilikeder Tekin S’, ‘Kaya AS’, ‘Akgรผn P’, ‘Yฤฑlmaz SD’, ‘Tokalak S’]
Journal: Inquiry
Citation: Yaลa ฤฐC, et al. Artificial Intelligence in Speech and Language Therapy: A Qualitative Comparative Analysis of Clinical Applications and Outcomes. Artificial Intelligence in Speech and Language Therapy: A Qualitative Comparative Analysis of Clinical Applications and Outcomes. 2026; 63:469580261445316. doi: 10.1177/00469580261445316