Abstract

The integration of generative artificial intelligence (AI) into pediatric speech-language pathology (SLP) presents new opportunities for enhancing clinical efficiency, creativity, and personalized care. This article explores the emerging field of prompt engineering, the practice of crafting precise AI instructions to yield clinically relevant and developmentally appropriate outputs, and its transformative potential in speech therapy. The article outline essential prompt components and adaptable prompt patterns tailored for SLP applications, emphasizing how clinicians can leverage these tools to create individualized therapy materials across a range of disorders, including fluency, articulation, language delays, and social communication challenges. Furthermore, I introduce the adapted “SLP Prompt Canvas Toolkit,” a structured framework designed to guide clinicians in systematically developing effective prompts. By combining clinical expertise with AI capabilities, speech-language pathologists can optimize therapy planning, expand creative possibilities, and deliver evidence-based interventions more efficiently. Finally, the article address best practices, ethical considerations, and future directions to ensure that generative AI supports patient-centered care while maintaining accuracy and safety in clinical contexts.

Keywords

Generative AI, Speech-Language Pathology, Prompt Engineering, Paediatric Therapy, Chatgpt, Clinical Efficiency, Personalized Intervention,

References

  1. American Speech-Language-Hearing Association. (2016). Scope of practice in speech-language pathology https://www.asha.org/policy/sp2016-00343/
  2. American Speech-Language-Hearing Association. (2023). the Big Nine. https://find.asha.org/asha/#sort=relevancy
  3. Belda-Medina, J., Calvo-Ferrer, J.R. (2022). Using chatbots as AI conversational partners in language learning. Applied Sciences, 12(17), 8427. https://doi.org/10.3390/app12178427
  4. Bender, E.M., Gebru, T., McMillan-Major, A., Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610-623. https://doi.org/10.1145/3442188.3445922
  5. Brahmi, Z., Mahyoob, M., Al-Sarem, M., Algaraady, J., Bousselmi, K., Alblwi, A. (2024). Exploring the role of machine learning in diagnosing and treating speech disorders: A systematic literature review. Psychology Research and Behavior Management, 17, 2205–2232. https://doi.org/10.2147/PRBM.S460283
  6. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A. and Agarwal, S., (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. https://doi.org/10.48550/arXiv.2005.14165
  7. Cho, Y., Kim, M., Kim, S., Kwon, O., Kwon, R. D., Lee, Y., Lim, D. (2023). Evaluating the efficacy of interactive language therapy based on large language models for high-functioning autistic adolescent psychological counseling. arXiv. https://doi.org/10.48550/arXiv.2311.09243
  8. Deka, C., Shrivastava, A., Abraham, A.K., Nautiyal, S., Chauhan, P. (2024). AI-based automated speech therapy tools for persons with speech sound disorder: A systematic litera-ture review. Speech, Language and Hearing, 28(1), 2359274. https://doi.org/10.1080/2050571X.2024.2359274
  9. Du, Y., Choe, S., Vega, J., Liu, Y., Trujillo, A., colleagues. (2022). Listening to stakeholders involved in speech-language therapy for children with communication disorders: Content analysis of Apple App Store reviews. JMIR Pediatrics and Parenting, 5(1), e28661. https://doi.org/10.2196/28661
  10. Du, Y., Juefei Xu, F. (2023). Generative AI for therapy? Opportunities and barriers for ChatGPT in speech language therapy. Tiny Papers@ICLR 2023. https://openreview.net/forum?id=cRZSr6Tpr1S
  11. Federiakin, D., Molerov, D., Zlatkin-Troitschanskaia, O. and Maur, A. (2024). Understanding prompt structure: Instruction, context, input data, and output indicators. Frontiers in Education, 9, 1366434. https://doi.org/10.3389/feduc.2024.1366434
  12. Ganzeboom, M., Bakker, M., Beijer, L., Strik, H., Rietveld, T. (2022). A serious game for speech training in dysarthric speakers with Parkinson’s disease: Exploring therapeutic effi-cacy and patient satisfaction. International Journal of Lan-guage & Communication Disorders, 57(4), 808-821. https://doi.org/10.1111/1460-6984.12722
  13. Gao, E., Chen, J. (2024). Prompt engineering in healthcare: Designing and optimizing input prompts to guide AI systems toward generating clinically relevant and accurate outputs. Electronics, 13(15), 2961. https://doi.org/10.3390/electronics13152961
  14. Gerke, S., Minssen, T., Cohen, G. (2020). Ethical and legal challenges of artificial intelligence-driven healthcare. In Artificial Intelligence in Healthcare, Academic Press. 295–336. https://doi.org/10.1016/B978-0-12-818438-7.00012-5
  15. Green, J.R. (2024). Artificial intelligence in communication sciences and disorders: Introduction to the forum. Journal of Speech, Language, and Hearing Research, 67(11), 4157–4161. https://doi.org/10.1044/2024_JSLHR-24-00594
  16. Hebb, D.O. (2005). The organization of behavior: A neuropsychological theory (1st ed.). Psychology Press. https://doi.org/10.4324/9781410612403
  17. Hewing, M., Leinhos, V. (2024). The Prompt Canvas: A literature-based practitioner guide for creating effective prompts in large language models, arXiv. ArXiv:2412.05127v1. https://arxiv.org/abs/2412.05127
  18. Jauk, S., Kramer, D., Veeranki, S. P. K., Siml-Fraissler, A., Lenz-Waldbauer, A., Tax, E., Leodolter, W., Gugatschka, M. (2023). Evaluation of a machine learning-based dysphagia prediction tool in clinical routine: A prospective observational cohort study. Dysphagia, 38(4), 1238–1246. https://doi.org/10. 1007/s00455-022-10548-9
  19. Kim, Y., Kim, M., Kim, J., Song, T.J. (2024). Smartphone-based speech therapy for poststroke dysarthria: Pilot random-ized controlled trial evaluating efficacy and feasibility. Journal of Medical Internet Research, 26, e56417. https://doi.org/10.2196/56417
  20. Li, X. L., Liang, P. (2021). Prefix tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Long Papers). Association for Computational Linguistics, 1, 4582–4597. https://doi.org/10.18653/v1/2021.acl-long.353
  21. Liss, J., Berisha, V. (2020). How will artificial intelligence reshape speech-language pathology services and practice in the future? ASHA Leader Live. https://academy.pubs.asha.org/2020/08/how-will-artificial-intelligence-reshape-speech-language-pathology-services-and-practice-in-the-future/
  22. Lu, A., Zhang, H., Zhang, Y., Wang, X., Yang, D. (2023). Bounding the capabilities of large language models in open text generation with prompt constraints. arXivpreprint. https://doi.org/10.48550/arXiv.2302.09185
  23. McCulloch, W.S., Pitts, W.A. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115–133. https://doi.org/10.1007/BF02478259
  24. Neumann, M., Kothare, H., Ramanarayanan, V. (2024). Multi-modal speech biomarkers for remote monitoring of ALS disease progression. Computers in Biology and Medicine, 180, 108949. https://doi.org/10.1016/j.compbiomed.2024.108949
  25. OpenAI. (2022). ChatGPT release notes [Software]. OpenAI. https://help.openai.com/en/articles/6825453-chatgpt-release-notes#h_e18c6a1b3a
  26. Privitera, A.J., Ng, S.H.S., Kong, A.P.H., Weekes, B.S. (2024). AI and aphasia in the digital age: A critical review. Brain Sciences, 14(4), 383. https://doi.org/10.3390/brainsci14040383
  27. Richter, V., Neumann, M., Green, J. R., Richburg, B., Roesler, O., Kothare, H., Ramanarayanan, V. (2023). Remote assess-ment for ALS using multimodal dialog agents: Data quality, fea-sibility and task compliance. Proceedings of INTERSPEECH, 2023, 5441–5445. https://doi.org/10.21437/Interspeech.2023-2115
  28. Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386–408. https://doi.org/10.1037/h0042519
  29. Russell, S.J., Norvig, P. (2020). Artificial intelligence: A modern approach (4th ed.). Pearson Education. https://aima.cs.berkeley.edu/
  30. Sahoo, P., Kumar Singh, A., Saha, S., Jain, V., Mondal, S., Chadha, A. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927. https://doi.org/10.48550/arXiv.2402.07927
  31. Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., Dulepet, P.S., Vidyadhara, S., Ki, D., Agrawal, S., Pham, C., Kroiz, G., Li, F., Tao, H., Srivastava, A., Da Costa, H., Gupta, S., Rogers, M. L., Goncearenco, I., Sarli, G., Galynker, I., Peskoff, D., Carpuat, M., White, J., Anadkat, S., Hoyle, A.M., Resnik, P. (2024). Instruction prompting: Providing clear, task oriented directions to improve AI response fidelity. The Prompt Report: A Systematic Survey of Prompting Techniques. arXiv. https://doi.org/10.48550/arXiv.2406.06608
  32. Suh, H., Dangol, A., Meadan, H., Miller, C.A., Kientz, J. A. (2024). Opportunities and challenges for AI-based support for speech-language pathologists. Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Inter-action for Work, 14. https://doi.org/10.1145/3663384.3663387
  33. Tang, L., Sun, Z., Idnay, B., Nestor, J.G., Soroush, A., Elias, P.A., Xu, Z., Ding, Y., Durrett, G., Rousseau, J.F. and Weng, C., (2023). Evaluating large language models on medical evidence summarization. NPJ Digital Medicine, 6, 158. https://doi.org/10.1038/s41746-023-00896-7
  34. Wang, R.H., Kenyon, L.K., McGilton, K.S., Miller, W.C., Hovanec, N., Boger, J., Viswanathan, P., Robillard, J.M., Czarnuch, S.M. (2021). The time is now: a FASTER approach to generate research evidence for technology-based interventions in the field of disability and rehabilitation. Archives of Physical Medicine and Rehabilitation, 102(9), 1848-1859. https://doi.org/10.1016/j.apmr.2021.04.009
  35. White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., Schmidt, D. C. (2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv. https://doi.org/10.48550/arXiv.2302.11382