Evaluating the Potential of AI Chatbots in Treatment Decision-making for Acquired Bilateral Vocal Fold Paralysis in Adults.

J Voice

Division of Laryngology and Broncho-esophagology, Department of Otolaryngology-Head Neck Surgery, EpiCURA Hospital, UMONS Research Institute for Health Sciences and Technology, University of Mons (UMons), Mons, Belgium; Department of Otorhinolaryngology and Head and Neck Surgery, Foch Hospital, Scho

Published: July 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Objectives: The development of artificial intelligence-powered language models, such as Chatbot Generative Pre-trained Transformer (ChatGPT) or Large Language Model Meta AI (Llama), is emerging in medicine. Patients and practitioners have full access to chatbots that may provide medical information. The aim of this study was to explore the performance and accuracy of ChatGPT and Llama in treatment decision-making for bilateral vocal fold paralysis (BVFP).

Methods: Data of 20 clinical cases, treated between 2018 and 2023, were retrospectively collected from four tertiary laryngology centers in Europe. The cases were defined as the most common or most challenging scenarios regarding BVFP treatment. The treatment proposals were discussed in their local multidisciplinary teams (MDT). Each case was presented to ChatGPT-4.0 and Llama Chat-2.0, and potential treatment strategies were requested. The Artificial Intelligence Performance Instrument (AIPI) treatment subscore was used to compare both Chatbots' performances to MDT treatment proposal.

Results: Most common etiology of BVFP was thyroid surgery. A form of partial arytenoidectomy with or without posterior transverse cordotomy was the MDT proposal for most cases. The accuracy of both Chatbots was very low regarding their treatment proposals, with a maximum AIPI treatment score in 5% of the cases. In most cases even harmful assertions were made, including the suggestion of vocal fold medialisation to treat patients with stridor and dyspnea. ChatGPT-4.0 performed significantly better in suggesting the correct treatment as part of the treatment proposal (50%) compared to Llama Chat-2.0 (15%).

Conclusion: ChatGPT and Llama are judged as inaccurate in proposing correct treatment for BVFP. ChatGPT significantly outperformed Llama. Treatment decision-making for a complex condition such as BVFP is clearly beyond the Chatbot's knowledge expertise. This study highlights the complexity and heterogeneity of BVFP treatment, and the need for further guidelines dedicated to the management of BVFP.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jvoice.2024.02.020DOI Listing

Publication Analysis

Top Keywords

treatment
14
treatment decision-making
12
vocal fold
12
bilateral vocal
8
fold paralysis
8
chatgpt llama
8
llama treatment
8
bvfp treatment
8
treatment treatment
8
treatment proposals
8

Similar Publications

Background: Owing to the unique characteristics of digital health interventions (DHIs), a tailored approach to economic evaluation is needed-one that is distinct from that used for pharmacotherapy. However, the absence of clear guidelines in this area is a substantial gap in the evaluation framework.

Objective: This study aims to systematically review and compare the economic evaluation literature on DHIs and pharmacotherapy for the treatment of depression.

View Article and Find Full Text PDF

Background: Breast cancer treatment, particularly during the perioperative period, is often accompanied by significant psychological distress, including anxiety and uncertainty. Mobile health (mHealth) interventions have emerged as promising tools to provide timely psychosocial support through convenient, flexible, and personalized platforms. While research has explored the use of mHealth in breast cancer prevention, care management, and survivorship, few studies have examined patients' experiences with mobile interventions during the perioperative phase of breast cancer treatment.

View Article and Find Full Text PDF

Introduction: Diabetes Mellitus is a chronic disease characterised by elevated plasma glucose (PG) levels. HbA1c has been widely utilized for diabetes diagnosis. However, certain conditions restrict its use.

View Article and Find Full Text PDF

Tuning the Electrical Property and Electronic Band Structures of Organic Semiconductors via Surface Tension.

J Phys Chem Lett

September 2025

National Laboratory of Solid-State Microstructures, School of Electronic Science and Engineering, Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, P. R. China.

Stress engineering is an effective way to tune the performance of semiconductors, which has been verified in the work of inorganic and organic single-crystal semiconductors. However, due to the limitations of the vapor-phase growth preparation conditions, the deposited polycrystalline organic semiconductors are more susceptible to residual stress. Therefore, it is of great research significance to develop a low-cost stress engineering applicable to vapor-deposited semiconductors.

View Article and Find Full Text PDF

Systemic Delivery of an mRNA-Encoding, Tumor-Activated Interleukin-12 Lock to Eliminate Tumors and Avoid Immune-Related Adverse Events.

Nano Lett

September 2025

Molecular Science and Biomedicine Laboratory (MBL), State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, College of Biology, Aptamer Engineering Center of Hunan Province, Hunan University, Changsha 410082, China.

Interleukin-12 (IL-12) is a robust proinflammatory cytokine that activates immune cells, such as T cells and natural killer cells, to induce antitumor immunity. However, the clinical application of recombinant IL-12 has been limited by systemic immune-related adverse events (irAEs) and rapid degradation. To address these challenges, we employed mRNA technology to encode a tumor-activated IL-12 "lock" fusion protein that offers both therapeutic efficacy and systemic safety.

View Article and Find Full Text PDF