Comparative Analysis of Artificial Intelligence Virtual Assistant and Large Language Models in Post-Operative Care
Bibliographic Data
| ID | 16945891 |
|---|---|
| Authors | Sahar Borna (0000-0002-7845-7356, Mayo Clinic in Florida), Cesar A Gomez-Cabello (0009-0008-0603-3192, Mayo Clinic in Florida), Steven Pressman (0009-0000-0398-8024, Mayo Clinic in Florida), Sophia M Pressman, Syed Ali Haider (0009-0007-5621-2861, Mayo Clinic in Florida), Ashwini Sehgal (0009-0007-7562-8758, Mayo Clinic), Bradley C Leibovich (0000-0003-0043-6659, Mayo Clinic), Daniel Cole (0009-0007-2065-5089, Mayo Clinic), Antonio Jorge Forte (0000-0003-2004-7538, Mayo Clinic, corresponding author) |
| Year | 2024 |
| Volume | 14 |
| Issue | 5 |
| Pages | 1413-1424 |
| Publication date | 2024-05-15 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | European Journal of Investigation in Health, Psychology and Education (JOURNAL) |
| Journal identifiers | ISSN: 2174-8144 • E-ISSN: 2254-9625 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ejihpe14050093 |
| PMID | 38785591 |
| OpenAlex | W4396977148 |
| Language | EN |
| References cited | 37 |
In postoperative care, patient education and follow-up are pivotal for enhancing the quality of care and satisfaction. Artificial intelligence virtual assistants (AIVA) and large language models (LLMs) like Google BARD and ChatGPT-4 offer avenues for addressing patient queries using natural language processing (NLP) techniques. However, the accuracy and appropriateness of the information vary across these platforms, necessitating a comparative study to evaluate their efficacy in this domain. We conducted a study comparing AIVA (using Google Dialogflow) with ChatGPT-4 and Google BARD, assessing the accuracy, knowledge gap, and response appropriateness. AIVA demonstrated superior performance, with significantly higher accuracy (mean: 0.9) and lower knowledge gap (mean: 0.1) compared to BARD and ChatGPT-4. Additionally, AIVA’s responses received higher Likert scores for appropriateness. Our findings suggest that specialized AI tools like AIVA are more effective in delivering precise and contextually relevant information for postoperative care compared to general-purpose LLMs. While ChatGPT-4 shows promise, its performance varies, particularly in verbal interactions. This underscores the importance of tailored AI solutions in healthcare, where accuracy and clarity are paramount. Our study highlights the necessity for further research and the development of customized AI solutions to address specific medical contexts and improve patient outcomes
CLARITY · Health care · Medical education · Political science · AI in Service Interactions · Artificial Intelligence in Healthcare and Education · Computer Science · COVID-19 diagnosis using AI · Medicine · Psychology · Artificial Intelligence
| Citation velocity | historical |
|---|---|
| Highly cited | No |