Assessing the accuracy and completeness of artificial intelligence language models in providing information on methotrexate use

Disparities in medical recommendations from AI-based chatbots across different countries/regions

This study explores disparities and opportunities in healthcare information provided by AI chatbots. We focused on recommendations for adjuvant therapy in endometrial cancer, analyzing responses across four regions (Indonesia, Nigeria, Taiwan, USA) and three platforms (Bard, Bing, ChatGPT-3.5). Utilizing previously published cases, we asked identical questions to chatbots from each location within a 24-h window. Responses were evaluated in a double-blinded manner on relevance, clarity, depth, focus, and coherence by ten experts in endometrial cancer. Our analysis revealed significant variations across different countries/regions (p < 0.001). Interestingly, Bing's responses in Nigeria consistently outperformed others (p < 0.05), excelling in all evaluation criteria (p < 0.001). Bard also performed better in Nigeria compared to other regions (p < 0.05), consistently surpassing them across all categories (p < 0.001, with relevance reaching p < 0.01). Notably, Bard's overall scores were significantly higher than those of ChatGPT-3.5 and Bing in all locations (p < 0.001). These findings highlight disparities and opportunities in the quality of AI-powered healthcare information based on user location and platform. This emphasizes the necessity for more research and development to guarantee equal access to trustworthy medical information through AI technologies.

Can large language models provide accurate and quality information to parents regarding chronic kidney diseases?

RATIONALE

Artificial Intelligence (AI) large language models (LLM) are tools capable of generating human-like text responses to user queries across topics. The use of these language models in various medical contexts is currently being studied. However, the performance and content quality of these language models have not been evaluated in specific medical fields.

AIMS AND OBJECTIVES

This study aimed to compare the performance of AI LLMs ChatGPT, Gemini and Copilot in providing information to parents about chronic kidney diseases (CKD) and compare the information accuracy and quality with that of a reference source.

METHODS

In this study, 40 frequently asked questions about CKD were identified. The accuracy and quality of the answers were evaluated with reference to the Kidney Disease: Improving Global Outcomes guidelines. The accuracy of the responses generated by LLMs was assessed using F1, precision and recall scores. The quality of the responses was evaluated using a five-point global quality score (GQS).

RESULTS

ChatGPT and Gemini achieved high F1 scores of 0.89 and 1, respectively, in the diagnosis and lifestyle categories, demonstrating significant success in generating accurate responses. Furthermore, ChatGPT and Gemini were successful in generating accurate responses with high precision values in the diagnosis and lifestyle categories. In terms of recall values, all LLMs exhibited strong performance in the diagnosis, treatment and lifestyle categories. Average GQ scores for the responses generated were 3.46 ± 0.55, 1.93 ± 0.63 and 2.02 ± 0.69 for Gemini, ChatGPT 3.5 and Copilot, respectively. In all categories, Gemini performed better than ChatGPT and Copilot.

CONCLUSION

Although LLMs provide parents with high-accuracy information about CKD, their use is limited compared with that of a reference source. The limitations in the performance of LLMs can lead to misinformation and potential misinterpretations. Therefore, patients and parents should exercise caution when using these models.

Communicative competence of generative artificial intelligence in responding to patient queries about colorectal cancer surgery

PURPOSE

To examine the ability of generative artificial intelligence (GAI) to answer patients' questions regarding colorectal cancer (CRC).

METHODS

Ten clinically relevant questions about CRC were selected from top-rated hospitals' websites and patient surveys and presented to three GAI tools (Chatbot Generative Pre-Trained Transformer [GPT-4], Google Bard, and CLOVA X). Their responses were compared with answers from the CRC information book. Response evaluation was performed by two groups, each consisting of five healthcare professionals (HCP) and patients. Each question was scored on a 1-5 Likert scale based on four evaluation criteria (maximum score, 20 points/question).

RESULTS

In an analysis including only HCPs, the information book scored 11.8 ± 1.2, GPT-4 scored 13.5 ± 1.1, Google Bard scored 11.5 ± 0.7, and CLOVA X scored 12.2 ± 1.4 (P = 0.001). The score of GPT-4 was significantly higher than those of the information book (P = 0.020) and Google Bard (P = 0.001). In an analysis including only patients, the information book scored 14.1 ± 1.4, GPT-4 scored 15.2 ± 1.8, Google Bard scored 15.5 ± 1.8, and CLOVA X scored 14.4 ± 1.8, without significant differences (P = 0.234). When both groups of evaluators were included, the information book scored 13.0 ± 0.9, GPT-4 scored 14.4 ± 1.2, Google Bard scored 13.5 ± 1.0, and CLOVA X scored 13.3 ± 1.5 (P = 0.070).

CONCLUSION

The three GAIs demonstrated similar or better communicative competence than the information book regarding questions related to CRC surgery in Korean. If high-quality medical information provided by GAI is supervised properly by HCPs and published as an information book, it could be helpful for patients to obtain accurate information and make informed decisions.

Exploring the Role of ChatGPT-4, BingAI, and Gemini as Virtual Consultants to Educate Families about Retinopathy of Prematurity

BACKGROUND

Large language models (LLMs) are becoming increasingly important as they are being used more frequently for providing medical information. Our aim is to evaluate the effectiveness of electronic artificial intelligence (AI) large language models (LLMs), such as ChatGPT-4, BingAI, and Gemini in responding to patient inquiries about retinopathy of prematurity (ROP).

METHODS

The answers of LLMs for fifty real-life patient inquiries were assessed using a 5-point Likert scale by three ophthalmologists. The models' responses were also evaluated for reliability with the DISCERN instrument and the EQIP framework, and for readability using the Flesch Reading Ease (FRE), Flesch-Kincaid Grade Level (FKGL), and Coleman-Liau Index.

RESULTS

ChatGPT-4 outperformed BingAI and Gemini, scoring the highest with 5 points in 90% (45 out of 50) and achieving ratings of "agreed" or "strongly agreed" in 98% (49 out of 50) of responses. It led in accuracy and reliability with DISCERN and EQIP scores of 63 and 72.2, respectively. BingAI followed with scores of 53 and 61.1, while Gemini was noted for the best readability (FRE score of 39.1) but lower reliability scores. Statistically significant performance differences were observed particularly in the screening, diagnosis, and treatment categories.

CONCLUSION

ChatGPT-4 excelled in providing detailed and reliable responses to ROP-related queries, although its texts were more complex. All models delivered generally accurate information as per DISCERN and EQIP assessments.

Evaluation of ChatGPT-Generated Educational Patient Pamphlets for Common Interventional Radiology Procedures

RATIONALE AND OBJECTIVES

This study aimed to evaluate the accuracy and reliability of educational patient pamphlets created by ChatGPT, a large language model, for common interventional radiology (IR) procedures.

METHODS AND MATERIALS

Twenty frequently performed IR procedures were selected, and five users were tasked to independently request ChatGPT to generate educational patient pamphlets for each procedure using identical commands. Subsequently, two independent radiologists assessed the content, quality, and accuracy of the pamphlets. The review focused on identifying potential errors, inaccuracies, the consistency of pamphlets.

RESULTS

In a thorough analysis of the education pamphlets, we identified shortcomings in 30% (30/100) of pamphlets, with a total of 34 specific inaccuracies, including missing information about sedation for the procedure (10/34), inaccuracies related to specific procedural-related complications (8/34). A key-word co-occurrence network showed consistent themes within each group of pamphlets, while a line-by-line comparison at the level of users and across different procedures showed statistically significant inconsistencies (P < 0.001).

CONCLUSION

ChatGPT-generated education pamphlets demonstrated potential clinical relevance and fairly consistent terminology; however, the pamphlets were not entirely accurate and exhibited some shortcomings and inter-user structural variabilities. To ensure patient safety, future improvements and refinements in large language models are warranted, while maintaining human supervision and expert validation.

The performance of artificial intelligence models in generating responses to general orthodontic questions: ChatGPT vs Google Bard

INTRODUCTION

This study aimed to evaluate and compare the performance of 2 artificial intelligence (AI) models, Chat Generative Pretrained Transformer-3.5 (ChatGPT-3.5; OpenAI, San Francisco, Calif) and Google Bidirectional Encoder Representations from Transformers (Google Bard; Bard Experiment, Google, Mountain View, Calif), in terms of response accuracy, completeness, generation time, and response length when answering general orthodontic questions.

METHODS

A team of orthodontic specialists developed a set of 100 questions in 10 orthodontic domains. One author submitted the questions to both ChatGPT and Google Bard. The AI-generated responses from both models were randomly assigned into 2 forms and sent to 5 blinded and independent assessors. The quality of AI-generated responses was evaluated using a newly developed tool for accuracy of information and completeness. In addition, response generation time and length were recorded.

RESULTS

The accuracy and completeness of responses were high in both AI models. The median accuracy score was 9 (interquartile range [IQR]: 8-9) for ChatGPT and 8 (IQR: 8-9) for Google Bard (Median difference: 1; P <0.001). The median completeness score was similar in both models, with 8 (IQR: 8-9) for ChatGPT and 8 (IQR: 7-9) for Google Bard. The odds of accuracy and completeness were higher by 31% and 23% in ChatGPT than in Google Bard. Google Bard's response generation time was significantly shorter than that of ChatGPT by 10.4 second/question. However, both models were similar in terms of response length generation.

CONCLUSIONS

Both ChatGPT and Google Bard generated responses were rated with a high level of accuracy and completeness to the posed general orthodontic questions. However, acquiring answers was generally faster using the Google Bard model.

Comparison of the Audiological Knowledge of Three Chatbots: ChatGPT, Bing Chat, and Bard

INTRODUCTION

The purpose of this study was to evaluate three chatbots - OpenAI ChatGPT, Microsoft Bing Chat (currently Copilot), and Google Bard (currently Gemini) - in terms of their responses to a defined set of audiological questions.

METHODS

Each chatbot was presented with the same 10 questions. The authors rated the responses on a Likert scale ranging from 1 to 5. Additional features, such as the number of inaccuracies or errors and the provision of references, were also examined.

RESULTS

Most responses given by all three chatbots were rated as satisfactory or better. However, all chatbots generated at least a few errors or inaccuracies. ChatGPT achieved the highest overall score, while Bard was the worst. Bard was also the only chatbot unable to provide a response to one of the questions. ChatGPT was the only chatbot that did not provide information about its sources.

CONCLUSIONS

Chatbots are an intriguing tool that can be used to access basic information in a specialized area like audiology. Nevertheless, one needs to be careful, as correct information is not infrequently mixed in with errors that are hard to pick up unless the user is well versed in the field.

ChatGPT performance in prosthodontics: Assessment of accuracy and repeatability in answer generation

STATEMENT OF PROBLEM

The artificial intelligence (AI) software program ChatGPT is based on large language models (LLMs) and is widely accessible. However, in prosthodontics, little is known about its performance in generating answers.

PURPOSE

The purpose of this study was to determine the performance of ChatGPT in generating answers about removable dental prostheses (RDPs) and tooth-supported fixed dental prostheses (FDPs).

MATERIAL AND METHODS

Thirty short questions were designed about RDPs and tooth-supported FDP, and 30 answers were generated for each of the questions using ChatGPT-4 in October 2023. The 900 generated answers were independently graded by experts using a 3-point Likert scale. The relative frequency and absolute percentage of answers were described. Accuracy was assessed using the Wald binomial method, while repeatability was evaluated using percentage agreement, Brennan and Prediger coefficient, Conger generalized Cohen kappa, Fleiss kappa, Gwet AC, and Krippendorff alpha methods. Confidence intervals were set at 95%. Statistical analysis was performed using the STATA software program.

RESULTS

The performance of ChatGPT in generating answers related to RDP and tooth-supported FDP was limited. The answers showed a reliability of 25.6%, with a confidence range between 22.9% and 28.6%. The repeatability ranged from substantial to moderate.

CONCLUSIONS

The results show that currently ChatGPT has limited ability to generate answers related to RDPs and tooth-supported FDPs. Therefore, ChatGPT cannot replace a dentist, and, if professionals were to use it, they should be aware of its limitations.