ChatGPT in Research: Balancing Ethics, Transparency and Advancement

A comparison of drug information question responses by a drug information center and by ChatGPT

PURPOSE

A study was conducted to assess the accuracy and ability of Chat Generative Pre-trained Transformer (ChatGPT) to systematically respond to drug information inquiries relative to responses of a drug information center (DIC).

METHODS

Ten drug information questions answered by the DIC in 2022 or 2023 were selected for analysis. Three pharmacists created new ChatGPT accounts and submitted each question to ChatGPT at the same time. Each question was submitted twice to identify consistency in responses. Two days later, the same process was conducted by a fourth pharmacist. Phase 1 of data analysis consisted of a drug information pharmacist assessing all 84 ChatGPT responses for accuracy relative to the DIC responses. In phase 2, 10 ChatGPT responses were selected to be assessed by 3 blinded reviewers. Reviewers utilized an 8-question predetermined rubric to evaluate the ChatGPT and DIC responses.

RESULTS

When comparing the ChatGPT responses (n = 84) to the DIC responses, ChatGPT had an overall accuracy rate of 50%. Accuracy across the different question types varied. In regards to the overall blinded score, ChatGPT responses scored higher than the responses by the DIC according to the rubric (overall scores of 67.5% and 55.0%, respectively). The DIC responses scored higher in the categories of references mentioned and references identified.

CONCLUSION

Responses generated by ChatGPT have been found to be better than those created by a DIC in clarity and readability; however, the accuracy of ChatGPT responses was lacking. ChatGPT responses to drug information questions would need to be carefully reviewed for accuracy and completeness.

ChatGPT's Performance in Spinal Metastasis Cases-Can We Discuss Our Complex Cases with ChatGPT?

Background: The integration of artificial intelligence (AI), particularly large language models (LLMs) like ChatGPT-4, is transforming healthcare. ChatGPT's potential to assist in decision-making for complex cases, such as spinal metastasis treatment, is promising but widely untested. Especially in cancer patients who develop spinal metastases, precise and personalized treatment is essential. This study examines ChatGPT-4's performance in treatment planning for spinal metastasis cases compared to experienced spine surgeons. Materials and Methods: Five spine metastasis cases were randomly selected from recent literature. Consequently, five spine surgeons and ChatGPT-4 were tasked with providing treatment recommendations for each case in a standardized manner. Responses were analyzed for frequency distribution, agreement, and subjective rater opinions. Results: ChatGPT's treatment recommendations aligned with the majority of human raters in 73% of treatment choices, with moderate to substantial agreement on systemic therapy, pain management, and supportive care. However, ChatGPT's recommendations tended towards generalized statements, with raters noting its generalized answers. Agreement among raters improved in sensitivity analyses excluding ChatGPT, particularly for controversial areas like surgical intervention and palliative care. Conclusions: ChatGPT shows potential in aligning with experienced surgeons on certain treatment aspects of spinal metastasis. However, its generalized approach highlights limitations, suggesting that training with specific clinical guidelines could potentially enhance its utility in complex case management. Further studies are necessary to refine AI applications in personalized healthcare decision-making.

Evaluation of ChatGPT as a Tool for Answering Clinical Questions in Pharmacy Practice

Background: In the healthcare field, there has been a growing interest in using artificial intelligence (AI)-powered tools to assist healthcare professionals, including pharmacists, in their daily tasks. Objectives: To provide commentary and insight into the potential for generative AI language models such as ChatGPT as a tool for answering practice-based, clinical questions and the challenges that need to be addressed before implementation in pharmacy practice settings. Methods: To assess ChatGPT, pharmacy-based questions were prompted to ChatGPT (Version 3.5; free version) and responses were recorded. Question types included 6 drug information questions, 6 enhanced prompt drug information questions, 5 patient case questions, 5 calculations questions, and 10 drug knowledge questions (e.g., top 200 drugs). After all responses were collected, ChatGPT responses were assessed for appropriateness. Results: ChatGPT responses were generated from 32 questions in 5 categories and evaluated on a total of 44 possible points. Among all ChatGPT responses and categories, the overall score was 21 of 44 points (47.73%). ChatGPT scored higher in pharmacy calculation (100%), drug information (83%), and top 200 drugs (80%) categories and lower in drug information enhanced prompt (33%) and patient case (20%) categories. Conclusion: This study suggests that ChatGPT has limited success as a tool to answer pharmacy-based questions. ChatGPT scored higher in calculation and multiple-choice questions but scored lower in drug information and patient case questions, generating misleading or fictional answers and citations.

Quantitative Comparison of Chatbots on Common Rhinology Pathologies

OBJECTIVES

Understanding the strengths and weaknesses of chatbots as a source of patient information is critical for providers in the rising artificial intelligence landscape. This study is the first to quantitatively analyze and compare four of the most used chatbots available regarding treatments of common pathologies in rhinology.

METHODS

The treatment of epistaxis, chronic sinusitis, sinus infection, allergic rhinitis, allergies, and nasal polyps was asked to chatbots ChatGPT, ChatGPT Plus, Google Bard, and Microsoft Bing in May 2023. Individual responses were analyzed by reviewers for readability, quality, understandability, and actionability using validated scoring metrics. Accuracy and comprehensiveness were evaluated for each response by two experts in rhinology.

RESULTS

ChatGPT, Plus, Bard, and Bing had FRE readability scores of 33.17, 35.93, 46.50, and 46.32, respectively, indicating higher readability for Bard and Bing compared to ChatGPT (p = 0.003, p = 0.008) and Plus (p = 0.025, p = 0.048). ChatGPT, Plus, and Bard had mean DISCERN quality scores of 20.42, 20.89, and 20.61, respectively, which was higher than the score for Bing of 16.97 (p < 0.001). For understandability, ChatGPT and Bing had PEMAT scores of 76.67 and 66.61, respectively, which were lower than both Plus at 92.00 (p < 0.001, p < 0.001) and Bard at 92.67 (p < 0.001, p < 0.001). ChatGPT Plus had an accuracy score of 4.39 which was higher than ChatGPT (3.97, p = 0.118), Bard (3.72, p = 0.002), and Bing (3.19, p < 0.001).

CONCLUSION

On aggregate of the tested domains, our results suggest ChatGPT Plus and Google Bard are currently the most patient-friendly chatbots for the treatment of common pathologies in rhinology.

LEVEL OF EVIDENCE

N/A Laryngoscope, 134:4225-4231, 2024.

Utilizing artificial intelligence in academic writing: an in-depth evaluation of a scientific review on fertility preservation written by ChatGPT-4

PURPOSE

To evaluate the ability of ChatGPT-4 to generate a biomedical review article on fertility preservation.

METHODS

ChatGPT-4 was prompted to create an outline for a review on fertility preservation in men and prepubertal boys. The outline provided by ChatGPT-4 was subsequently used to prompt ChatGPT-4 to write the different parts of the review and provide five references for each section. The different parts of the article and the references provided were combined to create a single scientific review that was evaluated by the authors, who are experts in fertility preservation. The experts assessed the article and the references for accuracy and checked for plagiarism using online tools. In addition, both experts independently scored the relevance, depth, and currentness of the ChatGPT-4's article using a scoring matrix ranging from 0 to 5 where higher scores indicate higher quality.

RESULTS

ChatGPT-4 successfully generated a relevant scientific article with references. Among 27 statements needing citations, four were inaccurate. Of 25 references, 36% were accurate, 48% had correct titles but other errors, and 16% were completely fabricated. Plagiarism was minimal (mean = 3%). Experts rated the article's relevance highly (5/5) but gave lower scores for depth (2-3/5) and currentness (3/5).

CONCLUSION

ChatGPT-4 can produce a scientific review on fertility preservation with minimal plagiarism. While precise in content, it showed factual and contextual inaccuracies and inconsistent reference reliability. These issues limit ChatGPT-4 as a sole tool for scientific writing but suggest its potential as an aid in the writing process.

Exploring the Role of Artificial Intelligence Chatbots in Preoperative Counseling for Head and Neck Cancer Surgery

OBJECTIVE

To evaluate the potential use of artificial intelligence (AI) chatbots, such as ChatGPT, in preoperative counseling for patients undergoing head and neck cancer surgery.

STUDY DESIGN

Cross-Sectional Survey Study.

SETTING

Single institution tertiary care center.

METHODS

ChatGPT was used to generate presurgical educational information including indications, risks, and recovery time for five common head and neck surgeries. Chatbot-generated information was compared with information gathered from a simple browser search (first publicly available website excluding scholarly articles). The accuracy of the information, readability, thoroughness, and number of errors were compared by five experienced head and neck surgeons in a blinded fashion. Each surgeon then chose a preference between the two information sources for each surgery.

RESULTS

With the exception of total word count, ChatGPT-generated pre-surgical information has similar readability, content of knowledge, accuracy, thoroughness, and numbers of medical errors when compared to publicly available websites. Additionally, ChatGPT was preferred 48% of the time by experienced head and neck surgeons.

CONCLUSION

Head and neck surgeons rated ChatGPT-generated and readily available online educational materials similarly. Further refinement in AI technology may soon open more avenues for patient counseling. Future investigations into the medical safety of AI counseling and exploring patients' perspectives would be of strong interest.

LEVEL OF EVIDENCE

N/A. Laryngoscope, 134:2757-2761, 2024.

BPPV Information on Google Versus AI (ChatGPT)

OBJECTIVE

To quantitatively compare online patient education materials found using traditional search engines (Google) versus conversational Artificial Intelligence (AI) models (ChatGPT) for benign paroxysmal positional vertigo (BPPV).

STUDY DESIGN

The top 30 Google search results for "benign paroxysmal positional vertigo" were compared to the OpenAI conversational AI language model, ChatGPT, responses for 5 common patient questions posed about BPPV in February 2023. Metrics included readability, quality, understandability, and actionability.

SETTING

Online information.

METHODS

Validated online information metrics including Flesch-Kincaid Grade Level (FKGL), Flesch Reading Ease (FRE), DISCERN instrument score, and Patient Education Materials Assessment Tool for Printed Materials were analyzed and scored by reviewers.

RESULTS

Mean readability scores, FKGL and FRE, for the Google webpages were 10.7 ± 2.6 and 46.5 ± 14.3, respectively. ChatGPT responses had a higher FKGL score of 13.9 ± 2.5 (P < .001) and a lower FRE score of 34.9 ± 11.2 (P = .005), both corresponding to lower readability. The Google webpages had a DISCERN part 2 score of 25.4 ± 7.5 compared to the individual ChatGPT responses with a score of 17.5 ± 3.9 (P = .001), and the combined ChatGPT responses with a score of 25.0 ± 0.9 (P = .928). The average scores of the reviewers for all ChatGPT responses for accuracy were 4.19 ± 0.82 and 4.31 ± 0.67 for currency.

CONCLUSION

The results of this study suggest that the information on ChatGPT is more difficult to read, of lower quality, and more difficult to comprehend compared to information on Google searches.

Generative artificial intelligence performs rudimentary structural biology modeling

Natural language-based generative artificial intelligence (AI) has become increasingly prevalent in scientific research. Intriguingly, capabilities of generative pre-trained transformer (GPT) language models beyond the scope of natural language tasks have recently been identified. Here we explored how GPT-4 might be able to perform rudimentary structural biology modeling. We prompted GPT-4 to model 3D structures for the 20 standard amino acids and an α-helical polypeptide chain, with the latter incorporating Wolfram mathematical computation. We also used GPT-4 to perform structural interaction analysis between nirmatrelvir and its target, the SARS-CoV-2 main protease. Geometric parameters of the generated structures typically approximated close to experimental references. However, modeling was sporadically error-prone and molecular complexity was not well tolerated. Interaction analysis further revealed the ability of GPT-4 to identify specific amino acid residues involved in ligand binding along with corresponding bond distances. Despite current limitations, we show the capacity of natural language generative AI to perform basic structural biology modeling and interaction analysis with atomic-scale accuracy.

Chatbot Performance in Defining and Differentiating Palliative Care, Supportive Care, Hospice Care

CONTEXT

Artificial intelligence (AI) chatbot platforms are increasingly used by patients as sources of information. However, there is limited data on the performance of these platforms, especially regarding palliative care terms.

OBJECTIVES

We evaluated the accuracy, comprehensiveness, reliability, and readability of three AI platforms in defining and differentiating "palliative care," "supportive care," and "hospice care."

METHODS

We asked ChatGPT, Microsoft Bing Chat, Google Bard to define and differentiate "palliative care," "supportive care," and "hospice care" and provide three references. Outputs were randomized and assessed by six blinded palliative care physicians using 0-10 scales (10 = best) for accuracy, comprehensiveness, and reliability. Readability was assessed using Flesch Kincaid Grade Level and Flesch Reading Ease scores.

RESULTS

The mean (SD) accuracy scores for ChatGPT, Bard, and Bing Chat were 9.1 (1.3), 8.7 (1.5), and 8.2 (1.7), respectively; for comprehensiveness, the scores for the three platforms were 8.7 (1.5), 8.1 (1.9), and 5.6 (2.0), respectively; for reliability, the scores were 6.3 (2.5), 3.2 (3.1), and 7.1 (2.4), respectively. Despite generally high accuracy, we identified some major errors (e.g., Bard stated that supportive care had "the goal of prolonging life or even achieving a cure"). We found several major omissions, particularly with Bing Chat (e.g., no mention of interdisciplinary teams in palliative care or hospice care). References were often unreliable. Readability scores did not meet recommended levels for patient educational materials.

CONCLUSION

We identified important concerns regarding the accuracy, comprehensiveness, reliability, and readability of outputs from AI platforms. Further research is needed to improve their performance.

Leveraging and exercising caution with ChatGPT and other generative artificial intelligence tools in environmental psychology research

Generative Artificial Intelligence (GAI) is an emerging and disruptive technology that has attracted considerable interest from researchers and educators across various disciplines. We discuss the relevance and concerns of ChatGPT and other GAI tools in environmental psychology research. We propose three use categories for GAI tools: integrated and contextualized understanding, practical and flexible implementation, and two-way external communication. These categories are exemplified by topics such as the health benefits of green space, theory building, visual simulation, and identifying practical relevance. However, we also highlight the balance of productivity with ethical issues, as well as the need for ethical guidelines, professional training, and changes in the academic performance evaluation systems. We hope this perspective can foster constructive dialogue and responsible practice of GAI tools.

Publishers' and journals' instructions to authors on use of generative artificial intelligence in academic and scientific publishing: bibliometric analysis

OBJECTIVES

To determine the extent and content of academic publishers' and scientific journals' guidance for authors on the use of generative artificial intelligence (GAI).

DESIGN

Cross sectional, bibliometric study.

SETTING

Websites of academic publishers and scientific journals, screened on 19-20 May 2023, with the search updated on 8-9 October 2023.

PARTICIPANTS

Top 100 largest academic publishers and top 100 highly ranked scientific journals, regardless of subject, language, or country of origin. Publishers were identified by the total number of journals in their portfolio, and journals were identified through the Scimago journal rank using the Hirsch index (H index) as an indicator of journal productivity and impact.

MAIN OUTCOME MEASURES

The primary outcomes were the content of GAI guidelines listed on the websites of the top 100 academic publishers and scientific journals, and the consistency of guidance between the publishers and their affiliated journals.

RESULTS

Among the top 100 largest publishers, 24% provided guidance on the use of GAI, of which 15 (63%) were among the top 25 publishers. Among the top 100 highly ranked journals, 87% provided guidance on GAI. Of the publishers and journals with guidelines, the inclusion of GAI as an author was prohibited in 96% and 98%, respectively. Only one journal (1%) explicitly prohibited the use of GAI in the generation of a manuscript, and two (8%) publishers and 19 (22%) journals indicated that their guidelines exclusively applied to the writing process. When disclosing the use of GAI, 75% of publishers and 43% of journals included specific disclosure criteria. Where to disclose the use of GAI varied, including in the methods or acknowledgments, in the cover letter, or in a new section. Variability was also found in how to access GAI guidelines shared between journals and publishers. GAI guidelines in 12 journals directly conflicted with those developed by the publishers. The guidelines developed by top medical journals were broadly similar to those of academic journals.

CONCLUSIONS

Guidelines by some top publishers and journals on the use of GAI by authors are lacking. Among those that provided guidelines, the allowable uses of GAI and how it should be disclosed varied substantially, with this heterogeneity persisting in some instances among affiliated publishers and journals. Lack of standardization places a burden on authors and could limit the effectiveness of the regulations. As GAI continues to grow in popularity, standardized guidelines to protect the integrity of scientific output are needed.

New evidence-based practice: Artificial intelligence as a barrier breaker

The concept of evidence-based practice has persisted over several years and remains a cornerstone in clinical practice, representing the gold standard for optimal patient care. However, despite widespread recognition of its significance, practical application faces various challenges and barriers, including a lack of skills in interpreting studies, limited resources, time constraints, linguistic competencies, and more. Recently, we have witnessed the emergence of a groundbreaking technological revolution known as artificial intelligence. Although artificial intelligence has become increasingly integrated into our daily lives, some reluctance persists among certain segments of the public. This article explores the potential of artificial intelligence as a solution to some of the main barriers encountered in the application of evidence-based practice. It highlights how artificial intelligence can assist in staying updated with the latest evidence, enhancing clinical decision-making, addressing patient misinformation, and mitigating time constraints in clinical practice. The integration of artificial intelligence into evidence-based practice has the potential to revolutionize healthcare, leading to more precise diagnoses, personalized treatment plans, and improved doctor-patient interactions. This proposed synergy between evidence-based practice and artificial intelligence may necessitate adjustments to its core concept, heralding a new era in healthcare.

AI interprets the Central Dogma and Genetic Code

Generative artificial intelligence (AI) is a burgeoning field with widespread applications, including in science. Here, we explore two paradigms that provide insight into the capabilities and limitations of Chat Generative Pre-trained Transformer (ChatGPT): its ability to (i) define a core biological concept (the Central Dogma of molecular biology); and (ii) interpret the genetic code.

Exploring the role of ChatGPT in patient care (diagnosis and treatment) and medical research: A systematic review

BACKGROUND

ChatGPT is an artificial intelligence based tool developed by OpenAI (California, USA). This systematic review examines the potential of ChatGPT in patient care and its role in medical research.

METHODS

The systematic review was done according to the PRISMA guidelines. Embase, Scopus, PubMed and Google Scholar data bases were searched. We also searched preprint data bases. Our search was aimed to identify all kinds of publications, without any restrictions, on ChatGPT and its application in medical research, medical publishing and patient care. We used search term "ChatGPT". We reviewed all kinds of publications including original articles, reviews, editorial/ commentaries, and even letter to the editor. Each selected records were analysed using ChatGPT and responses generated were compiled in a table. The word table was transformed in to a PDF and was further analysed using ChatPDF.

RESULTS

We reviewed full texts of 118 articles. ChatGPT can assist with patient enquiries, note writing, decision-making, trial enrolment, data management, decision support, research support, and patient education. But the solutions it offers are usually insufficient and contradictory, raising questions about their originality, privacy, correctness, bias, and legality. Due to its lack of human-like qualities, ChatGPT's legitimacy as an author is questioned when used for academic writing. ChatGPT generated contents have concerns with bias and possible plagiarism.

CONCLUSION

Although it can help with patient treatment and research, there are issues with accuracy, authorship, and bias. ChatGPT can serve as a "clinical assistant" and be a help in research and scholarly writing.

Universal skepticism of ChatGPT: a review of early literature on chat generative pre-trained transformer

ChatGPT, a new language model developed by OpenAI, has garnered significant attention in various fields since its release. This literature review provides an overview of early ChatGPT literature across multiple disciplines, exploring its applications, limitations, and ethical considerations. The review encompasses Scopus-indexed publications from November 2022 to April 2023 and includes 156 articles related to ChatGPT. The findings reveal a predominance of negative sentiment across disciplines, though subject-specific attitudes must be considered. The review highlights the implications of ChatGPT in many fields including healthcare, raising concerns about employment opportunities and ethical considerations. While ChatGPT holds promise for improved communication, further research is needed to address its capabilities and limitations. This literature review provides insights into early research on ChatGPT, informing future investigations and practical applications of chatbot technology, as well as development and usage of generative AI.

Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions

The integration of large language models (LLMs), such as those in the Generative Pre-trained Transformers (GPT) series, into medical education has the potential to transform learning experiences for students and elevate their knowledge, skills, and competence. Drawing on a wealth of professional and academic experience, we propose that LLMs hold promise for revolutionizing medical curriculum development, teaching methodologies, personalized study plans and learning materials, student assessments, and more. However, we also critically examine the challenges that such integration might pose by addressing issues of algorithmic bias, overreliance, plagiarism, misinformation, inequity, privacy, and copyright concerns in medical education. As we navigate the shift from an information-driven educational paradigm to an artificial intelligence (AI)-driven educational paradigm, we argue that it is paramount to understand both the potential and the pitfalls of LLMs in medical education. This paper thus offers our perspective on the opportunities and challenges of using LLMs in this context. We believe that the insights gleaned from this analysis will serve as a foundation for future recommendations and best practices in the field, fostering the responsible and effective use of AI technologies in medical education.

Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions (Preprint).. [DOI: 10.2196/preprints.48291] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

UNSTRUCTURED

The integration of large language models (LLMs), such as those in the Generative Pre-trained Transformers (GPT) series, into medical education has the potential to transform learning experiences for students and elevate their knowledge, skills, and competence. Drawing on a wealth of professional and academic experience, we propose that LLMs hold promise for revolutionizing medical curriculum development, teaching methodologies, personalized study plans and learning materials, student assessments, and more. However, we also critically examine the challenges that such integration might pose by addressing issues of algorithmic bias, overreliance, plagiarism, misinformation, inequity, privacy, and copyright concerns in medical education. As we navigate the shift from an information-driven educational paradigm to an artificial intelligence (AI)–driven educational paradigm, we argue that it is paramount to understand both the potential and the pitfalls of LLMs in medical education. This paper thus offers our perspective on the opportunities and challenges of using LLMs in this context. We believe that the insights gleaned from this analysis will serve as a foundation for future recommendations and best practices in the field, fostering the responsible and effective use of AI technologies in medical education.