Readership Awareness Series – Paper 3: Paper Mills

Self Cite

Purpose: This study aimed to report the performance of the large language model ChatGPT (OpenAI, San Francisco, CA, U.S.A.) in the context of lacrimal drainage disorders. Methods: A set of prompts was constructed through questions and statements spanning common and uncommon aspects of lacrimal drainage disorders. Care was taken to avoid constructing prompts that had significant or new knowledge beyond the year 2020. Each of the prompts was presented thrice to ChatGPT. The questions covered common disorders such as primary acquired nasolacrimal duct obstruction and congenital nasolacrimal duct obstruction and their cause and management. The prompts also tested ChatGPT on certain specifics, such as the history of dacryocystorhinostomy (DCR) surgery, lacrimal pump anatomy, and human canalicular surfactants. ChatGPT was also quizzed on controversial topics such as silicone intubation and the use of mitomycin C in DCR surgery. The responses of ChatGPT were carefully analyzed for evidence-based content, specificity of the response, presence of generic text, disclaimers, factual inaccuracies, and its abilities to admit mistakes and challenge incorrect premises. Three lacrimal surgeons graded the responses into three categories: correct, partially correct, and factually incorrect. Results: A total of 21 prompts were presented to the ChatGPT. The responses were detailed and were based according to the prompt structure. In response to most questions, ChatGPT provided a generic disclaimer that it could not give medical advice or professional opinion but then provided an answer to the question in detail. Specific prompts such as “how can I perform an external DCR?” were responded by a sequential listing of all the surgical steps. However, several factual inaccuracies were noted across many ChatGPT replies. Several responses on controversial topics such as silicone intubation and mitomycin C were generic and not precisely evidence-based. ChatGPT’s response to specific questions such as canalicular surfactants and idiopathic canalicular inflammatory disease was poor. The presentation of variable prompts on a single topic led to responses with either repetition or recycling of the phrases. Citations were uniformly missing across all responses. Agreement among the three observers was high (95%) in grading the responses. The responses of ChatGPT were graded as correct for only 40% of the prompts, partially correct in 35%, and outright factually incorrect in 25%. Hence, some degree of factual inaccuracy was present in 60% of the responses, if we consider the partially correct responses. The exciting aspect was that ChatGPT was able to admit mistakes and correct them when presented with counterarguments. It was also capable of challenging incorrect prompts and premises. Conclusion: The performance of ChatGPT in the context of lacrimal drainage disorders, at best, can be termed average. However, the potential of this AI chatbot to infl...

Section: Table 4 Chatgpt and Ct-dacryocystographymentioning

confidence: 99%

“…The scientific community was jolted when the abilities of ChatGPT to construct manuscripts came to light. 1 Several articles also mentioned ChatGPT as a coauthor. 2 , 3 While efforts have been made to correct it, it also led to a larger question—Can ChatGPT be given authorship?…”

mentioning

confidence: 99%

ChatGPT and Lacrimal Drainage Disorders: Performance and Scope of Improvement

Ali¹

2023

Self Cite

“…Naturally, serious factual inaccuracies should be a matter of concern. 1–4 However, the ability of ChatGPT or similar large language model AI chatbots to correct their responses when confronted with factual inaccuracies is inspiring. There is a need to train the chatbots to meet the specific requirements of individual specialties.…”

Section: To the Editormentioning

confidence: 99%

“…The medical community needs to understand that it will take some time for ChatGPT to be useful in routine medical practice, and while the concerns about their misuse remain, their potential to be helpful with several aspects of clinical and academic work cannot be discounted. 1–4…”

Section: To the Editormentioning

confidence: 99%

Reply Re: “ChatGPT and Lacrimal Drainage Disorders: Performance and Scope of Improvement”

Ali¹

2023

There are many potential applications for AI in clinical research. Other problems, though, also need to be addressed. Accuracy and dependability's significance have already been mentioned. Research is being done on AI's capacity to predict how clinical difficulties will turn out. It ought to be clear that using it has some drawbacks. AI shouldn't create, analyze, or approve vital information without human review. 2 Usage management techniques that are ineffective may lead to abuse. It could be used, for instance, to automatically find plagiarism and ghostwriting. Everyone agrees that AI need a more secure base. Everyone agrees that AI need a more secure base. We can all agree that for AI to function properly, a cutting-edge strategy is required.

“…This author has addressed these issues in detail in their other papers on ChatGPT and will briefly discuss them here. 1–4…”

Section: To the Editormentioning

confidence: 99%

Reply Re: “ChatGPT and Lacrimal Drainage Disorders: Performance and Scope of Improvement”

Ali¹

2023

increase the ocular surface exposure and worsen the inflammation. The included patients in our series had severe cicatricial entropion with limbal stem cell deficiency and persistent dryness with an increased risk of ocular inflammation. Hence, caution should be exercised in chronic cicatrizing conjunctivitis eyes for procedures like blepharoplasty or supratrasal fixation and instead use mucous membrane grafting (MMG) over the bare tarsus to prevent the downward sliding of tissues.Ghahvehchian et al. further state that supratarsal fixation, upper blepharoplasty, or both should be combined with ALR surgery to avoid long-term downward sliding of skin orbicularis. We added MMG for the same reason to act as a barrier between the eyelash line and posterior eyelid margin, as we encountered high failure rates with ALR alone, or with blepharoplasty. However, as we have not touched the levator muscle, the levator (once the anesthesia effect wanes off) can also pull the posterior lamella upwards and might reduce the gap between the eyelash line and eyelid margin. We cannot comment upon the superiority of either technique in severe cicatricial entropion; however, comparison of the outcomes of these two techniques in similar patient severity may require a multicentric trial. Besides, due to multiple associated comorbidities, it would be inappropriate to subject patients with chronic cicatrizing conjunctivitis to trials of ALR with and without MMG.