Beyond the Keyboard: Academic Writing in the Era of ChatGPT

Doskaliuk, Bohdana; Zimba, Olena

doi:10.3346/jkms.2023.38.e207

Cited by 13 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Datasets used for training LLMs are normally not domain-specific and lack reliability since unverified internet sources are included. 29 30 31 This could lead LLMs to generate inaccurate information in medical domain of specific matters. 29 32 To address this issue, LLMs can be fine-tuned with medical data.…”

Section: Discussionmentioning

confidence: 99%

Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation

Kim,

Jin,

Jung

et al. 2024

J Korean Med Sci

View full text Add to dashboard Cite

Background Although discharge summaries in patient-friendly language can enhance patient comprehension and satisfaction, they can also increase medical staff workload. Using a large language model, we developed and validated software that generates a patient-friendly discharge summary. Methods We developed and tested the software using 100 discharge summary documents, 50 for patients with myocardial infarction and 50 for patients treated in the Department of General Surgery. For each document, three new summaries were generated using three different prompting methods (Zero-shot, One-shot, and Few-shot) and graded using a 5-point Likert Scale regarding factuality, comprehensiveness, usability, ease, and fluency. We compared the effects of different prompting methods and assessed the relationship between input length and output quality. Results The mean overall scores differed across prompting methods (4.19 ± 0.36 in Few-shot, 4.11 ± 0.36 in One-shot, and 3.73 ± 0.44 in Zero-shot; P < 0.001). Post-hoc analysis indicated that the scores were higher with Few-shot and One-shot prompts than in zero-shot prompts, whereas there was no significant difference between Few-shot and One-shot prompts. The overall proportion of outputs that scored ≥ 4 was 77.0% (95% confidence interval: 68.8–85.3%), 70.0% (95% confidence interval [CI], 61.0–79.0%), and 32.0% (95% CI, 22.9–41.1%) with Few-shot, One-shot, and Zero-shot prompts, respectively. The mean factuality score was 4.19 ± 0.60 with Few-shot, 4.20 ± 0.55 with One-shot, and 3.82 ± 0.57 with Zero-shot prompts. Input length and the overall score showed negative correlations in the Zero-shot ( r = −0.437, P < 0.001) and One-shot ( r = −0.327, P < 0.001) tests but not in the Few-shot ( r = −0.050, P = 0.625) tests. Conclusion Large-language models utilizing Few-shot prompts generally produce acceptable discharge summaries without significant misinformation. Our research highlights the potential of such models in creating patient-friendly discharge summaries for Korean patients to support patient-centered care.

show abstract

Section: Discussionmentioning

confidence: 99%

Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation

Kim,

Jin,

Jung

et al. 2024

J Korean Med Sci

View full text Add to dashboard Cite

show abstract

“…14,21,22 There is currently no clear consensus whether AI-detecting programs commonly used by journal publishers can reliably detect texts prepared by ChatGPT. [23][24][25][26] Because of the ease of use, manuscripts prepared with this chatbot are already appearing in the literature, 27 raising the question of whether chatbots such as ChatGPT can be authors of scientific papers. Statements have been issued by journals such as Nature and Science, 28,29 and are surrounded by active ethical debates and the increasing need for innovation and federation of knowledge-all of which also need to be addressed by the laboratory medicine community.…”

Section: Manuscript Productionmentioning

confidence: 99%

“…For this reason, AI-assisted scientific writing or proofing may democratize the scientific literature and facilitate the production of manuscripts from non-native speakers in high-quality idiomatic English that is appropriate for a scientific publication. 14,24 This might range from situations that are ethically unambiguous and would be essentially indistinguishable from using spelling/grammar checkers in word processing programs to more problematic situations where AI assistance might alter the context or content substantially, thereby creating factually wrong or nonsensical scientific text. 14 Chatbots could also do the work of expert librarians, who routinely assist in data synthesis and systematic reviews, and could be an additional advantage to researchers working under limited circumstances.…”

Section: Manuscript Productionmentioning

confidence: 99%

“…There is currently no clear consensus whether AI‐detecting programs commonly used by journal publishers can reliably detect texts prepared by ChatGPT 23–26 . Because of the ease of use, manuscripts prepared with this chatbot are already appearing in the literature, 27 raising the question of whether chatbots such as ChatGPT can be authors of scientific papers.…”

Section: Advantages Referencesmentioning

confidence: 99%

“…Although for‐profit companies have exploited this niche and market their editing services to authors, researchers practicing in resource‐limited environments may be unable to access good‐quality English language editing. For this reason, AI‐assisted scientific writing or proofing may democratize the scientific literature and facilitate the production of manuscripts from non‐native speakers in high‐quality idiomatic English that is appropriate for a scientific publication 14,24 . This might range from situations that are ethically unambiguous and would be essentially indistinguishable from using spelling/grammar checkers in word processing programs to more problematic situations where AI assistance might alter the context or content substantially, thereby creating factually wrong or nonsensical scientific text 14 .…”

Section: Advantages Referencesmentioning

confidence: 99%

See 2 more Smart Citations

Responsible use of chatbots to advance the laboratory hematology scientific literature: Challenges and opportunities

Lucas,

Mackie,

d'Onofrio

et al. 2024

Int J Lab Hematology

View full text Add to dashboard Cite

Large language models (LLMs) are artificial neural networks, a particular type of artificial intelligence (AI), trained to recognize complex patterns in natural language or text to generate written content similar to what a human would produce. 1 Chatbots are specific LLM-based applications or interfaces designed to simulate human conversation, generating prompt responses to a variety of inquiries. Chatbots are now offered by several developers, but often differ in data set processing, architecture, training, number of parameters, cost, licensing, and ease of availability, among others. 1 Chat Generative Pre-trained

show abstract

The emerging paradigm in pediatric rheumatology: harnessing the power of artificial intelligence

Koker,

Sahin,

Yildiz

et al. 2024

Rheumatol Int

View full text Add to dashboard Cite

Artificial intelligence algorithms, with roots extending into the past but experiencing a resurgence and evolution in recent years due to their superiority over traditional methods and contributions to human capabilities, have begun to make their presence felt in the field of pediatric rheumatology. In the ever-evolving realm of pediatric rheumatology, there have been incremental advancements supported by artificial intelligence in understanding and stratifying diseases, developing biomarkers, refining visual analyses, and facilitating individualized treatment approaches. However, like in many other domains, these strides have yet to gain clinical applicability and validation, and ethical issues remain unresolved. Furthermore, mastering different and novel terminologies appears challenging for clinicians. This review aims to provide a comprehensive overview of the current literature, categorizing algorithms and their applications, thus offering a fresh perspective on the nascent relationship between pediatric rheumatology and artificial intelligence, highlighting both its advancements and constraints.

show abstract

Beyond the Keyboard: Academic Writing in the Era of ChatGPT

Cited by 13 publications

References 12 publications

Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation

Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation

Responsible use of chatbots to advance the laboratory hematology scientific literature: Challenges and opportunities

The emerging paradigm in pediatric rheumatology: harnessing the power of artificial intelligence

Contact Info

Product

Resources

About