Generative Pre-training Research Articles

Optimizing Readability of Patient-Facing Hand Surgery Education Materials Using Chat Generative Pretrained Transformer 3.5

To address patient health literacy, the American Medical Association and the National Institutes of Health recommend that readability of patient education materials should not exceed an eighth grade reading level. However, patient-facing materials often remain above the recommended average reading level. Current online calculators provide readability scores; however, they lack the ability to provide text-specific feedback, which may streamline the process of simplifying patient materials. The purpose of this study was to evaluate Chat Generative Pretrained Transformer (ChatGPT) 3.5 as a tool for optimizing patient-facing hand surgery education materials through reading level analysis and simplification. The readability of 18 patient-facing hand surgery education materials was compared by a traditional online calculator for reading level and ChatGPT 3.5. The original excerpts were then entered into ChatGPT 3.5 and simplified by the artificial intelligence tool. The simplified excerpts were scored by the same calculators. The readability scores for the original excerpts from the online calculator and ChatGPT 3.5 were similar. The simplified excerpts' scores were lower than the originals, with a mean of 7.28, less than the maximum recommended8. The use of ChatGPT 3.5 for the purpose of simplification and readability analysis of patient-facing hand surgery materials is efficient and may help facilitate the conveyance of important health information. ChatGPT 3.5 rendered readability scores comparable with traditional readability calculators, in addition to excerpt-specific feedback. It was also able to simplify materials to the recommended grade levels. By confirming ChatGPT3.5's ability to assess and simplify patient education materials, this study offers a practical solution for potentially improving patient comprehension, engagement, and health outcomes in clinical settings.

Artificial Intelligence-Powered Hand Surgery Consultation: GPT-4 as an Assistant in a Hand Surgery Outpatient Clinic

Exploring the integration of artificial intelligence in clinical settings, this study examined the feasibility of using Generative Pretrained Transformer 4 (GPT-4), a large language model, as a consultation assistant in a hand surgery outpatient clinic. The study involved 10 simulated patient scenarios with common hand conditions, where GPT-4, enhanced through specific prompt engineering techniques, conducted medical history interviews, and assisted in diagnostic processes. A panel of expert hand surgeons, each board-certified in hand surgery, evaluated GPT-4's responses using a Likert Scale across five criteria with scores ranging from 1 (lowest) to 5 (highest). Generative Pretrained Transformer 4 achieved an average score of 4.6, reflecting good performance in documenting a medical history, as evaluated by the hand surgeons. These findings suggest that GPT-4 can effectively document medical histories to meet the standards of hand surgeons in a simulated environment. The findings indicate potential for future application in patient care, but the actual performance of GPT-4 in real clinical settings remains to be investigated. This study provides a preliminary indication that GPT-4 could be a useful consultation assistant in a hand surgery outpatient clinic, but further research is required to explore its reliability and practicality in actual practice.

Assessing the Accuracy, Completeness, and Reliability of Artificial Intelligence-Generated Responses in Dentistry: A Pilot Study Evaluating the ChatGPT Model.

Artificial intelligence (AI) can be a tool in the diagnosis and acquisition of knowledge, particularly in dentistry, sparking debates on its application in clinical decision-making. This study aims to evaluate the accuracy, completeness, and reliability of the responses generated by Chatbot Generative Pre-Trained Transformer (ChatGPT) 3.5 in dentistry using expert-formulated questions. Experts were invited to create three questions, answers, and respective references according to specialized fields of activity. The Likert scale was used to evaluate agreement levels between experts and ChatGPT responses. Statistical analysis compared descriptive and binary question groups in terms of accuracy and completeness. Questions with low accuracy underwent re-evaluation, and subsequent responses were compared for improvement. The Wilcoxon test was utilized (α = 0.05). Ten experts across six dental specialties generated 30 binary and descriptive dental questions and references. The accuracy score had a median of 5.50 and a mean of 4.17. For completeness, the median was 2.00 and the mean was 2.07. No difference was observed between descriptive and binary responses for accuracy and completeness. However, re-evaluated responses showed a significant improvement with a significant difference in accuracy (median 5.50 vs. 6.00; mean 4.17 vs. 4.80; p=0.042) and completeness (median 2.0 vs. 2.0; mean 2.07 vs. 2.30; p=0.011). References were more incorrect than correct, with no differences between descriptive and binary questions. ChatGPT initially demonstrated good accuracy and completeness, which was further improved with machine learning (ML) over time. However, some inaccurate answers and references persisted. Human critical discernment continues to be essential to facing complex clinical cases and advancing theoretical knowledge and evidence-based practice.

Evaluating the performance of ChatGPT-3.5 and ChatGPT-4 on the Taiwan plastic surgery board examination

BackgroundChat Generative Pre-Trained Transformer (ChatGPT) is a state-of-the-art large language model that has been evaluated across various medical fields, with mixed performance on licensing examinations. This study aimed to assess the performance of ChatGPT-3.5 and ChatGPT-4 in answering questions from the Taiwan Plastic Surgery Board Examination. MethodsThe study evaluated the performance of ChatGPT-3.5 and ChatGPT-4 on 1375 questions from the past 8 years of the Taiwan Plastic Surgery Board Examination, including 985 single-choice and 390 multiple-choice questions. We obtained the responses between June and July 2023, launching a new chat session for each question to eliminate memory retention bias. ResultsOverall, ChatGPT-4 outperformed ChatGPT-3.5, achieving a 59 % correct answer rate compared to 41 % for ChatGPT-3.5. ChatGPT-4 passed five out of eight yearly exams, whereas ChatGPT-3.5 failed all. On single-choice questions, ChatGPT-4 scored 66 % correct, compared to 48 % for ChatGPT-3.5. On multiple-choice, ChatGPT-4 achieved a 43 % correct rate, nearly double the 23 % of ChatGPT-3.5. ConclusionAs ChatGPT evolves, its performance on the Taiwan Plastic Surgery Board Examination is expected to improve further. The study suggests potential reforms, such as incorporating more problem-based scenarios, leveraging ChatGPT to refine exam questions, and integrating AI-assisted learning into candidate preparation. These advancements could enhance the assessment of candidates' critical thinking and problem-solving abilities in the field of plastic surgery.

GPT Chat: Useful or Not in Supporting Learning in Higher Education

Background. Chat GPT is a natural language model developed by OpenAI, based on the GPT (Generative Pretrained Transformer) architecture. It is renowned for its ability to generate text that closely resembles human writing, including in chat and conversational interactions. In the growing digital era, artificial intelligence technology is increasingly playing an important role in various fields, including education. Purpose. This study aims to identify the benefits of using Chat GPT in learning in higher education and how its use can improve the quality of learning, accelerate the assessment process, increase student engagement, improve teaching efficiency, and facilitate student understanding. Method. The research method used is quantitative by using google form which will produce data in the form of numbers. By using google form, a questionnaire will be made and distributed to students in higher education. Results. The results show that the use of Chat GPT has significant benefits in learning in higher education. The use of Chat GPT can improve the quality of learning, accelerate the assessment process, increase student engagement, and improve teaching efficiency. Conclusion. The conclusion from this study is that the use of Chat GPT in a college setting can be beneficial in supporting learning in an innovative and effective way. However, the limitation of this study is that the researcher was only able to conduct a study of a few students in higher education. Therefore, the researcher hopes that future research can be conducted with a wider scope. The researcher also recommends that future research can be a reference material in conducting research related to the utilisation of Chat GPT in supporting learning in higher education.

ChatGPT in Education: Applications, Concerns and Recommendations

Chat Generative Pretrained Transformer (chatGPT) is a language model that enables users to engage in natural language conversations with the system through text. The model is available through an easy-to-use, free web interface with impressive capabilities, which has contributed to its rapid popularity among students. This significant interest of students in utilizing chatGPT underscores the need to understand its impact on education. This paper presents applications, concerns, and recommendations on the use of chatGPT in education. The reviewed articles highlight several educational applications, including assisting students with writing tasks and helping teachers create learning materials. However, concerns have been raised about its unregulated use among students, particularly issues related to academic integrity, privacy violations, and potential biases. Regardless, many researchers advocate for the integration of chatGPT into the education system. Some do have reservations and recommend measures, including learning goals adjustments and development of new assessment forms to embrace ChatGPT in learning. While there is a great potential of chatGPT use in education, further research is needed to fully understand its implications when used without appropriate guidance and its long-term effects on students.

Revolutionising Translation Technology: A Comparative Study of Variant Transformer Models - BERT, GPT, and T5

Recently, transformer-based models have reshaped the landscape of Natural Language Processing (NLP), particularly in the domain of Machine Translation (MT). this study explores three revolutionary transformer models: Bidirectional Encoder Representations from Transformers (BERT), Generative Pretrained Transformer (GPT), and Text-to-Text Transfer Transformer (T5). The study delves into their architecture, capabilities, and applications in the context of translation technology. The study begins by discussing the evolution of machine translation from rule-based to statistical machine translation and finally to transformer models. The models have distinct architectures and purposes which pushed the limits of MT and have been instrumental in revolutionising the field. The study found significant contributions of the models in the advancement of NLP tasks including translation technology. Using comparative approach, the study further elaborates on each model’s design and utility. BERT is strong in excelling in tasks requiring a deep understanding of the context. GPT is excellent for tasks such as text generation, translation and creative writing. While the strengths of T5 is text-to-text framework by simplifying the taskspecific architectures, making it easy to perform different NLP tasks. Recognising these models’ unique features allows translators to select the best one for particular translation tasks and adjust them for better accuracy, fluency, and cultural relevance in translations. The study concludes that the models bridge language barriers, improve cross-cultural communication and pave way for more accurate and natural translations in the future. The study also points out that language processing models are continually evolving but understanding BERT, GPT, and T5’s specific features is key for ongoing development in translation technology.

DETERMINING THE EFFECTIVENESS OF USING CHATGPT-4 IN ORGANISING EXCURSIONS

As artificial intelligence (AI) technology becomes more deeply embedded in people's daily lives and work, the importance of ChatGPT (Generative Pretrained Transformer) is growing and its application in the tourism sector is expanding. ChatGPT can be useful in organising new excursions because of its capabilities such as data analysis, interpretation, scenario creation and model evaluation. Therefore, the purpose of this study was to determine the effectiveness of using ChatGPT-4 in organising new excursions. The study was conducted at the Abai Kazakh National Pedagogical University and 82 students participated in the study. The study consisted of two stages, at the first stage students answered a questionnaire on the discipline of "Literary excursion", which was studied for 15 weeks, and at the second stage was conducted a study based on comparative analysis, with the assignment of 6 specially prepared questions to determine the effectiveness of using ChatGPT-4. As a result of the study, the need to study the excursion subject for students of educational programmes "Kazakh language and literature" was 72%. ChatGPT-4 became an indispensable tool in drawing up excursion itineraries for students, making their technological map and selecting an excursion object. In addition, with the help of ChatGPT-4 students built routes of new excursions and correctly identified tourist objects and traffic routes, type. Also very qualitatively wrote the text of the excursion in lit erary language and brought it to the level of an interesting script. Thus, using ChatGPT-4 when organising new excursions will help you to get information, save time, make specific decisions and improve quality. The results of this study may be useful in th e future to explore ChatGPT-4 in the potential integration of other technologies such as augmented reality or virtual reality.

AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design.

Large language models (LLMs) such as generative pretrained transformers (GPTs) have shown potential for various commercial applications, but their applicability for materials design remains underexplored. In this Letter, AtomGPT is introduced as a model specifically developed for materials design based on transformer architectures, demonstrating capabilities for both atomistic property prediction and structure generation. This study shows that a combination of chemical and structural text descriptions can efficiently predict material properties with accuracy comparable to graph neural network models, including formation energies, electronic bandgaps from two different methods, and superconducting transition temperatures. Furthermore, AtomGPT can generate atomic structures for tasks such as designing new superconductors, with the predictions validated through density functional theory calculations. This work paves the way for leveraging LLMs in forward and inverse materials design, offering an efficient approach to the discovery and optimization of materials.

Assessing Generative Pretrained Transformers (GPT) in Clinical Decision-Making: Comparative Analysis of GPT-3.5 and GPT-4.

Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement. This study aims to analyze the performance of ChatGPT-3.5 and ChatGPT-4 in addressing complex clinical and ethical dilemmas, and to illustrate their potential role in health care decision-making while comparing seniors' and residents' ratings, and specific question types. A total of 4 specialized physicians formulated 176 real-world clinical questions. A total of 8 senior physicians and residents assessed responses from GPT-3.5 and GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, and comprehensiveness. Evaluations were conducted within internal medicine, emergency medicine, and ethics. Comparisons were made globally, between seniors and residents, and across classifications. Both GPT models received high mean scores (4.4, SD 0.8 for GPT-4 and 4.1, SD 1.0 for GPT-3.5). GPT-4 outperformed GPT-3.5 across all rating dimensions, with seniors consistently rating responses higher than residents for both models. Specifically, seniors rated GPT-4 as more beneficial and complete (mean 4.6 vs 4.0 and 4.6 vs 4.1, respectively; P<.001), and GPT-3.5 similarly (mean 4.1 vs 3.7 and 3.9 vs 3.5, respectively; P<.001). Ethical queries received the highest ratings for both models, with mean scores reflecting consistency across accuracy and completeness criteria. Distinctions among question types were significant, particularly for the GPT-4 mean scores in completeness across emergency, internal, and ethical questions (4.2, SD 1.0; 4.3, SD 0.8; and 4.5, SD 0.7, respectively; P<.001), and for GPT-3.5's accuracy, beneficial, and completeness dimensions. ChatGPT's potential to assist physicians with medical issues is promising, with prospects to enhance diagnostics, treatments, and ethics. While integration into clinical workflows may be valuable, it must complement, not replace, human expertise. Continued research is essential to ensure safe and effective implementation in clinical environments.

Artificial Intelligence as a Consent Aid for Carpal Tunnel Release.

Background Hand surgeons have been charged with the use of diverse modalities to enhance the consenting process following the Montgomery ruling. Artificial Intelligence language models have been suggested as patient education tools that may aid consent. Methods We compared the quality and readability of the Every Informed Decision Online (EIDO) patient information leaflet for carpal tunnel release with the artificial intelligence language model Chat Generative Pretrained Transformer (GPT). Results The quality of information by ChatGPT was significantly higher using the DISCERN score, 71/80 for ChatGPT compared to 62/80 for EIDO (p=0.014). DISCERN interrater observer reliability was high (0.65) using the kappa statistic. Flesch-Kincaid readability scoring was 12.3 for ChatGPT and 7.5 for EIDO, suggesting a more complex reading age for the ChatGPT information. Conclusion The artificial intelligence language model ChatGPT produces high-quality information at the expense of readability when compared to EIDO information leaflets for carpal tunnel release consent.

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

PurposeTo examine the ability of generative artificial intelligence (GAI) to answer patients’ questions regarding colorectal cancer (CRC).MethodsTen 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).ResultsIn 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).ConclusionThe 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.

The Potential of GPT in Education: Opportunities for Students’ Feedback

The objective of this study is to investigate the capacity of GPT (Generative Pre-trained Transformer) in delivering feedback to students. The research methodology employed was bibliographic research, involving the gathering of data from various sources such as books, articles, and academic documents. The findings uncover various crucial prospects for employing GPT in providing feedback to students. Firstly, GPT has the ability to automate the generation of feedback, providing consistent and immediate responses. Additionally, it facilitates personalised learning by customising feedback to meet the specific needs of each student, enabling multiple instances of personalised learning reinforcement. In addition, GPT offers language assistance, aiding students in overcoming linguistic obstacles. It improves the process of creating content by aiding in the development of educational materials and assignments. Another notable benefit is its round-the-clock availability, guaranteeing that students can receive feedback at any hour, thereby enhancing their learning experience. Finally, GPT can be incorporated into cutting-edge educational applications, promoting a more interactive and captivating learning environment. In summary, GPT's ability to produce automated, tailored, and easily accessible feedback demonstrates its potential to greatly enhance educational methods and student achievements.

RELATIONAL DIMENSION VERSUS ARTIFICIAL INTELLIGENCE.

Thirty years ago, we proposed the similarity between the functioning of artificial intelligence and the human psyche, suggesting multiple parallels between the Freudian model proposed in the "Project for Psychology for Neurologists" and the connectionist theories applied in the generation of parallel distributed processing systems (PDP), also known as connectionist models. These models have been and continue to be the foundation of general artificial intelligences like ChatGPT, evolving and gaining prominence in everyday life. From the earliest applications in psychiatry, recreating computationally simulated modes of illnesses, to the use of deep learning models, especially in the field of computer vision for tasks such as image recognition, segmentation, and classification. Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) are employed for tasks involving sequences of data, such as natural language processing, or models based on the Transformer architecture, like BERT and GPT (Generative Pre-trained Transformer), which have revolutionized natural language processing. In this present work, we analyze the significance of the emergence and exponential growth of these types of tools in the field of healthcare, from medical diagnosis and patient care to psychological attention and psychotherapeutic treatment, exploring the changes and transformations in the forms of subjective expression that are arising. We also examine and argue for the importance and validity of the relational dimension proposed by our psychoanalytic approach in contrast to the potential use of these tools as treatment models.

ChatGPT can yield valuable responses in the context of orthopaedic trauma surgery.

To assess the possibility of using Generative Pretrained Transformer (ChatGPT) specifically in the context of orthopaedic trauma surgery by questions posed to ChatGPT and to evaluate responses (correctness, completenessand adaptiveness) by orthopaedic trauma surgeons. ChatGPT (GPT-4 of 12 May 2023) was asked to address 34 common orthopaedic trauma surgery-related questions and generate responses suited to three target groups: patient, nonorthopaedic medical doctorand expert orthopaedic surgeon. Three orthopaedic trauma surgeons independently assessed ChatGPT's responses by using a three-point response scale with a response range between 0 and 2, where a higher number indicates better performance (correctness, completenessand adaptiveness). A total of 18 (52.9%) of all responses were assessed to be correct (2.0) for the patient target group, while 22 (64.7%) and 24 (70.5%) of the responses were determined to be correct for nonorthopaedic medical doctors and expert orthopaedic surgeons, respectively. Moreover, a total of 18 (52.9%), 25 (73.5%)and 28 (82.4%) of the responses were assessed to be complete (2.0) for patients, nonorthopaedic medical doctorsand expert orthopaedic surgeons, respectively. The average adaptiveness was 1.93, 1.95and 1.97 for patients, nonorthopaedic medical doctors and expert orthopaedic surgeons, respectively. The study results indicate that ChatGPT can yield valuable and overall correct responses in the context of orthopaedic trauma surgery across different target groups, which encompassed patients, nonorthopaedic medical surgeonsand expert orthopaedic surgeons. The average correctness scores, completeness levelsand adaptiveness values indicated the ability of ChatGPT to generate overall correct and complete responses adapted to the target group. Not applicable.

RAG based Chatbot using LLMs

Historically, Artificial Intelligence (AI) was used to understand and recommend information. Now, Generative AI can also help us create new content. Generative AI builds on existing technologies, like Large Language Models (LLMs) which are trained on large amounts of text and learn to predict the next word in a sentence. Generative AI can not only create new text, but also images, videos, or audio. This project focuses on the implementation of a chatbot based the concepts of Generative AI and Large Language Models which can answer any query regarding the content provided in the PDFs. The primary technologies utilized include Python libraries like LangChain, PyTorch for model training, and Hugging Face’s Transformers library for accessing pre-trained models like Llama2, GPT- 3.5 (Generative Pre-trained Transformer) architectures. The re- sponses are generated using the Retrieval Augmented Generation (RAG) approach. The project aims to develop a chatbot which can generate the sensible responses from the data in the form of PDF files. The project demonstrates the capabilities and applications of advanced Natural Language Processing (NLP) techniques in creating conversational agents that can be deployed across various platforms in the corporation, to enhance user interaction and support automated tasks. Index Terms—Generative AI, Artificial Intelligence, Natural Language Processing, Large Language Model, Llama2, Tran- formers, Document Loaders, Retrieval Augmented Generation, Vector Database, Langchain, Chainlit

Transformative Trends: A Comprehensive Review of Large Language Models (LLMs) in Healthcare

Recent years have witnessed notable progress in Language Model (LM) technology, especially with the introduction of Large Language Models (LLMs). With the use of complex neural networks and enormous volumes of data, these models—like the GPT (Generative Pre-trained Transformer) series—have completely changed the field of natural language processing. This study offers a thorough analysis of LLMs, examining their uses as well as the difficulties and moral issues that come with implementing LLMs in practical settings. Moreover, it investigates the wide range of uses of LLMs in many fields, such as question answering, drug discovery, language translation, and text production. By means of this review, we hope to offer ideas on future directions in this quickly developing field as well as insights into the state-of-the-art in LLM research today. Key Words: Large Language Models, LangChain, Natural language processing, GPT, ChatGPT, AI chatbots, Indirect Prompt Injection

Server-side rescoring of spoken entity-centric knowledge queries for virtual assistants

On-device virtual assistants (VAs) powered by automatic speech recognition (ASR) require effective knowledge integration for the challenging entity-rich query recognition. In this paper, we conduct an empirical study of modeling strategies for server-side rescoring of spoken information domain queries using various categories of language models (LMs) (N-gram word LMs, sub-word neural LMs). We investigate the combination of on-device and server-side signals, and demonstrate significant word error rate improvements of 23%-35% relative on various entity-centric query subpopulations by integrating various server-side LMs compared to performing ASR on-device only. We also perform a comparison between LMs trained on domain data and a generative pre-trained (GPT) (a variant GPT-3) offered by OpenAI as a baseline. Furthermore, we also show that model fusion of multiple server-side LMs trained from scratch most effectively combines complementary strengths of each model and integrates knowledge learned from domain-specific data to a VA ASR system.

Fine-tuning for accuracy: evaluation of Generative Pretrained Transformer (GPT) for automatic assignment of International Classification of Disease (ICD) codes to clinical documentation

Fine-tuning for accuracy: evaluation of Generative Pretrained Transformer (GPT) for automatic assignment of International Classification of Disease (ICD) codes to clinical documentation

Fitnessgpt Using Artificial Intelligence and Deep Learning

Abstract: This research describes the creation and application of a cutting-edge fitness GPT (Generative Pre-trained Transformer) system that uses deep learning (DL) and artificial intelligence (AI) to provide individualized workout recommendations based on user profiles. The system has important features including strong user authentication, ongoing monitoring of fitness activities, and dynamic engines for suggestion, building on the insights gained from the conversation. The workout GPT system evaluates user data, including physical characteristics, health measurements, and activity levels, using complex AI algorithms to provide individualized workout regimens and dietary suggestions. Modern DL models are used to drive the system's evolution and adaptation in response to user feedback, guaranteeing ongoing relevance and optimization. This study highlights Fitness GPT's revolutionary potential to revolutionize the fitness sector by providing consumers with tailored, datadriven advice to successfully meet their wellness and health objectives.