Generative Pre-trained Transformer Research Articles

Large-scale identification of social and behavioral determinants of health from clinical notes: comparison of Latent Semantic Indexing and Generative Pretrained Transformer (GPT) models

BackgroundSocial and behavioral determinants of health (SBDH) are associated with a variety of health and utilization outcomes, yet these factors are not routinely documented in the structured fields of electronic health records (EHR). The objective of this study was to evaluate different machine learning approaches for detection of SBDH from the unstructured clinical notes in the EHR.MethodsLatent Semantic Indexing (LSI) was applied to 2,083,180 clinical notes corresponding to 46,146 patients in the MIMIC-III dataset. Using LSI, patients were ranked based on conceptual relevance to a set of keywords (lexicons) pertaining to 15 different SBDH categories. For Generative Pretrained Transformer (GPT) models, API requests were made with a Python script to connect to the OpenAI services in Azure, using gpt-3.5-turbo-1106 and gpt-4-1106-preview models. Prediction of SBDH categories were performed using a logistic regression model that included age, gender, race and SBDH ICD-9 codes.ResultsLSI retrieved patients according to 15 SBDH domains, with an overall average PPV ≥\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ge$$\\end{document} 83%. Using manually curated gold standard (GS) sets for nine SBDH categories, the macro-F1 score of LSI (0.74) was better than ICD-9 (0.71) and GPT-3.5 (0.54), but lower than GPT-4 (0.80). Due to document size limitations, only a subset of the GS cases could be processed by GPT-3.5 (55.8%) and GPT-4 (94.2%), compared to LSI (100%). Using common GS subsets for nine different SBDH categories, the macro-F1 of ICD-9 combined with either LSI (mean 0.88, 95% CI 0.82-0.93), GPT-3.5 (0.86, 0.82-0.91) or GPT-4 (0.88, 0.83-0.94) was not significantly different. After including age, gender, race and ICD-9 in a logistic regression model, the AUC for prediction of six out of the nine SBDH categories was higher for LSI compared to GPT-4.0.ConclusionsThese results demonstrate that the LSI approach performs comparable to more recent large language models, such as GPT-3.5 and GPT-4.0, when using the same set of documents. Importantly, LSI is robust, deterministic, and does not have document-size limitations or cost implications, which make it more amenable to real-world applications in health systems.

ChatGPT Assisting Diagnosis of Neuro-Ophthalmology Diseases Based on Case Reports

Background: To evaluate the accuracy of Chat Generative Pre-Trained Transformer (ChatGPT), a large language model (LLM), to assist in diagnosing neuro-ophthalmic diseases based on case reports. Methods: We selected 22 different case reports of neuro-ophthalmic diseases from a publicly available online database. These cases included a wide range of chronic and acute diseases commonly seen by neuro-ophthalmic subspecialists. We inserted each case as a new prompt into ChatGPTs (GPT-3.5 and GPT-4) and asked for the most probable diagnosis. We then presented the exact information to 2 neuro-ophthalmologists and recorded their diagnoses, followed by comparing responses from both versions of ChatGPT. Results: GPT-3.5 and GPT-4 and the 2 neuro-ophthalmologists were correct in 13 (59%), 18 (82%), 19 (86%), and 19 (86%) out of 22 cases, respectively. The agreements between the various diagnostic sources were as follows: GPT-3.5 and GPT-4, 13 (59%); GPT-3.5 and the first neuro-ophthalmologist, 12 (55%); GPT-3.5 and the second neuro-ophthalmologist, 12 (55%); GPT-4 and the first neuro-ophthalmologist, 17 (77%); GPT-4 and the second neuro-ophthalmologist, 16 (73%); and first and second neuro-ophthalmologists 17 (77%). Conclusions: The accuracy of GPT-3.5 and GPT-4 in diagnosing patients with neuro-ophthalmic diseases was 59% and 82%, respectively. With further development, GPT-4 may have the potential to be used in clinical care settings to assist clinicians in providing quick, accurate diagnoses of patients in neuro-ophthalmology. The applicability of using LLMs like ChatGPT in clinical settings that lack access to subspeciality trained neuro-ophthalmologists deserves further research.

Exploring the Efficacy of Artificial Intelligence: A Comprehensive Analysis of CHAT-GPT's Accuracy and Completeness in Addressing Urinary Incontinence Queries.

Artificial intelligence models are increasingly gaining popularity among patients and healthcare professionals. While it is impossible to restrict patient's access to different sources of information on the Internet, healthcare professional needs to be aware of the content-quality available across different platforms. To investigate the accuracy and completeness of Chat Generative Pretrained Transformer (ChatGPT) in addressing frequently asked questions related to the management and treatment of female urinary incontinence (UI), compared to recommendations from guidelines. This is a cross-sectional study. Two researchers developed 14 frequently asked questions related to UI. Then, they were inserted into the ChatGPT platform on September 16, 2023. The accuracy (scores from 1 to 5) and completeness (score from 1 to 3) of ChatGPT's answers were assessed individually by two experienced researchers in the Women's Health field, following the recommendations proposed by the guidelines for UI. Most of the answers were classified as "more correct than incorrect" (n = 6), followed by "incorrect information than correct" (n = 3), "approximately equal correct and incorrect" (n = 2), "near all correct" (n = 2, and "correct" (n = 1). Regarding the appropriateness, most of the answers were classified as adequate, as they provided the minimum information expected to be classified as correct. These results showed an inconsistency when evaluating the accuracy of answers generated by ChatGPT compared by scientific guidelines. Almost all the answers did not bring the complete content expected or reported in previous guidelines, which highlights to healthcare professionals and scientific community a concern about using artificial intelligence in patient counseling.

The Use of the OpenAI GPT-3 AI Technology for Marketing Content Purposes

Artificial intelligence (AI) technologies rapidly transform marketing worldwide with fast-paced content creation productivity driven by machine learning algorithms generating heightened interest from researchers. In recent years, AI tools helped writers by acting as a helping hand in the creation process, quick fact-checking and grammar correction. As OpenAI introduced the Generative Pre-trained Transformer 3 model (GPT-3), its newest autoregressive language model that uses deep learning to produce human-like text; we have researched its usability for generating a wide range of marketing content. The main objective of the research was to analyze different outputs of the GPT-3 AI with the help of a group of anonymous respondents to attempt to measure its usability in marketing environments as well as a way to measure if GPT-3 could pass the Touring test.

Evaluating the positive predictive value of code-based identification of cirrhosis and its complications utilizing GPT-4.

Diagnosis code classification is a common method for cohort identification in cirrhosis research, but it is often inaccurate and augmented by labor-intensive chart review. Natural language processing (NLP) using large language models (LLMs) is a potentially more accurate method. To assess LLMs' potential for cirrhosis cohort identification, we compared code-based versus LLM-based classification with chart review as a "gold standard." We extracted and conducted a limited chart review of 3,788 discharge summaries of cirrhosis admissions. We engineered zero-shot prompts using Generative Pre-trained Transformer (GPT)-4 to determine whether cirrhosis and its complications were active hospitalization problems. We calculated positive predictive values (PPVs) of LLM-based classification versus limited chart review, and PPVs of code-based versus LLM-based classification as a "silver standard" in all 3,788 summaries. Versus gold standard chart review, code-based classification achieved PPVs of 82.2% for identifying cirrhosis, 41.7% hepatic encephalopathy, 72.8% ascites, 59.8% gastrointestinal bleeding, and 48.8% spontaneous bacterial peritonitis. Compared to chart review, GPT-4 achieved 87.8-98.8% accuracies for identifying cirrhosis and its complications. Using LLM as a silver standard, code-based classification achieved PPVs of 79.8% for identifying cirrhosis, 53.9% hepatic encephalopathy, 55.3% ascites, 67.6% gastrointestinal bleeding, and 65.5% spontaneous bacterial peritonitis. LLM-based classification was highly accurate versus manual chart review in identifying cirrhosis and its complications - this allowed us to assess the performance of code-based classification at scale using LLMs as a silver standard. These results suggest LLMs could augment or replace code-based cohort classification and raise questions regarding the necessity of chart review.

Assessing the Clinical Appropriateness and Practical Utility of ChatGPT as an Educational Resource for Patients Considering Minimally Invasive Spine Surgery.

Introduction Minimally invasive spine surgery (MISS) has evolved over the last three decades as a less invasive alternative to traditional spine surgery, offering benefits such as smaller incisions, faster recovery, and lower complication rates. With patients frequently seeking information about MISS online, the comprehensibility and accuracy of this information are crucial. Recent studies have shown that much of the online material regarding spine surgery exceeds the recommended readability levels, making it difficult for patients to understand. This study explores the clinical appropriateness and readability of responses generated by Chat Generative Pre-Trained Transformer (ChatGPT) to frequently asked questions (FAQs) about MISS. Methods A set of 15 FAQs was formulated based on clinical expertise and existing literature on MISS. Each question was independently inputted into ChatGPT five times, and the generated responses were evaluated by three neurosurgery attendings for clinical appropriateness. Appropriateness was judged based on accuracy, readability, and patient accessibility. Readability was assessed using seven standardized readability tests, including the Flesch-Kincaid Grade Level and Flesch Reading Ease (FRE) scores. Statistical analysis was performed to compare readability scores across preoperative, postoperative, and intraoperative/technical question categories. Results The mean readability scores for preoperative, postoperative, and intraoperative/technical questions were 15±2.8, 16±3, and 15.7±3.2, respectively, significantly exceeding the recommended sixth- to eighth-grade reading level for patient education (p=0.017). Differences in readability across individual questions were also statistically significant (p<0.001). All responses required a reading level above 11th grade, with a majority indicating college-level comprehension. Although preoperative and postoperative questions generally elicited clinically appropriate responses, 50% of intraoperative/technical questions yielded either "inappropriate" or "unreliable" responses, particularly for inquiries about radiation exposure and the use of lasers in MISS. Conclusions While ChatGPT is proficient in providing clinically appropriate responses to certain FAQs about MISS, it frequently produces responses that exceed the recommended readability level for patient education. This limitation suggests that its utility may be confined to highly educated patients, potentially exacerbating existing disparities in patient comprehension. Future AI-based patient education tools must prioritize clear and accessible communication, with oversight from medical professionals to ensure accuracy and appropriateness. Further research comparing ChatGPT's performance with other AI models could enhance its application in patient education across medical specialties.

GPT-4 and Beyond : Advancements in AI Language Models

This comprehensive article explores the groundbreaking advancements and implications of GPT-4, the latest iteration in the Generative Pre-trained Transformer series. It delves into GPT-4's enhanced comprehension and contextual awareness, multilingual proficiency, expanded knowledge base, multimodal capabilities, and improved safety and ethical considerations. The article provides quantifiable improvements and practical implications across various domains, including natural language processing, machine translation, research assistance, education, and content creation. It also addresses the challenges and limitations of the model, such as biases and computational requirements, while discussing future directions in AI development. The piece concludes with projections for future AI capabilities, emphasizing more human-like reasoning, handling of complex tasks, and seamless integration with other systems, while also highlighting the ethical considerations and challenges that accompany these advancements.

Exploring the Effectiveness of Advanced Chatbots in Educational Settings: A Mixed-Methods Study in Statistics

The Generative Pre-trained Transformer (GPT) is a highly advanced natural language processing model. This model can generate conversation-style responses to user input. The rapid rise of GPT has transformed academic domains, with studies exploring the potential of chatbots in education. This research investigates the effectiveness of ChatGPT 3.5, ChatGPT 4.0 by OpenAI, and Chatbot Bing by Microsoft in solving statistical exam-type problems in the educational setting. In addition to quantifying the errors made by these chatbots, this study seeks to understand the causes of these errors to provide recommendations. A mixed-methods approach was employed to achieve this goal, including quantitative and qualitative analyses (Grounded Theory with semi-structured interviews). The quantitative stage involves statistical problem-solving exercises for undergraduate engineering students, revealing error rates based on the reason for the error, statistical fields, sub-statistics fields, and exercise types. The quantitative analysis provided crucial information necessary to proceed with the qualitative study. The qualitative stage employs semi-structured interviews with selected chatbots; this includes confrontation between them that generates agreement, disagreement, and differing viewpoints. On some occasions, chatbots tend to maintain rigid positions, lacking the ability to adapt or acknowledge errors. This inflexibility may affect their effectiveness. The findings contribute to understanding the integration of AI tools in education, offering insights for future implementations and emphasizing the need for critical evaluation and responsible use.

Enhancing English abstract quality for non-English speaking authors using ChatGPT: A comparative study of Taiwan, Japan, China, and South Korea with slope graphs.

A clear and proficient English abstract is crucial for disseminating research findings to a global audience, significantly impacting the accessibility and visibility of research from non-English speaking countries. Despite the adoption of ChatGPT since November 30, 2022, a comprehensive analysis of improvements in English abstracts in scholarly journals has not been conducted. This study aims to identify which authors from Taiwan, Japan, China, and South Korea (TJCS) have shown the most improvement in English abstracts. Article abstracts published in Medicine (Baltimore) sourced from the Web of Science Core Collection from 2020 to 2023 were downloaded. A mixed-methods approach was employed, combining quantitative analysis of linguistic quality indicators and qualitative assessments of coherence and engagement using the Rasch model. Ten quality indicators were determined by prompting ChatGPT. Two scenarios were analyzed: (1) generative pretrained transformer (GPT) versus non-GPT (each with 30 abstracts from 2021) and (2) TJCS in comparison (each with 100 abstracts from 2021 and 2023, respectively). Standardized mean differences were compared using paired samples t test. Visuals including forest plots, Rasch Wright Map, the slope graph, and scatter plot with 95% control lines were used to examine the 2 scenarios. (1) No significant difference was found between GPT and non-GPT abstracts with Rasch logit scores of 3.31 and 3.17, respectively (P = .42), likely due to small sample size (n = 30); (2) significant difference exists between 2020 and 2023 in each country, and between South Korea and Taiwan in 2020. Among TJCS, Taiwan showed the greatest improvement in English abstract quality post-ChatGPT implementation, followed by Japan, China, and South Korea. The English abstracts in Medicine (Baltimore) have improved, reflecting the tool's positive impact on enhancing technical language. This study demonstrates that ChatGPT can enhance the quality of English abstracts for authors from non-English speaking regions, although the assumption that all authors use ChatGPT is invalid and impractical. The findings underscore the value of artificial intelligence tools in academic writing and recommend further investigation into the long-term implications of artificial intelligence integration in scholarly communication.

A thorough examination of ChatGPT-3.5 potential applications in medical writing: A preliminary study.

Effective communication of scientific knowledge plays a crucial role in the advancement of medical research and health care. Technological advancements have introduced large language models such as Chat Generative Pre-Trained Transformer (ChatGPT), powered by artificial intelligence (AI), which has already shown promise in revolutionizing medical writing. This study aimed to conduct a detailed evaluation of ChatGPT-3.5's role in enhancing various aspects of medical writing. From May 10 to 12, 2023, the authors engaged in a series of interactions with ChatGPT-3.5 to evaluate its effectiveness in various tasks, particularly its application to medical writing, including vocabulary enhancement, text rewriting for plagiarism prevention, hypothesis generation, keyword generation, title generation, article summarization, simplification of medical jargon, transforming text from informal to scientific and data interpretation. The exploration of ChatGPT's functionalities in medical writing revealed its potential in enhancing various aspects of the writing process, demonstrating its efficiency in improving vocabulary usage, suggesting alternative phrasing, and providing grammar enhancements. While the results indicate the effectiveness of ChatGPT (version 3.5), the presence of certain imperfections highlights the current indispensability of human intervention to refine and validate outputs, ensuring accuracy and relevance in medical settings. The integration of AI into medical writing shows significant potential for improving clarity, efficiency, and reliability. This evaluation highlights both the benefits and limitations of using ChatGPT-3.5, emphasizing its ability to enhance vocabulary, prevent plagiarism, generate hypotheses, suggest keywords, summarize articles, simplify medical jargon, and transform informal text into an academic format. However, AI tools should not replace human expertise. It is crucial for medical professionals to ensure thorough human review and validation to maintain the accuracy and relevance of the content in case they eventually use AI as a supplementary resource in medical writing. Accepting this mutually symbiotic partnership holds the promise of improving medical research and patient outcomes, and it sets the stage for the fusion of AI and human knowledge to produce a novel approach to medical assessment. Thus, while AI can streamline certain tasks, experienced medical writers and researchers must perform final reviews to uphold high standards in medical communications.

Postoperative Otoplasty Care With ChatGPT-4: A Study on Artificial Intelligence (AI)-Assisted Patient Concern and Education.

Otoplasty is a cosmetic surgery that is performed to alter the size, shape, or position of the ear by using permanent stitches. Its main purpose is to correct protruding ears, a condition known as prominauris. After the surgery, it is crucial to provide proper care to ensure successful recovery. However, obtaining timely medical advice can be difficult, especially in remote areas or places with limited resources. To address this issue, incorporating advanced artificial intelligence (AI) tools like Chat Generative Pre-trained Transformer (ChatGPT)-4 into postsurgical care could help fill the gap in patient education and support. This study aims to assess whether ChatGPT4 can be a reliable, accurate, and effective method for answering the most common patient questions and concerns post-otoplasty. The main objective was to assess the AI chatbot's capacity to deliver precise, concise, and pertinent information, especially in situations where health care professionals are limited in availability. In this study, over 50 patients were engaged, and ChatGPT4 was employed to present the same 5 common postoperative questions post-otoplasty surgery care. The AI chatbot's responses were analyzed for accuracy, response time, clarity, and relevance. The chatbot could potentially provide timely assistance, answer questions, and address concerns related to postsurgical care in otoplasty. The responses exhibited a perfect accuracy rate of 100%, closely corresponding to existing medical guidelines. This study explores the potential of AI-driven solutions to enhance patient education and support, especially in areas where access to health care professionals may be limited. However, professional medical advice is crucial in postoperative care and cannot be replaced by ChatGPT-4. By leveraging AI tools like chatbots, individuals in remote or resource-limited settings can potentially receive valuable information and guidance, contributing to successful rehabilitation and overall health care outcomes. Ethical considerations around the use of AI in health care must also be carefully addressed to ensure patient privacy, data security, and appropriate clinical oversight.

Technological Advancements in Menstrual Health: The Role of Generative Pre-Trained Transformer and Bees Algorithm

This paper introduces the concept of a smart menstrual cup, incorporating advanced technology to address challenges associated with traditional menstrual health management methods. The proposed method, Hybrid Bidirectional Encoder Generative Transformer based Bees Search (Hybrid BEGT-BS), aims to enhance the longevity and reliability of smart menstrual cups. The Generative Pre-trained Transformer (GPT) is employed to extract key information and determine emotional tones related to menstruation, while the Bidirectional Encoder Representations from Transformer (BERT) classifies menstrual-related data such as cycle tracking, hygiene, and symptoms. Further different validation metrics such as F1-score, specificity, Area Under the Curve-Receiver Operating Characteristic (AUC-ROC), Mean Squared Error (MSE), recall, energy consumption, accuracy, and precision are employed to assess the method's effectiveness. From the comparative results it demonstrates the superior performance of the Hybrid BEGT-BS method in enhancing the performance of smart menstrual cups.

Efficacy of large language models and their potential in Obstetrics and Gynecology education.

The performance of large language models (LLMs) and their potential utility in obstetric and gynecological education are topics of ongoing debate. This study aimed to contribute to this discussion by examining the recent advancements in LLM technology and their transformative potential in artificial intelligence. This study assessed the performance of generative pre-trained transformer (GPT)-3.5 and -4 in understanding clinical information, as well as its potential implications for obstetric and gynecological education. Obstetrics and gynecology residents at three hospitals underwent an annual promotional examination, from which 116 of the 170 questions over 4 years (2020-2023) were analyzed, excluding 54 questions with images. The scores achieved by GPT-3.5, -4, and the 100 residents were compared. The average scores across all 4 years for GPT-3.5 and -4 were 38.79 (standard deviation [SD], 5.65) and 79.31 (SD, 3.67), respectively. For groups R1, R2, and R3, the cumulative annual average scores were 79.12 (SD, 9.00), 80.95 (SD, 5.86), and 83.60 (SD, 6.82), respectively. No statistically significant differences were observed between the scores of GPT-4.0 and those of the residents. When analyzing questions specific to obstetrics, the average scores for GPT-3.5 and -4.0 were 33.44 (SD, 10.18) and 90.22 (SD, 7.68), respectively. GPT-4 demonstrated exceptional performance in obstetrics, different types of data interpretation, and problem solving, showcasing the potential utility of LLMs in these areas. However, acknowledging the constraints of LLMs is crucial and their utilization should augment human expertise and discernment.

APPLICATIONS OF MULTIMODAL GENERATIVE ARTIFICIAL INTELLIGENCE IN A REAL-WORLD RETINA CLINIC SETTING.

This study evaluates a large language model, Generative Pre-trained Transformer 4 with vision, for diagnosing vitreoretinal diseases in real-world ophthalmology settings. A retrospective cross-sectional study at Bascom Palmer Eye Clinic, analyzing patient data from January 2010 to March 2023, assesses Generative Pre-trained Transformer 4 with vision's performance on retinal image analysis and International Classification of Diseases 10th revision coding across 2 patient groups: simpler cases (Group A) and complex cases (Group B) requiring more in-depth analysis. Diagnostic accuracy was assessed through open-ended questions and multiple-choice questions independently verified by three retina specialists. In 256 eyes from 143 patients, Generative Pre-trained Transformer 4-V demonstrated a 13.7% accuracy for open-ended questions and 31.3% for multiple-choice questions, with International Classification of Diseases 10th revision code accuracies at 5.5% and 31.3%, respectively. Accurately diagnosed posterior vitreous detachment, nonexudative age-related macular degeneration, and retinal detachment. International Classification of Diseases 10th revision coding was most accurate for nonexudative age-related macular degeneration, central retinal vein occlusion, and macular hole in OEQs, and for posterior vitreous detachment, nonexudative age-related macular degeneration, and retinal detachment in multiple-choice questions. No significant difference in diagnostic or coding accuracy was found in Groups A and B. Generative Pre-trained Transformer 4 with vision has potential in clinical care and record keeping, particularly with standardized questions. Its effectiveness in open-ended scenarios is limited, indicating a significant limitation in providing complex medical advice.

Generative pre-trained transformer (GPT)-4 support for differential diagnosis in neuroradiology.

Differential diagnosis in radiology relies on the accurate identification of imaging patterns. The use of large language models (LLMs) in radiology holds promise, with many potential applications that may enhance the efficiency of radiologists' workflow. The study aimed to evaluate the efficacy of generative pre-trained transformer (GPT)-4, a LLM, in providing differential diagnoses in neuroradiology, comparing its performance with board-certified neuroradiologists. Sixty neuroradiology reports with variable diagnoses were inserted into GPT-4, which was tasked with generating a top-3 differential diagnosis for each case. The results were compared to the true diagnoses and to the differential diagnoses provided by three blinded neuroradiologists. Diagnostic accuracy and agreement between readers were assessed. Of the 60 patients (mean age 47.8 years, 65% female), GPT-4 correctly included the diagnoses in its differentials in 61.7% (37/60) of cases, while the neuroradiologists' accuracy ranged from 63.3% (38/60) to 73.3% (44/60). Agreement between GPT-4 and the neuroradiologists, and among the neuroradiologists was fair to moderate [Cohen's kappa (kw) 0.34-0.44 and kw 0.39-0.54, respectively]. GPT-4 shows potential as a support tool for differential diagnosis in neuroradiology, though it was outperformed by human experts. Radiologists should remain mindful to the limitations of LLMs, while harboring their potential to enhance educational and clinical work.

Comparative Analysis of Single and Multiagent Large Language Model Architectures for Domain-Specific Tasks in Well Construction

Summary This paper explores the application of large language models (LLMs) in the oil and gas (O&amp;G) sector, specifically within well construction and maintenance tasks. The study evaluates the performances of a single agent and a multiagent LLM-based architecture in processing different tasks, offering a comparative perspective on their accuracy and the cost implications of their implementation. The results indicate that multiagent systems offer improved performance in question and answer (Q&amp;A) tasks, with a truthfulness measure 28% higher than single-agent systems but at a higher financial cost. Specifically, the multiagent architecture incurs costs that are, on average, 3.7 times higher than those of the single-agent setup due to the increased number of tokens processed. Conversely, single-agent systems excel in Text-to-SQL (structured query language) tasks, particularly when using the Generative Pre-Trained Transformer 4 (GPT-4), achieving a 15% higher score compared to multiagent configurations, suggesting that simpler architectures can sometimes outpace complexity. The novelty of this work lies in its original examination of the specific challenges presented by the complex, technical, unstructured data inherent in well construction operations, contributing to strategic planning for adopting generative artificial intelligence (AI) (Gen-AI) applications and providing a basis for optimizing solutions against economic and technological parameters.

Prompt engineering with a large language model to assist providers in responding to patient inquiries: a real-time implementation in the electronic health record.

Large language models (LLMs) can assist providers in drafting responses to patient inquiries. We examined a prompt engineering strategy to draft responses for providers in the electronic health record. The aim was to evaluate the change in usability after prompt engineering. A pre-post study over 8 months was conducted across 27 providers. The primary outcome was the provider use of LLM-generated messages from Generative Pre-Trained Transformer 4 (GPT-4) in a mixed-effects model, and the secondary outcome was provider sentiment analysis. Of the 7605 messages generated, 17.5% (n = 1327) were used. There was a reduction in negative sentiment with an odds ratio of 0.43 (95% CI, 0.36-0.52), but message use decreased (P < .01). The addition of nurses after the study period led to an increase in message use to 35.8% (P < .01). The improvement in sentiment with prompt engineering suggests better content quality, but the initial decrease in usage highlights the need for integration with human factors design. Future studies should explore strategies for optimizing the integration of LLMs into the provider workflow to maximize both usability and effectiveness.

SIGMA: Secure GPT Inference with Function Secret Sharing

Secure 2-party computation (2PC) enables secure inference that offers protection for both proprietary machine learning (ML) models and sensitive inputs to them. However, the existing secure inference solutions suffer from high latency and communication overheads, particularly for transformers. Function secret sharing (FSS) is a recent paradigm for obtaining efficient 2PC protocols with a preprocessing phase. We provide Sigma, the first end-to-end system for secure transformer inference based on FSS. By constructing new FSS-based protocols for complex machine learning functionalities, such as Softmax, GeLU and SiLU, and also accelerating their computation on GPUs, Sigma improves the latency of secure inference of transformers by 11 - 19x over the state-of-the-art that uses preprocessing and GPUs. We present the first secure inference of generative pre-trained transformer (GPT) models. In particular, Sigma executes Meta's Llama2 (available on HuggingFace) with 13 billion parameters in 44 seconds and GPT2 in 1.6 seconds

Lumbar Radicular Pain in the Eyes of Artificial Intelligence: Can You ‘Imagine’ What I ‘Feel’?

Pain is a complex sensory and emotional experience that significantly impacts individuals' well-being. Lumbar radicular pain (LRP) is a prevalent neuropathic pain affecting 9.9% to 25% of the population annually.Accurate identification of pain patterns in LRP is essential for diagnosis and management. Artificial intelligence has potential in health care but faces challenges in reliability and accuracy. This study aimed to investigate the accuracy and consistency of LRP patterns demonstrated by ChatGPT-4o. The study was conducted at Üsküdar State Hospital from June 1 to June 30, 2024, utilizing the Generative Pretrained Transformer (GPT), version 4o language model. ChatGPT-4o was prompted to generate and mark LRP patterns for L4, L5, and S1 radiculopathies on an anatomical model. The process was repeated after two weeks to assess consistency. The markings by ChatGPT were compared with those by two experienced specialists using OpenCV for analysis. ChatGPT's initial and follow-up markings of L4, L5, and S1 radiculopathy pain patterns were statistically significantly different from each other and from the specialists' markings (P < 0.001 for all comparisons). ChatGPT currently lacks the capacity to accurately and consistently represent LRP patterns. AI tools in health care require further refinement, validation, and regulation to ensure reliability and safety. Future research should involve multiple AI platforms and broader medical conditions to enhance generalizability.

Nursing Education in the Era of Generative Artificial Intelligence: Are We Ready?

Generative artificial intelligence (GAI) has taken the world by storm, causing notable tension within the field of education. Nursing education is no exception, facing imminent challenges and opportunities. GAI, a unique and immensely powerful technology championed by ChatGPT (Chat generative pre-trained transformer), represents a new frontier in artificial intelligence. ChatGPT, a product of deep learning - a subset of machine learning that mirrors the human brain's approach to learning and responding to data, information, and prompts - exemplifies this technological leap (Sahoo et al., 2022). GAI stands out for its ability not only to provide responses but also to generate the content of those responses, surpassing the human-like interactions typically seen in conversational AI (Lim et al., 2023; Su & Yang, 2023). Currently, ChatGPT has demonstrated significant application potential in nursing education in various aspects. For example, ChatGPT provides personalized learning (Tam et al., 2023); is easy to use (Vaughn et al., 2024); provides rapid information (Goktas et al., 2024; Liu et al., 2023), rapid responses, and assistance in writing (Sun & Hoelscher, 2023); improves students' problem-solving and critical thinking skills (Goktas et al., 2024; Sun & Hoelscher, 2023); supports educators in developing curricula and preparing course materials and may be used in translation processes (Tam et al., 2023); and helps healthcare professionals better understand complex medical concepts and procedures by providing easily comprehensible and up-to-date information (Krüger et al., 2023). Therefore, integrating ChatGPT into nursing education not only provides students with a more effective and interactive learning experience but also offers educators supportive tools that are directly applicable in teaching. These technologies can enhance / improve teaching by providing personalized learning solutions through, for example, generating teaching cases and simulating clinical scenarios to enhance the learning experience of students (Liu et al., 2023; Vaughn et al., 2024). Despite the significant benefits realized, nursing education in the era of GAI also faces challenges and limitations. Over-reliance on ChatGPT may limit students' critical thinking, problem-solving, and innovation capabilities, leading to a lack of independent thought. Educators should integrate GAI-supported tools into the learning process, but encourage and guide students to use ChatGPT as a supplementary learning tool rather than a substitute (Tam et al., 2023). This approach will help ensure students develop the skills and knowledge necessary to use the technology responsibly and ethically and allow educators to better address key related challenges, enhance education quality, and lay a foundation for cultivating high-quality nursing professionals. GAI is inevitable, and banning it may lead to increased attention and psychological reactance, making students more eager to access this technology. Therefore, educational institutions should embrace rather than shun its use (Lim et al., 2023). It is hoped that readers, after reading this special column, will be inspired to learn more about GAI applications and their significance and thus come to view GAI as a driving force for educational transformation, ensuring the continuous development of education and safeguarding the future of education and, by extension, the society of tomorrow.