UNASSIGNED: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out.
UNASSIGNED: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot.
UNASSIGNED: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated.
UNASSIGNED: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference -0.51, 95% CI -0.54 to -0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference -0.06, 95% CI -0.08 to -0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001).
UNASSIGNED: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work.

UNASSIGNED: Accurately assessing an individual\'s diet is vital in the management of personal nutrition and in the study of the effect of diet on health. Despite its importance, the tools available for dietary assessment remain either too imprecise, expensive, or burdensome for clinical or research use. Image-based methods offer a potential new tool to improve the reliability and accessibility of dietary assessment. Though promising, image-based methods are sensitive to adherence, as images cannot be captured from meals that have already been consumed. Adherence to image-based methods may be improved with appropriately timed prompting via text message.
UNASSIGNED: This study aimed to quantitatively examine the effect of prompt timing on adherence to an image-based dietary record and qualitatively explore the participant experience of dietary assessment in order to inform the design of a novel image-based dietary assessment tool.
UNASSIGNED: This study used a randomized crossover design to examine the intraindividual effect of 3 prompt settings on the number of images captured in an image-based dietary record. The prompt settings were control, where no prompts were sent; standard, where prompts were sent at 7:15 AM, 11:15 AM, and 5:15 PM for every participant; and tailored, where prompt timing was tailored to habitual meal times for each participant. Participants completed a text-based dietary record at baseline to determine the timing of tailored prompts. Participants were randomized to 1 of 6 study sequences, each with a unique order of the 3 prompt settings, with each 3-day image-based dietary record separated by a washout period of at least 7 days. The qualitative component comprised semistructured interviews and questionnaires exploring the experience of dietary assessment.
UNASSIGNED: A total of 37 people were recruited, and 30 participants (11 male, 19 female; mean age 30, SD 10.8 years), completed all image-based dietary records. The image rate increased by 0.83 images per day in the standard setting compared to control (P=.23) and increased by 1.78 images per day in the tailored setting compared to control (P≤.001). We found that 13/21 (62%) of participants preferred to use the image-based dietary record versus the text-based dietary record but reported method-specific challenges with each method, particularly the inability to record via an image after a meal had been consumed.
UNASSIGNED: Tailored prompting improves adherence to image-based dietary assessment. Future image-based dietary assessment tools should use tailored prompting and offer both image-based and written input options to improve record completeness.

BACKGROUND: Large language models (LLMs) have shown remarkable capabilities in natural language processing (NLP), especially in domains where labeled data are scarce or expensive, such as the clinical domain. However, to unlock the clinical knowledge hidden in these LLMs, we need to design effective prompts that can guide them to perform specific clinical NLP tasks without any task-specific training data. This is known as in-context learning, which is an art and science that requires understanding the strengths and weaknesses of different LLMs and prompt engineering approaches.
OBJECTIVE: The objective of this study is to assess the effectiveness of various prompt engineering techniques, including 2 newly introduced types-heuristic and ensemble prompts, for zero-shot and few-shot clinical information extraction using pretrained language models.
METHODS: This comprehensive experimental study evaluated different prompt types (simple prefix, simple cloze, chain of thought, anticipatory, heuristic, and ensemble) across 5 clinical NLP tasks: clinical sense disambiguation, biomedical evidence extraction, coreference resolution, medication status extraction, and medication attribute extraction. The performance of these prompts was assessed using 3 state-of-the-art language models: GPT-3.5 (OpenAI), Gemini (Google), and LLaMA-2 (Meta). The study contrasted zero-shot with few-shot prompting and explored the effectiveness of ensemble approaches.
RESULTS: The study revealed that task-specific prompt tailoring is vital for the high performance of LLMs for zero-shot clinical NLP. In clinical sense disambiguation, GPT-3.5 achieved an accuracy of 0.96 with heuristic prompts and 0.94 in biomedical evidence extraction. Heuristic prompts, alongside chain of thought prompts, were highly effective across tasks. Few-shot prompting improved performance in complex scenarios, and ensemble approaches capitalized on multiple prompt strengths. GPT-3.5 consistently outperformed Gemini and LLaMA-2 across tasks and prompt types.
CONCLUSIONS: This study provides a rigorous evaluation of prompt engineering methodologies and introduces innovative techniques for clinical information extraction, demonstrating the potential of in-context learning in the clinical domain. These findings offer clear guidelines for future prompt-based clinical NLP research, facilitating engagement by non-NLP experts in clinical NLP advancements. To the best of our knowledge, this is one of the first works on the empirical evaluation of different prompt engineering approaches for clinical NLP in this era of generative artificial intelligence, and we hope that it will inspire and inform future research in this area.

BACKGROUND: School canteens are a recommended setting to influence adolescent nutrition due to their scope to improve student food choices. Online lunch ordering systems (\"online canteens\") are increasingly used and represent attractive infrastructure to implement choice architecture interventions that nudge users toward healthier food choices. A recent cluster randomized controlled trial demonstrated the short-term effectiveness (2-month follow-up) of a choice architecture intervention to increase the healthiness of foods purchased by high school students from online canteens. However, there is little evidence regarding the long-term effectiveness of choice architecture interventions targeting adolescent food purchases, particularly those delivered online.
OBJECTIVE: This study aimed to determine the long-term effectiveness of a multi-strategy choice architecture intervention embedded within online canteen infrastructure in high schools at a 15-month follow-up.
METHODS: A cluster randomized controlled trial was undertaken with 1331 students (from 9 high schools) in New South Wales, Australia. Schools were randomized to receive the automated choice architecture intervention (including menu labeling, positioning, feedback, and prompting strategies) or the control (standard online ordering). The foods purchased were classified according to the New South Wales Healthy Canteen strategy as either \"everyday,\" \"occasional,\" or \"should not be sold.\" Primary outcomes were the average proportion of \"everyday,\" \"occasional,\" and \"should not be sold\" items purchased per student. Secondary outcomes were the mean energy, saturated fat, sugar, and sodium content of purchases. Outcomes were assessed using routine data collected by the online canteen.
RESULTS: From baseline to 15-month follow-up, on average, students in the intervention group ordered significantly more \"everyday\" items (+11.5%, 95% CI 7.3% to 15.6%; P<.001), and significantly fewer \"occasional\" (-5.4%, 95% CI -9.4% to -1.5%; P=.007) and \"should not be sold\" items (-6%, 95% CI -9.1% to -2.9%; P<.001), relative to controls. There were no between-group differences over time in the mean energy, saturated fat, sugar, or sodium content of lunch orders.
CONCLUSIONS: Given their longer-term effectiveness, choice architecture interventions delivered via online canteens may represent a promising option for policy makers to support healthy eating among high school students.
BACKGROUND: Australian Clinical Trials ACTRN12620001338954, https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=380546 ; Open Science Framework osf.io/h8zfr, https://osf.io/h8zfr/.

BACKGROUND: Given that signage, messaging, and advertisements (ads) are the gateway to many interventions in suicide prevention, it is important that we understand what type of messaging works best for whom.
OBJECTIVE: We investigated whether explicitly mentioning suicide increases engagement using internet ads by investigating engagement with campaigns with different categories of keywords searched, which may reflect different cognitive states.
METHODS: We ran a 2-arm study Australia-wide, with or without ads featuring explicit suicide wording. We analyzed whether there were differences in engagement for campaigns with explicit and nonexplicit ads for low-risk (distressed but not explicitly suicidal), high-risk (explicitly suicidal), and help-seeking for suicide keywords.
RESULTS: Our analyses revealed that having explicit wording has opposite effects, depending on the search terms used: explicit wording reduced the engagement rate for individuals searching for low-risk keywords but increased engagement for those using high-risk keywords.
CONCLUSIONS: The findings suggest that individuals who are aware of their suicidality respond better to campaigns that explicitly use the word \"suicide.\" We found that individuals who search for low-risk keywords also respond to explicit ads, suggesting that some individuals who are experiencing suicidality search for low-risk keywords.

Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we investigate the bias of AIGC produced by seven representative LLMs, including ChatGPT and LLaMA. We collect news articles from The New York Times and Reuters, both known for their dedication to provide unbiased news. We then apply each examined LLM to generate news content with headlines of these news articles as prompts, and evaluate the gender and racial biases of the AIGC produced by the LLM by comparing the AIGC and the original news articles. We further analyze the gender bias of each LLM under biased prompts by adding gender-biased messages to prompts constructed from these news headlines. Our study reveals that the AIGC produced by each examined LLM demonstrates substantial gender and racial biases. Moreover, the AIGC generated by each LLM exhibits notable discrimination against females and individuals of the Black race. Among the LLMs, the AIGC generated by ChatGPT demonstrates the lowest level of bias, and ChatGPT is the sole model capable of declining content generation when provided with biased prompts.

The versatility of ChatGPT in performing a diverse range of tasks has elicited considerable interest on its potential applications within professional fields. Taking drug discovery as a testbed, this paper provides a comprehensive evaluation of ChatGPT\'s ability on molecule property prediction. The study focuses on three aspects: 1) Effects of different prompt settings, where we investigate the impact of varying prompts on the prediction outcomes of ChatGPT; 2) Comprehensive evaluation on molecule property prediction, where we conduct a comprehensive evaluation on 53 ADMET-related endpoints; 3) Analysis of ChatGPT\'s potential and limitations, where we make comparisons with models tailored for molecule property prediction, thus gaining a more accurate understanding of ChatGPT\'s capabilities and limitations in this area. Through comprehensive evaluation, we find that 1) With appropriate prompt settings, ChatGPT can attain satisfactory prediction outcomes that are competitive with specialized models designed for those tasks. 2) Prompt settings significantly affect ChatGPT\'s performance. Among all prompt settings, the strategy of selecting examples in few-shot has the greatest impact on results. Scaffold sampling greatly outperforms random sampling. 3) The capacity of ChatGPT to accomplish high-precision predictions is significantly influenced by the quality of examples provided, which may constrain its practical applicability in real-world scenarios. This work highlights ChatGPT\'s potential and limitations on molecule property prediction, which we hope can inspire future design and evaluation of Large Language Models within scientific domains.

BACKGROUND: In the context of a syphilis outbreak in neighboring states, a multifaceted systems change to increase testing for sexually transmitted infections (STIs) among young Aboriginal people aged 15 to 29 years was implemented at an Aboriginal Community Controlled Health Service (ACCHS) in New South Wales, Australia. The components included electronic medical record prompts and automated pathology test sets to increase STI testing in annual routine health assessments, the credentialing of nurses and Aboriginal health practitioners to conduct STI tests independently, pathology request forms presigned by a physician, and improved data reporting.
OBJECTIVE: We aimed to determine whether the systems change increased the integration of STI testing into routine health assessments by clinicians between April 2019 and March 2020, the inclusion of syphilis tests in STI testing, and STI testing uptake overall. We also explored the understandings of factors contributing to the acceptability and normalization of the systems change among staff.
METHODS: We used a mixed methods design to evaluate the effectiveness and acceptability of the systems change implemented in 2019. We calculated the annual proportion of health assessments that included tests for chlamydia, gonorrhea, and syphilis, as well as an internal control (blood glucose level). We conducted an interrupted time series analysis of quarterly proportions 24 months before and 12 months after the systems change and in-depth semistructured interviews with ACCHS staff using normalization process theory.
RESULTS: Among 2461 patients, the annual proportion of health assessments that included any STI test increased from 16% (38/237) in the first year of the study period to 42.9% (94/219) after the implementation of the systems change. There was an immediate and large increase when the systems change occurred (coefficient=0.22; P=.003) with no decline for 12 months thereafter. The increase was greater for male individuals, with no change for the internal control. Qualitative data indicated that nurse- and Aboriginal health practitioner-led testing and presigned pathology forms proved more difficult to normalize than electronic prompts and shortcuts. The interviews identified that staff understood the modifications to have encouraged cultural change around the role of sexual health care in routine practice.
CONCLUSIONS: This study provides evidence for the first time that optimizing health assessments electronically is an effective and acceptable strategy to increase and sustain clinician integration and the completeness of STI testing among young Aboriginal people attending an ACCHS. Future strategies should focus on increasing the uptake of health assessments and promote whole-of-service engagement and accountability.

The vast majority of people who suffer unexpected cardiac arrest are performed cardiopulmonary resuscitation (CPR) by passersby in a desperate attempt to restore life, but endeavors turn out to be fruitless on account of disqualification. Fortunately, many pieces of research manifest that disciplined training will help to elevate the success rate of resuscitation, which constantly desires a seamless combination of novel techniques to yield further advancement. To this end, we collect a specialized CPR video dataset in which trainees make efforts to behave resuscitation on mannequins independently in adherence to approved guidelines, promoting an auxiliary toolbox to assist supervision and rectification of intermediate potential issues via modern deep learning methodologies. Our research empirically views this problem as a temporal action segmentation (TAS) task in computer vision, which aims to segment an untrimmed video at a frame-wise level. Here, we propose a Prompt-enhanced hierarchical Transformer (PhiTrans) that integrates three indispensable modules, including a textual prompt-based Video Features Extractor (VFE), a transformer-based Action Segmentation Executor (ASE), and a regression-based Prediction Refinement Calibrator (PRC). The backbone preferentially derives from applications in three approved public datasets (GTEA, 50Salads, and Breakfast) collected for TAS tasks, which experimentally facilitates the model excavation on the CPR dataset. In general, we probe into a feasible pipeline that elevates the CPR instruction qualification via action segmentation equipped with novel deep learning techniques. Associated experiments on the CPR dataset advocate our resolution with surpassing 91.0% on Accuracy, Edit score, and F1 score.

Prompt engineering is a relatively new field of research that refers to the practice of designing, refining, and implementing prompts or instructions that guide the output of large language models (LLMs) to help in various tasks. With the emergence of LLMs, the most popular one being ChatGPT that has attracted the attention of over a 100 million users in only 2 months, artificial intelligence (AI), especially generative AI, has become accessible for the masses. This is an unprecedented paradigm shift not only because of the use of AI becoming more widespread but also due to the possible implications of LLMs in health care. As more patients and medical professionals use AI-based tools, LLMs being the most popular representatives of that group, it seems inevitable to address the challenge to improve this skill. This paper summarizes the current state of research about prompt engineering and, at the same time, aims at providing practical recommendations for the wide range of health care professionals to improve their interactions with LLMs.