Utilizing large language models in infectious disease transmission modelling for public health preparedness.

Introduction: OpenAI's ChatGPT, a Large Language Model (LLM), is a powerful tool across domains, designed for text and code generation, fostering collaboration, especially in public health. Investigating the role of this advanced LLM chatbot in assisting public health practitioners in shaping disease transmission models to inform infection control strategies, marks a new era in infectious disease epidemiology research. This study used a case study to illustrate how ChatGPT collaborates with a public health practitioner in co-designing a mathematical transmission model. Methods: Using natural conversation, the practitioner initiated a dialogue involving an iterative process of code generation, refinement, and debugging with ChatGPT to develop a model to fit 10 days of prevalence data to estimate two key epidemiological parameters: i) basic reproductive number (Ro) and ii) final epidemic size. Verification and validation processes are conducted to ensure the accuracy and functionality of the final model. Results: ChatGPT developed a validated transmission model which replicated the epidemic curve and gave estimates of Ro of 4.19 (95 % CI: 4.13- 4.26) and a final epidemic size of 98.3 % of the population within 60 days. It highlighted the advantages of using maximum likelihood estimation with Poisson distribution over least squares method. Conclusion: Integration of LLM in medical research accelerates model development, reducing technical barriers for health practitioners, democratizing access to advanced modeling and potentially enhancing pandemic preparedness globally, particularly in resource-constrained populations.

Visual narratives in nursing education: A generative artificial intelligence approach.

AIM: The aim of this paper is to investigate the incorporation of visual narratives, such as comics and graphics, into nursing education using Generative Artificial Intelligence (GAI) models like DALL-E. BACKGROUND: Visual narratives serve as a powerful method for communicating intricate concepts in nursing education. Despite their advantages, challenges in creating effective educational comics persist due to the need for expertise in graphic design and the associated time and resource constraints. DESIGN: This study examines existing literature that highlights the efficacy of visual narratives in education and demonstrates the potential of GAI models, specifically DALL-E, in creating visual narratives for nursing education. METHODS: We analyze the potential of GAI models, specifically DALL-E, to create visual narratives for educational purposes. This was demonstrated through illustrative examples addressing sensitive topics, illustrating research methodology and designing recruitment posters for clinical trials. Additionally, we discussed the necessity of reviewing and editing the text generated by DALL-E to ensure its accuracy and relevance in educational contexts. The method also considered legal concerns related to copyright and ownership of the generated content, highlighting the evolving legal landscape in this domain. RESULTS: The study found that GAI, specifically DALL-E, has significant potential to bridge the gap in creating visual narratives for nursing education. While offering cost-effectiveness and accessibility, GAI tools require careful consideration of challenges such as text-related errors, misinterpretation of user prompts and legal concerns. CONCLUSIONS: GAI models like DALL-E offer promising solutions for enhancing visual storytelling in nursing education. However, their effective integration requires a collaborative approach, where educators engage with these tools as co-pilots, leveraging their capabilities while mitigating potential drawbacks. By doing so, educators can harness the full potential of GAI to enrich the educational experience for learners through compelling visual narratives.

Comparative analysis of symptom profile and risk of death associated with infection by SARS-CoV-2 and its variants in Hong Kong.

The recurrent multiwave nature of coronavirus disease 2019 (COVID-19) necessitates updating its symptomatology. We characterize the effect of variants on symptom presentation, identify the symptoms predictive and protective of death, and quantify the effect of vaccination on symptom development. With the COVID-19 cases reported up to August 25, 2022 in Hong Kong, an iterative multitier text-matching algorithm was developed to identify symptoms from free text. Multivariate regression was used to measure associations between variants, symptom development, death, and vaccination status. A least absolute shrinkage and selection operator technique was used to identify a parsimonious set of symptoms jointly associated with death. Overall, 70.9% (54 450/76 762) of cases were symptomatic with 102 symptoms identified. Intrinsically, the wild-type and delta variant caused similar symptoms among unvaccinated symptomatic cases, whereas the wild-type and omicron BA.2 subvariant had heterogeneous patterns, with seven symptoms (fatigue, fever, chest pain, runny nose, sputum production, nausea/vomiting, and sore throat) more frequent in the BA.2 cohort. With ≥2 vaccine doses, BA.2 was more likely than delta to cause fever among symptomatic cases. Fever, blocked nose, pneumonia, and shortness of breath remained jointly predictive of death among unvaccinated symptomatic elderly in the wild-type-to-omicron transition. Number of vaccine doses required for reducing occurrence varied by symptoms. We substantiate that omicron has a different clinical presentation compared to previous variants. Syndromic surveillance can be bettered with reduced reliance on symptom-based case identification, increased weighing on symptoms predictive of death in outcome prediction, individual-based risk assessment in care homes, and incorporating free-text symptom reporting.

Transforming nursing with large language models: from concept to practice.

Large language models (LLMs) such as ChatGPT have emerged as potential game-changers in nursing, aiding in patient education, diagnostic assistance, treatment recommendations, and administrative task efficiency. While these advancements signal promising strides in healthcare, integrated LLMs are not without challenges, particularly artificial intelligence hallucination and data privacy concerns. Methodologies such as prompt engineering, temperature adjustments, model fine-tuning, and local deployment are proposed to refine the accuracy of LLMs and ensure data security. While LLMs offer transformative potential, it is imperative to acknowledge that they cannot substitute the intricate expertise of human professionals in the clinical field, advocating for a synergistic approach in patient care.

Temporal variations of vaccine hesitancy amid the COVID-19 outbreaks in Hong Kong.

To inform the dynamic adjustments of vaccination campaigns, this study examined the transitions among vaccine hesitancy profiles over the COVID-19 pandemic progression and their predictors and outcomes. The transition patterns among hesitancy profiles over three periods were identified using a latent transition analysis with individuals from a longitudinal cohort study since the emergence of COVID-19 in Hong Kong. Four profiles (i.e., skeptics, apathetics, fence-sitters, and believers) emerged consistently over time. From Period 1 (third and fourth pandemic waves) to Period 2 (dormant period, vaccine rollout), 14.17% of believers became fence-sitters (ambivalization), and 12.11% of fence-sitters became apathetics (apathetization). From Period 2 to Period 3 (omicron surge and vaccine mandates), 20.21% of believers became fence-sitters. Lower trust in government predicted a transition to skepticism, whereas higher trust predicted the opposite. Staying as believers was associated with decreased hygienic and social distancing behavior. The stable hesitancy profiles amid the rapid vaccine uptake suggest that structural factors rather than personal agency may drive the surge. Ambivalization and apathetization may signal disengagement in preventive behaviors. Trust in the government is crucial in the pandemic response. Public health interventions may improve compliance with guidelines and prevent skepticism and apathy.

The importance of transparency: Declaring the use of generative artificial intelligence (AI) in academic writing.

The integration of generative artificial intelligence (AI) into academic research writing has revolutionized the field, offering powerful tools like ChatGPT and Bard to aid researchers in content generation and idea enhancement. We explore the current state of transparency regarding generative AI use in nursing academic research journals, emphasizing the need for explicitly declaring the use of generative AI by authors in the manuscript. Out of 125 nursing studies journals, 37.6% required explicit statements about generative AI use in their authors' guidelines. No significant differences in impact factors or journal categories were found between journals with and without such requirement. A similar evaluation of medicine, general and internal journals showed a lower percentage (14.5%) including the information about generative AI usage. Declaring generative AI tool usage is crucial for maintaining the transparency and credibility in academic writing. Additionally, extending the requirement for AI usage declarations to journal reviewers can enhance the quality of peer review and combat predatory journals in the academic publishing landscape. Our study highlights the need for active participation from nursing researchers in discussions surrounding standardization of generative AI declaration in academic research writing.

Extracting symptoms from free-text responses using ChatGPT among COVID-19 cases in Hong Kong.

OBJECTIVES: To investigate the feasibility and performance of Chat Generative Pretrained Transformer (ChatGPT) in converting symptom narratives into structured symptom labels. METHODS: We extracted symptoms from 300 deidentified symptom narratives of COVID-19 patients by a computer-based matching algorithm (the standard), and prompt engineering in ChatGPT. Common symptoms were those with a prevalence >10% according to the standard, and similarly less common symptoms were those with a prevalence of 2-10%. The precision of ChatGPT was compared with the standard using sensitivity and specificity with 95% exact binomial CIs (95% binCIs). In ChatGPT, we prompted without examples (zero-shot prompting) and with examples (few-shot prompting). RESULTS: In zero-shot prompting, GPT-4 achieved high specificity (0.947 [95% binCI: 0.894-0.978]-1.000 [95% binCI: 0.965-0.988, 1.000]) for all symptoms, high sensitivity for common symptoms (0.853 [95% binCI: 0.689-0.950]-1.000 [95% binCI: 0.951-1.000]), and moderate sensitivity for less common symptoms (0.200 [95% binCI: 0.043-0.481]-1.000 [95% binCI: 0.590-0.815, 1.000]). Few-shot prompting increased the sensitivity and specificity. GPT-4 outperformed GPT-3.5 in response accuracy and consistent labelling. DISCUSSION: This work substantiates ChatGPT's role as a research tool in medical fields. Its performance in converting symptom narratives to structured symptom labels was encouraging, saving time and effort in compiling the task-specific training data. It potentially accelerates free-text data compilation and synthesis in future disease outbreaks and improves the accuracy of symptom checkers. Focused prompt training addressing ambiguous descriptions impacts medical research positively.

Revisiting Vaccine Hesitancy in Residential Care Homes for the Elderly for Pandemic Preparedness: A Lesson from COVID-19.

Residents in residential care homes for the elderly (RCHEs) are at high risk of severe illnesses and mortality, while staff have high exposure to intimate care activities. Addressing vaccine hesitancy is crucial to safeguard vaccine uptake in this vulnerable setting, especially amid a pandemic. In response to this, we conducted a cross-sectional survey to measure the level of vaccine hesitancy and to examine its associated factors among residents and staff in RCHEs in Hong Kong. We recruited residents and staff from 31 RCHEs in July-November 2022. Of 204 residents, 9.8% had a higher level of vaccine hesitancy (scored ≥ 4 out of 7, mean = 2.44). Around 7% of the staff (n = 168) showed higher vaccine hesitancy (mean = 2.45). From multi-level regression analyses, higher social loneliness, higher anxiety, poorer cognitive ability, being vaccinated with fewer doses, and lower institutional vaccination rates predicted residents' vaccine hesitancy. Similarly, higher emotional loneliness, higher anxiety, being vaccinated with fewer doses, and working in larger RCHEs predicted staff's vaccine hesitancy. Although the reliance on self-report data and convenience sampling may hamper the generalizability of the results, this study highlighted the importance of addressing the loneliness of residents and staff in RCHEs to combat vaccine hesitancy. Innovative and technology-aided interventions are needed to build social support and ensure social interactions among the residents and staff, especially amid outbreaks.

Nursing education in the age of artificial intelligence powered Chatbots (AI-Chatbots): Are we ready yet?

This article discusses the challenges and implications of artificial intelligence powered chatbot (AI-Chatbots) in nursing education. Chat Generative Pre-trained Transformer (ChatGPT) is an AI-Chatbot that can engage in detailed dialog and pass qualification tests in various fields. It can be applied for drafting course materials and administrative paperwork. Students can use it for personalized self-paced learning. AI-Chatbot technology can be applied in problem-based learning for hands-on practice experiences. There are concerns about over-reliance on the technology, including issues with plagiarism and limiting critical thinking skills. Educators must provide clear guidelines on appropriate use and emphasize the importance of critical thinking and proper citation. Educators must proactively adjust their curricula and pedagogy. AI-Chatbot technology could transform the nursing profession by aiding and streamlining administrative tasks, allowing nurses to focus on patient care. The use of AI-Chatbots to socially assist patients and for therapeutic purposes in mental health shows promise in improving well-being of patients, and potentially easing shortage and burnout for healthcare workers. AI-Chatbots can help nursing students and researchers to overcome technical barriers in nursing informatics, increasing accessibility for individuals without technical background. AI-Chatbot technology has potential in easing tasks for nurses, improving patient care, and enhancing nursing education.