Explore the vast range of titles available.

Growing evidence suggests that severe acute COVID-19 illness increases the risk of long COVID (also known as post-COVID-19 condition). However, few studies have examined associations between acute symptoms and long COVID onset. This study aimed to examine associations between acute COVID-19 symptom profiles and long COVID prevalence using a population-based sample. We used a dual mode (phone and web-based) population-based probability survey of adults with polymerase chain reaction-confirmed SARS-CoV-2 between June 2020 and May 2022 in the Michigan Disease Surveillance System to examine (1) how acute COVID-19 symptoms cluster together using latent class analysis, (2) sociodemographic and clinical predictors of symptom clusters using multinomial logistic regression accounting for classification uncertainties, and (3) associations between symptom clusters and long COVID prevalence using modified Poisson regression. In our sample (n=4169), 15.9% (n=693) had long COVID, defined as new or worsening symptoms at least 90 days post SARS-CoV-2 infection. We identified 6 acute COVID-19 symptom clusters resulting from the latent class analysis, with flu-like symptoms (24.7%) and fever (23.6%) being the most prevalent in our sample, followed by nasal congestion (16.4%), multi-symptomatic (14.5%), predominance of fatigue (10.8%), and predominance of shortness of breath (10%) clusters. Long COVID prevalence was highest in the multi-symptomatic (39.7%) and predominance of shortness of breath (22.4%) clusters, followed by the flu-like symptom (15.8%), predominance of fatigue (14.5%), fever (6.4%), and nasal congestion (5.6%) clusters. After adjustment, females (vs males) had greater odds of membership in the multi-symptomatic, flu-like symptom, and predominance of fatigue clusters, while adults who were Hispanic or another race or ethnicity (vs non-Hispanic White) had greater odds of membership in the multi-symptomatic cluster. Compared with the nasal congestion cluster, the multi-symptomatic cluster had the highest prevalence of long COVID (adjusted prevalence ratio [aPR] 6.1, 95% CI 4.3-8.7), followed by the predominance of shortness of breath (aPR 3.7, 95% CI 2.5-5.5), flu-like symptom (aPR 2.8, 95% CI 1.9-4.0), and predominance of fatigue (aPR 2.2, 95% CI 1.5-3.3) clusters. Researchers and clinicians should consider acute COVID-19 symptom profiles when evaluating subsequent risk of long COVID, including potential mechanistic pathways in a research context, and proactively screen high-risk patients during the provision of clinical care.

The COVID-19 pandemic proved how sharing of genomic sequences in a timely manner, as well as early detection and surveillance of variants and characterization of their clinical impacts, helped to inform public health responses. However, the area of (re)emerging infectious diseases and our global connectivity require interdisciplinary collaborations to happen at local, national and international levels and connecting data to understand the linkages between all factors involved. Here, we describe experiences and lessons learned from a COVID-19 pilot study aimed at developing a model for storage and sharing linked laboratory data and clinical-epidemiological data using European open science infrastructure. We provide insights into the barriers and complexities of internationally sharing linked, complex cohort datasets from opportunistic studies for connected data analyses. An analytical timeline of events, describing key actions and delays in the execution of the pilot, and a critical path, defining steps in the process of internationally sharing a linked cohort dataset are included. The pilot showed how building on existing infrastructure that had previously been developed within the European Nucleotide Archive at the European Molecular Biology Laboratory-European Bioinformatics Institute for pathogen genomics data sharing, allowed the rapid development of connected \"data hubs.\" These data hubs were required to link human clinical-epidemiological data under controlled access with open high dimensional laboratory data, under FAIR (Findable, Accessible, Interoperable, Reusable) principles. Based on our own experiences, we call for action and make recommendations to support and to improve data sharing for outbreak preparedness and response.

Our study demonstrated the ability of ChatGPT-4 to answer 77.5% of all sampled text-based board review type questions correctly. Questions requiring the recall of factual information were answered correctly most often, with slight decreases in correctness as higher-order thinking requirements increased. Improvements to ChatGPT’s visual diagnostics capabilities will be required before it can be used reliably for clinical decision-making and visual diagnostics.

The use of artificial intelligence (AI) in health care has significant implications for patient-clinician interactions. Practical and ethical challenges have emerged with the adoption of large language models (LLMs) that respond to prompts from clinicians, patients, and caregivers. With an emphasis on patient experience, this paper examines the potential of LLMs to act as facilitators, interrupters, or both in patient-clinician relationships. Drawing on our experiences as patient advocates, computer scientists, and physician informaticists working to improve data exchange and patient experience, we examine how LLMs might enhance patient engagement, support triage, and inform clinical decision-making. While affirming LLMs as a tool enabling the rise of the “AI patient,” we also explore concerns surrounding data privacy, algorithmic bias, moral injury, and the erosion of human connection. To help navigate these tensions, we outline a conceptual framework that anticipates the role and impact of LLMs in patient-clinician dynamics and propose key areas for future inquiry. Realizing the potential of LLMs requires careful consideration of which aspects of the patient-clinician relationship must remain distinctly human and why, even when LLMs offer plausible substitutes. This inquiry should draw on ethics and philosophy, aligned with AI imperatives such as patient-centered design and transparency, and shaped through collaboration between technologists, health care providers, and patient communities.

Generative artificial intelligence (AI)-particularly large language models (LLMs)-has generated unprecedented interest in applications ranging from everyday questions and answers to health-related inquiries. However, little is known about how everyday users decide whether to trust and adopt these technologies in high-stakes contexts such as personal health. This study examines how ease of use, perceived usefulness, and risk perception interact to shape user trust in and intentions to adopt DeepSeek, an emerging LLM-based platform, for health care purposes. We adapted survey items from validated technology acceptance scales to assess user perception of DeepSeek. A 12-item Likert scale questionnaire was developed and pilot-tested (n=20). It was then distributed on the web to users in India, the United Kingdom, and the United States who had used DeepSeek within the past 2 weeks. Data analysis involved descriptive frequency assessments and Partial Least Squares Structural Equation Modeling. The model assessed direct and indirect effects, including potential quadratic relationships. A total of 556 complete responses were collected, with respondents almost evenly split across India (n=184), the United Kingdom (n=185), and the United States (n=187). Regarding AI in health care, when asked whether they were comfortable with their health care provider using AI tools, 59.3% (n=330) were fine with AI use provided their doctor verified its output, and 31.5% (n=175) were enthusiastic about its use without conditions. DeepSeek was used primarily for academic and educational purposes, 50.7% (n=282) used DeepSeek as a search engine, and 47.7% (n=265) used it for health-related queries. When asked about their intent to adopt DeepSeek over other LLMs such as ChatGPT, 52.1% (n=290) were likely to switch, and 28.9% (n=161) were very likely to do so. The study revealed that trust plays a pivotal mediating role; ease of use exerts a significant indirect impact on usage intentions through trust. At the same time, perceived usefulness contributes to trust development and direct adoption. By contrast, risk perception negatively affects usage intent, emphasizing the importance of robust data governance and transparency. Significant nonlinear paths were observed for ease of use and risk, indicating threshold or plateau effects. Users are receptive to DeepSeek when it is easy to use, useful, and trustworthy. The model highlights trust as a mediator and shows nonlinear dynamics shaping AI-driven health care tool adoption. Expanding the model with mediators such as privacy and cultural differences could provide deeper insights. Longitudinal experimental designs could establish causality. Further investigation into threshold and plateau phenomena could refine our understanding of user perceptions as they become more familiar with AI-driven health care tools.

Traditional Chinese Medicine (TCM) emphasizes the concept of medicine food homology (MFH), which integrates dietary therapy into health care. However, the practical application of MFH principles relies heavily on expert knowledge and manual interpretation, posing challenges for automating MFH-based dietary recommendations. Although large language models (LLMs) have shown potential in health care decision support, their performance in specialized domains such as TCM is often hindered by hallucinations and a lack of domain knowledge. The integration of uncertain knowledge graphs (UKGs) with LLMs via retrieval-augmented generation (RAG) offers a promising solution to overcome these limitations by enabling a structured and faithful representation of MFH principles while enhancing LLMs' ability to understand the inherent uncertainty and heterogeneity of TCM knowledge. Consequently, it holds potential to improve the reliability and accuracy of MFH-based dietary recommendations generated by LLMs. This study aimed to introduce Yaoshi-RAG, a framework that leverages UKGs to enhance LLMs' capabilities in generating accurate and personalized MFH-based dietary recommendations. The proposed framework began by constructing a comprehensive MFH knowledge graph (KG) through LLM-driven open information extraction, which extracted structured knowledge from multiple sources. To address the incompleteness and uncertainty within the MFH KG, UKG reasoning was used to measure the confidence of existing triples and to complete missing triples. When processing user queries, query entities were identified and linked to the MFH KG, enabling retrieval of relevant reasoning paths. These reasoning paths were then ranked based on triple confidence scores and entity importance. Finally, the most informative reasoning paths were encoded into prompts using prompt engineering, enabling the LLM to generate personalized dietary recommendations that aligned with both individual health needs and MFH principles. The effectiveness of Yaoshi-RAG was evaluated through both automated metrics and human evaluation. The constructed MFH KG comprised 24,984 entities, 22 relations, and 29,292 triples. Extensive experiments demonstrate the superiority of Yaoshi-RAG in different evaluation metrics. Integrating the MFH KG significantly improved the performance of LLMs, yielding an average increase of 14.5% in Hits@1 and 8.7% in F1-score, respectively. Among the evaluated LLMs, DeepSeek-R1 achieved the best performance, with 84.2% in Hits@1 and 71.5% in F1-score, respectively. Human evaluation further validated these results, confirming that Yaoshi-RAG consistently outperformed baseline models across all assessed quality dimensions. This study shows Yaoshi-RAG, a new framework that enhances LLMs' capabilities in generating MFH-based dietary recommendations through the knowledge retrieved from a UKG. By constructing a comprehensive TCM knowledge representation, our framework effectively extracts and uses MFH principles. Experimental results demonstrate the effectiveness of our framework in synthesizing traditional wisdom with advanced language models, facilitating personalized dietary recommendations that address individual health conditions while providing evidence-based explanations.

The impact of the COVID-19 pandemic has primarily been studied in the context of language delays or developmental disorders in infants and children. However, the effects on young adults have received less attention. COVID-19 not only affects physical health but also cognitive and language functions, which is an emerging area of research. While previous studies have focused on developmental stages, the effects of COVID-19 on the language abilities of healthy young adults remain underexplored. This study aimed to investigate the impact of COVID-19 on the spoken language, particularly in story retelling and working memory, in young adults. This study aimed to investigate the effects of COVID-19 on memory-based story retelling and verbal working memory in young adults. Specifically, it examined whether there were group differences in story retelling and working memory performance between individuals with and those without a history of COVID-19, and whether verbal working memory predicted story retelling outcomes. The study involved 79 young adult participants, of whom 39 were in the non-COVID-19 group and 40 were in the COVID-19 group. Participants completed the Story Retelling Procedure (SRP) and a verbal working memory task. Story retelling performance was quantified using information units per minute (IUs/min), a measure of informativeness in story retelling. Working memory was assessed using the Alphabet Span Test. Participants with COVID-19 produced fewer information units per minute (mean 0.53, SD 0.21) than those without COVID-19 (mean 0.63, SD 0.24; P=.049). No significant group differences were found in verbal working memory performance (P=.20). However, regression analysis showed that verbal working memory significantly predicted story retelling performance (R²=.064, P=.02), suggesting that individual differences in working memory capacity may contribute to discourse informativeness, regardless of COVID-19 history. Young adults with a history of COVID-19 exhibited reduced story retelling performance compared to those without a history of infection. In contrast, no significant differences were observed in verbal working memory performance between groups. Furthermore, verbal working memory scores significantly predicted story retelling performance, suggesting a functional link between these cognitive-linguistic domains. These findings suggest that story retelling performance may serve as a sensitive indicator of post-COVID-19 cognitive-linguistic changes in young adults.

The imperative arises to study the impact of socioeconomic factors on the acceptance of SARS-CoV-2 and influenza vaccines amid changes in immunization policies during the COVID-19 pandemic. To enhance targeted public health strategies and improve age-specific policies based on identified risk factors, this study investigated the associations between sociodemographic factors and vaccination behaviors during the COVID-19 pandemic, with emphasis on age-specific vaccine cost policies. This study analyzed data from the Korean Community Health Survey 2019-2022 with 507,964 participants to investigate the impact of age-specific policies on vaccination behaviors during the pandemic period. Cohorts aged 19-64 years and 65 years or older were stratified based on age (years), sociodemographic factors, and health indicators. The cohorts were investigated to assess the influence of relevant risk factors on vaccine acceptance under the pandemic by using weighted odds ratio and ratio of odds ratio (ROR). Among 507,964 participants, the acceptance of the SARS-CoV-2 vaccine (COVID-19 vaccine) was higher among individuals with factors possibly indicating higher socioeconomic status, such as higher education level (age 19-64 years: ROR 1.34; 95% CI 1.27-1.40 and age ≥65 years: ROR 1.19; 95% CI 1.01-1.41) and higher income (age 19-64 years: ROR 1.67; 95% CI 1.58-1.76 and age ≥65 years: ROR 1.21; 95% CI 1.06-1.38) for both age cohorts compared to influenza vaccine acceptance before the pandemic. In the context of influenza vaccination during the pandemic, the older cohort exhibited vaccine hesitancy associated with health care mobility factors such as lower general health status (ROR 0.89; 95% CI 0.81-0.97). SARS-CoV-2 vaccination strategies should focus on reducing hesitancy among individuals with lower social participation. To improve influenza vaccine acceptance during the pandemic, strategies for the younger cohort should focus on individuals with lower social participation, while efforts for the older cohort should prioritize individuals with limited access to health care services.

The universal availability of smartphones has created new opportunities for innovative telemedicine applications in health care. The COVID-19 pandemic has heightened the demand for contactless health care services, making SARS-CoV-2 polymerase chain reaction (PCR) testing a crucial component of pandemic containment. This feasibility study aimed to examine a comprehensive telemedicine approach for SARS-CoV-2 testing, focusing on the practicality, user satisfaction, and economic implications of self-sampling guided by a telemedicine platform. The study process involved shipping self-sampling kits, providing instructions for at-home sample collection, processing biomaterials (swabs and capillary blood), communicating test results, and providing interoperable data for clinical routine and research through a medical mobile app. A total of 100 individuals were randomly assigned to either the conventional health care professional (HCP)-performed SARS-CoV-2 testing group (conventional testing group, CG) or the telemedicine-guided SARS-CoV-2 self-sampling approach (telemedicine group, TG). Feasibility of the TG approach, user satisfaction, user-centered outcomes, and economic aspects were assessed and compared between the groups. In the TG group, 47 out of 49 (95%) individuals received a self-sampling kit via mail, and 37out of 49 (76%) individuals successfully returned at least one sample for diagnostics. SARS-CoV-2 PCR tests were conducted in 95% (35/37) of TG cases compared with 88% (44/50) in the CG. Users in the TG reported high satisfaction levels with ease of use (5.2/7), interface satisfaction (5.2/7), and usefulness (4.3/7). A microcosting model indicated a slightly higher cost for the TG approach than the CG approach. The TG demonstrated the potential to facilitate interoperable data transmission by providing anonymized, standardized datasets for extraction using Health Level 7-Fast Healthcare Interoperability Resources. This supports the national COVID-19 Data Exchange Platform and facilitates epidemiological evaluation based on the German COVID Consensus dataset. These preliminary findings suggest that a telemedicine-based approach to SARS-CoV-2 testing is feasible and could be integrated into existing hospital data infrastructures. This model has the potential for broader application in medical care, offering a scalable solution that could improve user satisfaction and treatment quality in the future.

Health care practitioners use clinical decision support systems (CDSS) as an aid in the crucial task of clinical reasoning and decision-making. Traditional CDSS are online repositories (ORs) and clinical practice guidelines (CPG). Recently, large language models (LLMs) such as ChatGPT have emerged as potential alternatives. They have proven to be powerful, innovative tools, yet they are not devoid of worrisome risks. This study aims to explore how medical students perform in an evaluated clinical case through the use of different CDSS tools. The authors randomly divided medical students into 3 groups, CPG, n=6 (38%); OR, n=5 (31%); and ChatGPT, n=5 (31%); and assigned each group a different type of CDSS for guidance in answering prespecified questions, assessing how students' speed and ability at resolving the same clinical case varied accordingly. External reviewers evaluated all answers based on accuracy and completeness metrics (score: 1-5). The authors analyzed and categorized group scores according to the skill investigated: differential diagnosis, diagnostic workup, and clinical decision-making. Answering time showed a trend for the ChatGPT group to be the fastest. The mean scores for completeness were as follows: CPG 4.0, OR 3.7, and ChatGPT 3.8 (P=.49). The mean scores for accuracy were as follows: CPG 4.0, OR 3.3, and ChatGPT 3.7 (P=.02). Aggregating scores according to the 3 students' skill domains, trends in differences among the groups emerge more clearly, with the CPG group that performed best in nearly all domains and maintained almost perfect alignment between its completeness and accuracy. This hands-on session provided valuable insights into the potential perks and associated pitfalls of LLMs in medical education and practice. It suggested the critical need to include teachings in medical degree courses on how to properly take advantage of LLMs, as the potential for misuse is evident and real.