Background: Traditional dietary assessment methods face limitations including reporting bias and scalability challenges. Large language models (LLMs) offer potential for automated food classification, yet their validation in morphologically complex, non-English languages like Polish remains limited. Methods: We analyzed 1992 food items from a Polish long-term care facility (LTCF) cohort using three advanced LLMs (Claude Opus 4.5, Gemini 3 pro, and GPT-5.1-chat-latest) with two prompting strategies: a structured double-step prompt integrating NOVA and World Health Organization (WHO) criteria, and a simplified single-step prompt. Classifications were compared against consensus judgments from two human experts. Results: All LLMs showed high agreement with human experts (90.3–94.2%), but there were statistically significant differences in all pairwise comparisons (χ² = 1174.5–1897.1; p < 0.001). The structured prompt produced very high Recall for UNHEALTHY items at the cost of lower Specificity, whereas the simplified prompt achieved higher overall Accuracy and a more balanced Recall–Specificity profile, indicating a trade-off between strict guideline adherence and alignment with general human judgment. Conclusions: Advanced LLMs demonstrate near-expert accuracy in Polish-language dietary classification, enhancing workflow efficiency by shifting effort toward validation. Expert oversight remains essential, and multi-model consensus alongside language-specific validation can improve AI reliability in nutrition assessment.

Background: Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). We aimed to determine the prevalence of current and past SARS-CoV-2 infections among police employees. Methods: This cross-sectional survey was undertaken among 5082 police employees from Mazowieckie Province, Poland. RT-PCR testing for current SARS-CoV-2 infection and serological tests (ELISA) for the presence of anti-SARS-CoV-2 IgM+IgA and IgG antibodies were performed. Results: All RT-PCR tests were negative. The anti-SARS-CoV-2 IgM+IgA index was positive (>8) in 8.9% of participants, including 11.2% women and 7.7% men (p < 0.001). Equivocal IgM+IgA index (6–8) was found in 9.8% of participants, including 11.9% women and 8.7% men (p < 0.001). The IgG index was positive (>6) in 4.3% and equivocal (4–6) in 13.2% of participants. A higher odds of positive IgM+IgA index was found in women vs. men (OR: 1.742) and police officers vs. civilian employees (OR: 1.411). Participants aged ≥60 years had a higher odds of positive IgG index vs. those aged 20–29 years (OR: 3.309). Daily vaping also increased the odds of positive IgG index (OR: 2.058). Conclusions: The majority of Polish police employees are seronegative for SARS-CoV-2 infection. Vaping and older age (≥60 years) were associated with a higher risk of SARS-CoV-2 infection.

Background: This study aimed to characterize sources of knowledge on the means of prevention of SARS-CoV-2 infections as well as to assess the methods of preventing SARS-CoV-2 infection among police employees in Poland and their potential impact on the risk of SARS-CoV-2 infection. Methods: The study consisted of two phases: questionnaire and laboratory tests for SARS-CoV-2 infection. The questionnaire included 30 questions related to risk factors, knowledge about SARS-CoV-2, and methods of infection prevention. Results: Data were obtained from 5082 police employees. The most common source of knowledge for a daily update on SARS-CoV-2 infection prevention was the Internet (42.6%), television (40.3%), and radio (39.7%). The most commonly used methods of SARS-CoV-2 infection included washing one’s hands for at least 20 s (95.8%), wearing facemasks (82.9%), and physical distancing (74.9%). Results of IgG tests were lower in police units where the overall compliance with the preventive measures was higher (p < 0.01). Women were more likely to exercise SARS-CoV-2 infection prevention behaviors compared to men. Compliance with the recommended protective measures increased with age. Conclusions: Lower anti-SARS-CoV-2 IgG seropositivity rates were observed in police units with better overall compliance with the preventive measures, suggesting the key importance of group rather than individual behaviors.

Background: Unhealthy food consumption in long-term care facilities (LTCFs) contributes to poor health outcomes among residents. This study aimed to assess its prevalence, identify demographic and physical risk factors, and propose targeted interventions. Methods: A mixed-methods study (2017–2021) analyzed data from 1000 Polish LTCF residents (aged 35–105 years). Anthropometric measurements, bioimpedance analyses, dietary assessments, and physical activity records were collected. Food items were classified as “healthy” or “unhealthy” using an AI-based Large Language Model (LLM), applying WHO guidelines and the NOVA classification system. Logistic regression and chi-square tests assessed associations between unhealthy food consumption and marital status, education level, mobility aid use, and portion control. Results: Unhealthy food consumption prevalence was 15.6%. Married residents had significantly higher rates than unmarried individuals (22.6% vs. 14.3%, p < 0.01). Lower educational attainment correlated with increased risk (partial primary education: 34.7% vs. tertiary education: 8.1%). Mobility aid users exhibited elevated consumption (cane: 34.6%; walker: 22.6%). Poor portion control showed the strongest association (OR = 3.2, 95% CI: 1.8–5.7). Conclusions: Marital status, educational disparities, mobility limitations, and portion control were key modifiable risk factors. Findings suggest the need for targeted nutrition programs, caregiver education, and policy reforms to improve dietary literacy and meal portioning. Future research should validate AI-based food classification methods, assess long-term intervention outcomes, and expand studies to diverse LTCF settings. These findings align with Poland’s National Health Programme and provide actionable insights for global LTCF populations.

Introduction and objective: Regular monitoring of the measles, mumps, and rubella (MMR) vaccine uptake quickly exposes immunity gaps in the population. In Poland, the first dose of the MMR vaccine is mandatory for children between 13 and 15 months of life. This study aimed to assess the uptake...

Objectives: This study aimed to identify factors influencing COVID-19 vaccination decisions and reasons for vaccine refusal among young Poles – a population with the lowest uptake in the country. Material and Methods: A nationwide cross-sectional study was conducted using the...