Background: Artificial intelligence (AI) is increasingly shaping medical education through adaptive learning systems, simulations, and large language models. These tools can enhance knowledge retention, clinical reasoning, and feedback, while raising concerns related to equity, bias, and institutional readiness. Methods: This narrative review examined AI applications in medical and health-profession education. A structured search of PubMed, Scopus, and Web of Science (2010–October 2025), supplemented by grey literature, identified empirical studies, reviews, and policy documents addressing AI-supported instruction, simulation, communication, procedural skills, assessment, or faculty development. Non-educational clinical AI studies were excluded. Results: AI facilitates personalized and interactive learning, improving clinical reasoning, communication practice, and simulation-based training. However, linguistic bias in Natural language processing (NLP) tools may disadvantage non-native English speakers, and limited digital infrastructure hinders adoption in rural or low-resource settings. When designed inclusively, AI can amplify accessibility for learners with disabilities. Faculty and students commonly report low confidence and infrequent use of AI tools, yet most support structured training to build competence. Conclusions: AI can shift medical education toward more adaptive, learner-centered models. Effective adoption requires addressing bias, ensuring equitable access, strengthening infrastructure, and supporting faculty development. Clear governance policies are essential for safe and ethical integration.

Atrial fibrillation (AF) is a common cardiac arrhythmia linked to an increased risk of stroke, heart failure, and mortality, yet its diagnosis remains challenging due to its intermittent and often asymptomatic nature. Traditional methods, such as standard electrocardiography (ECG) and prolonged cardiac monitoring, have limitations in terms of cost, accessibility, and diagnostic yield. Artificial intelligence (AI), particularly machine learning (ML) and deep learning, has emerged as a promising tool for AF detection and prediction by analyzing ECG data with high accuracy. AI models can identify subtle patterns in ECG signals that may indicate AF, even when the arrhythmia is not actively present, improving early diagnosis and risk stratification. Additionally, AI-powered ECG analysis has been integrated into wearable and mobile health devices, expanding screening capabilities beyond clinical settings. While studies have demonstrated AI’s effectiveness, challenges such as data bias, model reliability across diverse populations, and regulatory considerations must be addressed before widespread clinical adoption. If these obstacles are overcome, AI has the potential to revolutionize AF management by enabling earlier detection, reducing the need for resource-intensive monitoring, and improving patient outcomes.

The aim of this study was to assess the impact of the national government initiative Emergency Severity Index version 4.0 validated triage training on triage practitioners' knowledge and accuracy. This pre/post intervention study evaluated the knowledge of triage practitioners, who constituted 30% of employees trained by the national program, in 74 emergency departments across Poland in 2020. Statistical analysis was used to evaluate the impact of the triage training. No significant differences in triage knowledge were found based on experience, length of ED service, or previous training. Training resulted in increased accuracy (61.3% vs 81.1%) and decreased overtriage and undertriage. Participants significantly reduced errors and improved Emergency Severity Index guideline-based case evaluations, especially for Emergency Severity Index 1-3 cases, with the most notable improvements observed among those without prior triage experience. The training significantly improved interrater reliability. The Emergency Severity Index pilot training demonstrated a significant improvement in the accuracy of triage practitioners. Emergency Severity Index level 4 has been identified as a challenging area to learn, as well as yielding promising results in the acquisition of knowledge across levels 1 and 2, among less experienced practitioners.

Objective Out-of-hospital cardiac arrest (OHCA) has low survival rates with worse outcomes at night due to delayed emergency medical services (EMS) response, resource limitations and workforce fatigue. Since randomised trials are unfeasible, all-comers registries provide essential data to bridge evidence gaps and improve EMS protocols. Design Retrospective observational study using propensity score matching. Setting National EMS registry and death registry data from Poland, cases from September to November 2022. Participants Of 2388 eligible patients, cases were grouped by time of cardiac arrest (on-hours: 7:00–18:59; off-hours: 7:00–18:59 AM) and matched 1:1 using propensity scores, yielding 1194 pairs. Primary and secondary outcome measures Primary: return of spontaneous circulation (ROSC) and 30-day survival. Secondary: EMS response time. Results Our findings revealed significant disparities in OHCA outcomes between day and night shifts. ROSC rates were notably lower at night (20.9% vs 34.8%; p=0.01); however, no difference in 30-day survival was observed (8.3% vs 8.1%; p=0.94). Furthermore, EMS response times were significantly longer during nighttime hours (median and IQR): 12.4 (7.4–14.6) versus 11.2 (6.2–13.5) (minutes); p=0.01. Conclusions Patients with OHCA during off-hours experienced longer EMS response times and significantly lower rates of ROSC as compared with daytime hours. No difference in 30-day survival was observed between groups. Potential contributors include reduced staffing, fatigue and logistical delays. System-level changes in EMS scheduling and workforce planning might help to reduce time-of-day-related disparities in OHCA outcomes. Trial registration number Clinical Trials ID: NCT03130088; Post results

INTRODUCTION: Out-of-hospital cardiac arrest (OHCA) remains a significant public health challenge. This study aimed to assess impact of bystander and dispatcher interventions on survival outcomes in OHCA cases in Poland using data from the European Registry of Cardiac Arrest (EuReCa). MATERIAL AND METHODS: A retrospective analysis was conducted on 8,253 patients included in the EuReCa between 2014 and 2022. The data was collected from emergency medical team reports, and survival outcomes at 30 days were obtained from the national death registry. RESULTS: A gradual increase in CPR attempted by EMS or bystander, as well as CPR performed with the support of a dispatcher, was observed throughout consecutive years. Dispatcher-guided resuscitation was linked with increased return of spontaneous circulation (ROSC) (22.1% vs 30.6%; P =0.01). Patients treated with implementation of telephone-assisted cardiopulmonary resuscitation were associated with a higher prevalence of ROSC (21.0% vs. 27.4%; P =0.01). CONCLUSIONS: Dispatcher and bystander interventions significantly improve immediate outcomes in OHCA. However, long-term survival seems to not be improved. System-level strategies to increase AED accessibility, implement real-time support, and standardize Utstein-based reporting in Poland are crucial to increase survival and enable international comparisons.

Objective: Out-of-hospital cardiac arrest (OHCA) has low survival rates with worse outcomes at night due to delayed emergency medical services (EMS) response, resource limitations, and workforce fatigue. Timely resuscitation is crucial, but logistical challenges exacerbate disparities. Since randomized trials are unfeasible, all-comers registries provide essential data to bridge evidence gaps and improve EMS protocols. This study aimed to investigate the impact of day versus night shifts on OHCA outcomes, focusing on ROSC rates, 30-day survival, and timing metrics within EMS operations. Methods: This study analyzed OHCA cases in Poland from September to November 2022 using paramedics records and national death registry data. Patients were grouped by time of cardiac arrest (on-hours: 7:00 AM–6:59 PM; off-hours: 7:00 PM–6:59 AM) and matched 1:1 using propensity score analysis (1194 pairs). Results: Our findings revealed significant disparities in OHCA outcomes between day and night shifts. ROSC rates were notably lower at night (20.9% vs. 34.8%; P = 0.01 ), as was 30-day survival (47.0% vs. 59.3%; P = 0.01 ). EMS response times were significantly longer during nighttime hours (median and interquartile range: 12.4(7.4-14.6) vs. 11.2(6.2-13.5)(minutes); P = 0.01 ) Conclusions: Patients with OHCA during off-hours were exposed to longer EMS response time as compared to procedures conducted during regular working hours. Furthermore, OHCA during night shift might be associated with a lower rate of ROSC and decreased 30-day survival What’s New?: Out-of-hospital cardiac arrest (OHCA) remains a critical public health challenge with significant implications for morbidity and mortality. Despite advancements in emergency medical services systems and resuscitation techniques, survival rates following OHCA remain low, particularly during nighttime hours. This study provided a clinical view from a national perspective on the impact of day versus night shifts on the clinical outcomes in patients with OHCA. Propensity score match analysis was performed to evade risk of bias in the preselection process. This study suggested detrimental outcome in OHCA treatment during nighttime as compared to regular working hours. Patients from nighttime group were associated with longer response times as well as decreased rate of return of spontaneous circulation and 30-day survival as compared to daytime. These findings underscore the importance of systemic approach to improve OHCA outcome.