Oh, Hölzer et al., discuss the multidisciplinary approach used for monitoring the genomic and virological evolution of SARS-CoV-2 during the COVID-19 pandemic and its implications on public health in Germany. They emphasize the need for continuous surveillance and adaptation of public health strategies to address evolving viral threats.

Christof & Armoundas explore how large language models (LLMs) can augment clinician-level clinical reasoning across the three pillars-framing the encounter, diagnostic reasoning, and treatment/management-highlighting gains in information synthesis and pattern recognition while underscoring limits that require continuous human judgment and oversight. They advocate a bias-aware, privacy-preserving, and rigorously validated “human-in-the-loop” deployment that safeguards patient agency and clinical accountability, while integrating LLMs into real-world workflows via clear clinician imperatives.

Negussie et al. explore how cardiac MRI, though underutilized in Sub-Saharan Africa, could improve congenital heart disease diagnosis through AI-driven advancements. Key barriers are highlighted and targeted solutions proposed to enhance access, accuracy, and equity in cardiac imaging across the region.

Giesen et al. review multi-omics and systems-biology approaches to investigate how preeclampsia disrupts maternal haemodynamics, drives early life-adversity and influences cardiovascular risk in mothers and their offspring. They identify underlying molecular mechanisms and candidate biomarkers that may inform personalised medicine frameworks.

Sennersten et al. present a scoping review examining how the Russo-Ukrainian War disrupts healthcare for children, worsening access and mental health. Findings highlight research and policy needs to protect paediatric health during conflict.

Song et al. develop a wearable ultrasound system that automatically quantifies diaphragm movement in intercostal and subcostal views. This technique analyzes respiratory mechanics and accurately estimates cough strength, highlighting its potential as a standard practice in the intensive care unit.

Ward-Caviness et al. use a time-stratified case-crossover approach to estimate associations between PM2.5 and COVID19-related hospitalizations across the US. Higher concentrations of PM2.5 are associated with higher risk of COVID19-related hospitalizations, with heterogeneity seen across regions.

Liu, Gao et al. develop EmoScan, an LLM-based system to screen for emotional disorders. Findings reveal that EmoScan effectively screens for emotional disorders with high accuracy and can provide detailed explanations, enhancing transparency and trust in automated mental health assessments.

Zhang, Yi et al. examine if the brain age gap (BAG), compared to chronological aging, can accurately predict the risk for cognitive decline, neuropsychiatric disorders, and mortality. Findings reveal BAG can be used for clinical risk stratification and that healthier lifestyle interventions significantly reduce accelerated brain aging.

With this cross-journal Collection, the editors at Communications Medicine, Nature Communications, and Scientific Reports invite manuscripts that highlight ...

Meine, McPherson et al. assess risk and resilience factors in Swiss medical interns predicting skills improvement, burnout, wellbeing and career motivation. Based on quantitative and qualitative analyses, three important factors emerge: work dissatisfaction, social and team factors and degree of practical involvement.

Grieger, Takele, Vesco, et al. perform a systematic review and meta-analysis of gestational weight gain interventions. Findings indicate lifestyle interventions that reduce excessive gestational weight gain provide greater benefits for women with a normal BMI and higher HDL cholesterol levels at the initiation of interventions.

Harre et al. analyze serum lipids from patients with NSCLC and test how cholesterol- or ω−3 PUFA–enriched diets affect tumor growth and immunity in mouse models, with or without PD-1 therapy. They find that cholesterol drives tumor progression and immune suppression, while ω−3 PUFAs reduce tumor burden and improve PD-1 efficacy

mlHsu et al. examine the effectiveness of Angiotensin Receptor-Neprilysin Inhibitors (ARNI) in individuals with Chronic Obstructive Pulmonary Disease (COPD) and heart failure. Findings reveal that ARNI treatment in people with both COPD and HF may lower the risk of COPD exacerbations, respiratory failure, and respiratory tract infections.

Zhang, Huang et al. introduce mCODEGPT, a zero-shot framework that extracts named entities as structured data from clinical notes of cancer patients using Large Language Models. Their hierarchical prompt engineering approach enables accuracy information extraction without relying on expert-labelled training data.

Britsch et al. develop a dynamic machine learning model that predicts 48-hour mortality for intensive care unit patients throughout their stay. The model shows robust performance across disease groups and timepoints, offering interpretable, clinically relevant risk categorization.

Brown et al. apply statistical and unsupervised machine learning methods to identify and characterize associations between maternal and paternal characteristics with infant cardiac malformations. Known risk factors were identified alongside potential signals, which warrant further investigation.

Cente et al. investigate the acute effects of mild repetitive head impacts in female soccer players. Findings reveal that female players are more sensitive to head impacts compared to males, as manifested by short-term decline in cognitive performance, altered plasma tau protein profile, and initiation of neuroprotective pathways.

La Porta et al. present ARIADNE, an algorithm to analyze gene expression data in HER2-breast cancer patients. The predictive ability of response to immunotherapy is improved when complemented by a cytokine score.

Keeler et al. report an updated meta-analysis of peripheral cytokine concentrations in individuals with eating disorders. Results reveal elevations in interleukin (IL)-6 and IL-15 and reductions in IL-7 in people with anorexia nervosa in comparison to healthy controls, and no elevations in pro-inflammatory cytokines in people with bulimia nervosa.

Ousdal et al. investigate whether global or regional hippocampal volume increase after Electroconvulsive therapy (ECT) for major depressive episodes relate to cognitive side effects. Their findings suggest that pronounced structural change in the posterior hippocampus (i.e., body and tail) associates with reduced cognitive performance following ECT.

Thapa et al. highlight how repeated extreme weather and climate events function as Environmentally driven Adverse Childhood Experiences (E-ACEs). This Perspective calls for climate-responsive and trauma-informed public health strategies to protect mental health and well-being in children during an era of escalating environmental instability due to climate change.