Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Shi et al. describe a phenotypic, culture-free platform that completes the diagnosis of bloodstream infections about 15 hours faster than standard diagnostic technologies. Results from clinical blood samples that demonstrate near real-time diagnostic information suitable for clinicians is provided.
Allgaier et al. scrutinize the performance of machine learning (ML) models applied to 7 longitudinal mHealth datasets. Their study advocates for considering simple heuristics over complex ML models, underscoring the need for robust validation and expert consultation to address hidden groups in data.
Takele et al. conduct a systematic review and meta-analysis of the effects of intervention characteristics on preventing gestational diabetes. Group or healthcare facility-based physical activity interventions are found to be more effective in preventing gestational diabetes than community-based interventions.
Ratley, Zeldin et al. implicate xylene in the pathogenesis of atopic dermatitis by combining spatial analysis and patient surveys with prior epidemiological and mechanistic data. They propose that exposure of healthy skin commensals to xylene, benzene and isocyantes in synthetic fabrics disrupts normal lipid metabolism and activates itching.
Iwadare et al. investigate the value of serum autotaxin levels in predicting liver-related events within a retrospective cohort of 309 biopsy-proven NAFLD patients. Multivariate Cox proportional hazards models identify autotaxin levels and advanced fibrosis as independent predictive factors.
Kruper et al. investigate the impact of glaucoma on brain tissue by comparing MRI data from 856 people with glaucoma to matched controls without glaucoma. They find that neural networks using tissue properties from visual brain connections more accurately detect glaucoma than those trained on non-visual brain connections.
Kolbinger, Veldhuizen et al. systematically review reporting guidelines for artificial intelligence (AI) methods in clinical research. They identify several essential, commonly recommended items on study design and model performance, while other items are specific to particular fields and research stages.
Das and colleagues develop and evaluate a parallel discriminator generative adversarial network (P-GAN) for improved in-vivo imaging of retinal cellular structures. The P-GAN network improves retinal pigment epithelium contrast 3.5-fold and the overall throughput 99-fold.
Holm et al. present a SARS-CoV-2 surveillance model linking hospitalization, seroprevalence, and wastewater concentrations. They fit this model to epidemic data from Kentucky, USA, to generate counterfactual scenarios highlighting the plausible effects of vaccination and changes in dynamics due to emergence of new variants.
Nunez et al. investigate the use of natural language processing to predict which patients with cancer will see a psychiatrist or counselling using the initial oncology consultation document. Their study supports the use of such techniques with widely-available medical documents to better address the psychosocial needs of cancer patients.
Fola et al. perform a nationwide genomic surveillance study of P. falciparum parasites across Zambia from samples collected in 2018 and report key genetic metrics informing transmission intensity, genetic relatedness, and selection. These genomic surveillance data highlight the need to strengthen malaria control and surveillance of drug resistance.
Felton et al. conduct a systematic review to determine the utility of islet autoantibodies as biomarkers of type 1 diabetes heterogeneity. They find that islet autoantibodies are most likely to be useful for patient stratification prior to clinical diagnosis.
Bueichekú et al. use multimodal in vivo neuroimaging to investigate the brain characteristics of individuals presenting unawareness of memory loss who are at risk of Alzheimer’s disease due to age. They find unawareness of memory decline is an early behavioral sign that a person might develop Alzheimer’s disease.
Grover et al. describe the training, deployment, and evaluation of real-time super-resolution imaging for MRI-guided radiation therapy. Volunteer, phantom, and simulation experiments demonstrate that super-resolution can increase the spatiotemporal resolution of real-time MRI guidance.
Esposito et al. investigate the genetic basis of response to BNT162b2 mRNA COVID-19 vaccine in 1351 Italian subjects. They find variants in the human leukocyte antigen locus significantly associate with serum anti-SARS-CoV-2 antibody levels, after vaccination.
Mahbub et al. introduce a question-answering framework to extract injection drug use (IDU) details from unstructured clinical notes. The proposed framework demonstrates high performance and extracts IDU details efficiently, facilitating informed care for those who inject drugs.
Galhaut et al. evaluate the immunogenicity and efficacy of an inactivated whole virus COVID-19 vaccine in animal models. VLA2001 adjuvanted with alum and CpG 1018 generates polyfunctional Th1 cell responses and specific neutralizing antibodies to several SARS-CoV-2 variants of concern and protects macaques from viral replication and inflammation.
Fredolini et al. present a proteomics analysis of home-sampled dried blood spots taken from the general population in Stockholm during the COVID-19 pandemic. The study provides insights into the molecular effects of SARS-CoV-2 infection in non-hospitalized individuals and demonstrates the compatibility of self-sampled blood spots with proteomics.
Wang, Yang et al. propose KnowDDI, a graph neural network that leverages biomedical knowledge graphs for drug-drug interaction predictions. The model yields improved performance and interpretability over existing methods, especially in scenarios with sparse knowledge graphs, marking a significant advancement in biomedicine and healthcare.
Ptacin et al. utilize a semi-synthetic microbial platform with an expanded genetic code to discover a PEGylated IL-2 compound that stimulates Tregs, with minimal effects on effector populations. Studies in mice and primates demonstrate Treg stimulation and support development of this compound for the potential treatment of autoimmune diseases.