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.
Pooled testing for the diagnosis of COVID-19 via isothermal nucleic acid amplification and detection can be automated by using electromagnetically actuated swarms of millimetric magnets to handle droplets of magnetized samples on a microfluidic chip.
This Perspective discusses the applicability of integrated whole-body PET/MRI for the study of immune-mediated phenomena associated with haematopoietic activity and cardiovascular disease.
The inability to precisely manipulate mammalian mitochondrial DNA has stalled our understanding of mitochondrial biology and the generation of cellular and animal models in which to study it. DNA base editing technologies have enabled the generation of a library of mitochondrial base editors that precisely ablate every protein-coding gene in the mouse mitochondrial genome.
Water exchange through the transmembrane channel aquaporin-4 can be measured by conventional dynamic-contrast-enhanced magnetic resonance imaging and is a sensitive biomarker of the proliferation of gliomas and their resistance to chemotherapy.
Cytokine receptor agonists can be designed with longer half-lives in circulation and with enhanced penetration of the blood–brain barrier by genetically grafting macrocyclic peptides into the structural loops of fragment crystallizable regions.
Graph deep learning applied to multiplexed immunofluorescence data from tumour microenvironments reveals spatial cellular structures that are indicative of cancer prognosis.
Off-the-shelf microphones and earbud components connected to a smartphone can be as effective as an expensive clinical-grade device at measuring otoacoustic emissions to screen for hearing loss.
Developing gene therapy for use in the central nervous system has been hampered by the lack of an efficient vector for gene delivery. We report an adeno-associated virus vector with an enhanced ability to cross the blood–brain barrier in both rodents and non-human primates, and use it to develop systemic anti-tumour gene therapies for glioblastoma.
The flux of autophagosomes in heart tissue can be detected in live mice via the fluorescence and magnetic resonance properties of intravenously injected iron oxide nanoparticles decorated with fluorescent peptides cleavable by lysosomal cathepsins.
An assay leveraging strand-displacement reactions and enzymatic amplification for the recognition of viral RNA and implemented on origami paper allows for the fast colorimetric detection of SARS-CoV-2 variants, with single-nucleotide specificity.
Assays leveraging the CRISPR-associated enzyme Cas13 and isothermal RNA amplification for the detection of viral RNA are being simplified for point-of-care use.
Multiplex detection of two interacting Mycobacterium tuberculosis biomarkers on the surface of circulating extracellular vesicles, using a nanoplasmon-enhanced immunoassay, improves the diagnosis of tuberculosis in immunosuppressed children living with HIV.
Graph deep learning can be used to detect contextual pathological features within a complex tumour microenvironment. We have shown the use of graph deep learning for predicting the prognosis of patients with tumours, and use it to identify additional contextual prognostic biomarkers for pathologists.
Weakly supervised deep-learning models for the analysis of whole-slide images from tumour biopsies perform better at prognostic tasks if the models incorporate context from the local microenvironment.
This Review discusses the advantages and limitations of self-supervised methods and models for use in medicine and healthcare, and the challenges in collecting unbiased data for their training.
This Review discusses the use of deep generative models, federated learning and transformer models to address challenges in the deployment of machine learning for healthcare.
An adhesive hydrogel patch made from off-the-shelf materials seals and aids the healing of gastrointestinal-tissue defects without the need for sutures, as shown with the repair of gastrointestinal leaks in live rats and pigs.
This Perspective overviews the design and fabrication of tissue-mimicking phantom materials for the technical validation of biophotonic instrumentation, and identifies a set of criteria for their standardization.