This Review discusses the characteristics of neural probes that are most likely to facilitate the clinical translation of invasive neural interfaces, the abiotic and biotic factors that contribute to their failure and emerging neural-interface architectures.

This Perspective argues that dermal interstitial fluid cannot be generally considered a diagnostically useful proxy for blood, yet that it can offer advantageous utility for the monitoring of therapeutic drugs and of the status of the immune system.

This Perspective overviews the sources of prediction uncertainty in machine learning for applications in healthcare, and discusses how to implement suitable prediction-uncertainty metrics.

This Review highlights technological advances in exoskeleton technology from the past two decades, and challenges and opportunities in the exoskeleton-assisted rehabilitation of gait.

An assay leveraging the target-specific splinted ligation of DNA probes to generate expression cassettes for the cell-free synthesis of reporter proteins accurately detects nucleic acids at ambient temperature.

A high-throughput method leveraging peptide-encoding mRNA barcodes for the in vivo screening of libraries of nanoparticle formulations allows for the rapid optimization of a lipid nanoparticle for the delivery of mRNA to the liver.

A stretchable ultrasonic array conforming to the skin allows for the three-dimensional imaging of tissue modulus at depths of up to 4 cm.

Ensembles of explainable machine-learning models increase the quality of explanations for the molecular basis of synergetic drug combinations, as shown for the treatment of acute myeloid leukaemia.

An anti-inflammatory enzyme fused with a tissue-anchoring protein and injected into inflamed tissues ameliorates local inflammation without causing systemic immune suppression, as shown in multiple rodent models of inflammatory diseases.

A method leveraging an integrase-deficient lentivirus, homology-directed repair and the electroporation of a CRISPR-associated ribonucleoprotein complex allows for the knock-in and stable expression of large payloads in primary human cells.

The continuing optimization of the safety and applicability of CRISPR for ex vivo genome editing will broaden the prospects of cell therapies.

Bionic hands exemplify the challenges of developing neuroprostheses that can be embodied.

New strategies for enhancing the sensitivity and resolution of contrast in magnetic resonance imaging will broaden its applicability.

The consequences of their use will be far reaching.

At first glance, some research articles published in the journal may appear to lack substantial novelty.

Graph neural networks and transformers taking advantage of contextual information and large unannotated multimodal datasets are redefining what is possible in computational medicine.