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.
In a prospective study, a team-based approach combining continuous glucose monitoring with a technology-assisted remote patient monitoring program improved glycemia in a diverse cohort of children, adolescents and young adults with newly diagnosed type 1 diabetes.
Vision–language models can be trained to read cardiac ultrasound images with implications for improving clinical workflows, but additional development and validation will be required before such models can replace humans.
Using exome sequencing data from one of the largest cohorts of children with cerebral palsy, the genetic diagnostic rates of single-nucleotide and copy number variants were assessed and a sizeable fraction found to be clinically actionable.
A strategy that controls confounders in quantitative microbiome data challenges the validity of previously reported microbial markers in colorectal cancer and serves as a wake-up call for the microbiome research field.
The dynamics and durability of immune responses associated with protection against symptomatic infection in children offer insights to guide vaccination policies in pediatric populations.
In an open-label phase 2 trial, patients with non-small-cell lung cancer received neoadjuvant anti-PD-1 with or without anti-LAG-3, showing that curative intent surgery after combined blockade of PD-1 and LAG-3 is feasible, and leads to preliminary clinical responses.
A vision–language foundation model, trained on a dataset of more than 1 million echocardiogram video–text pairs, is able to assess various cardiac structural and functional parameters despite not having been directly trained on any specific image interpretation task.
A randomized controlled trial involving a telemedicine-based approach for the management of patients with acute coronary syndrome had several clinical benefits relative to standard of care.
In a randomized clinical trial, alerts based on the detection of abnormalities in electrocardiograms using a deep learning algorithm reduced all-cause mortality at 90 days in patients admitted to hospital emergency or internal medicine departments.
AI-enabled wellness apps exist in a regulatory gray area and may pose risks if used to manage mental health issues; this Perspective outlines the possible risks to users and the implications for app developers and regulators.
A survey of 23,000 adults in 23 countries in 2023 reports that the pandemic experience reduced participants’ willingness to be vaccinated for COVID-19 and receive routine vaccinations and reduced trust in recommendations from public health authorities.
An argument framework, grounded in the sciences of reasoning, provides an alternative to medicine’s measurement framework for evaluating and synthesizing evidence in healthcare.
In a case series of six patients with multidrug-resistant rheumatoid arthritis, the CD19xCD3-targeting bispecific T cell engager blinatumomab reduced disease activity and led to reductions in autoantibodies.
Tailored to detect and prevent potential medication direction errors in a digital pharmacy data processing pipeline, a large language model is shown to increase efficiency and decrease burden for technicians and pharmacists in a prospective application.
QR4 is a new cardiovascular disease (CVD) risk score developed and evaluated in 16.9 million people that has better performance than other commonly used CVD risk scores. It includes nine new risk factors associated with increased risk of developing CVD (for example, a heart attack or stroke) over the next 10 years.