Featured
-
-
Article |
Fruquintinib plus paclitaxel versus placebo plus paclitaxel for gastric or gastroesophageal junction adenocarcinoma: the randomized phase 3 FRUTIGA trial
In a randomized, double-blind, placebo-controlled phase 3 trial, the anti-vascular endothelial growth factor receptor small-molecule inhibitor fruquintinib plus chemotherapy significantly extended progression-free survival, but not overall survival, as second-line therapy in patients with advanced gastric or gastroesophageal junction cancers.
- Feng Wang
- , Lin Shen
- & Rui-Hua Xu
-
Correspondence |
Point-of-care testing for sepsis in remote Australia and for First Nations peoples
- Brooke Spaeth
- , Sean Taylor
- & Simon Finfer
-
Article
| Open Access
Multimodal assessment improves neuroprognosis performance in clinically unresponsive critical-care patients with brain injury
Multimodal approaches combining various numbers of behavioral, neuroimaging and electrophysiological markers improves neuroprognosis performance in clinically unresponsive critical-care patients.
- B. Rohaut
- , C. Calligaris
- & L. Naccache
-
Research Highlight |
Affordable and simplified whole-body MRI
A whole-body scanner developed using a permanent 0.05-tesla magnet and deep learning has demonstrated its versatility in imaging various anatomical structures, showcasing its potential to address unmet clinical needs.
- Sonia Muliyil
-
Correspondence |
Generating clinical evidence for treatment and prevention options for long COVID
- Stephanie Buchholz
- , Eugenia Di Meco
- & Marco Cavaleri
-
Article |
Noninvasive assessment of organ-specific and shared pathways in multi-organ fibrosis using T1 mapping
T1 mapping noninvasively assesses fibrosis in multiple organs and enables risk stratification of mortality and provides insights into shared and organ-specific pathways underlying fibrosis.
- Victor Nauffal
- , Marcus D. R. Klarqvist
- & Patrick T. Ellinor
-
News & Views |
What the SELECT trial of semaglutide means for clinicians
Accumulating data support the systemic benefits of semaglutide (and potentially other GLP-1RA-based therapies) in people with obesity, meaning that cardiologists and other clinicians must become familiar with prescribing them — particularly once market competition makes these drugs more accessible.
- Naveed Sattar
- , Matthew M. Y. Lee
- & Darren K. McGuire
-
Research Highlight |
Half a century of immunization success
A modeling study marking 50 years of vaccination through the Expanded Programme on Immunization of the World Health Organization highlights its lifesaving impact on infant and child health.
- Sonia Muliyil
-
Article
| Open Access
Prediction of recurrence risk in endometrial cancer with multimodal deep learning
A multimodal deep learning prognostic model based on histopathology outperforms current gold standards for identifying patients with endometrial cancer with different outcomes, in multiple external validation cohorts.
- Sarah Volinsky-Fremond
- , Nanda Horeweg
- & Tjalling Bosse
-
World View |
How to bridge innovation and regulation for responsible AI in healthcare
Quality assurance labs should independently test AI health tools.
- Brian Anderson
-
Article
| Open Access
Dual-energy lattice-tip ablation system for persistent atrial fibrillation: a randomized trial
In a randomized trial testing two types of catheter ablation treatments for persistent atrial fibrillation, a large-tip, dual pulsed field and radiofrequency catheter with a large footprint was non-inferior to a conventional radiofrequency catheter.
- Elad Anter
- , Moussa Mansour
- & Vivek Y. Reddy
-
Article |
Heat exposure induced risks of preterm birth mediated by maternal hypertension
Findings from a multicenter study of 197,080 singleton live births in China show maternal hypertension as a mediator of the risks imposed by heat exposure between conception and 20 weeks of gestation on preterm birth and its various clinical subtypes.
- Liyun Wang
- , Jiangli Di
- & Cunrui Huang
-
Article |
Effectiveness of bariatric metabolic surgery versus glucagon-like peptide-1 receptor agonists for prevention of congestive heart failure
In a retrospective study of individuals living with diabetes and obesity, conducted from 2008 through 2021, treatment with bariatric metabolic surgery was more effective than treatment with GLP-1 receptor agonists for prevention of incident congestive heart failure.
- Yael Wolff Sagy
- , Gil Lavie
- & Dror Dicker
-
Review Article |
Artificial intelligence in surgery
This Review outlines the state of the art of artificial intelligence in the preoperative, intraoperative and postoperative settings, where it has enormous potential to improve patient outcomes, surgical education and system efficiencies.
- Chris Varghese
- , Ewen M. Harrison
- & Eric J. Topol
-
Article
| Open Access
Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging
A two-step, video-based deep learning model is developed to first screen for cardiac anomalies using noncontrast magnetic resonance imaging, followed by diagnosis of 11 types of cardiovascular disease using gadolinium enhancement-based imaging.
- Yan-Ran (Joyce) Wang
- , Kai Yang
- & Shihua Zhao
-
Article
| Open Access
Long-term weight loss effects of semaglutide in obesity without diabetes in the SELECT trial
A prespecified analysis of the SELECT trial revealed that patients assigned to once-weekly subcutaneous semaglutide 2.4 mg lost significantly more weight than those receiving placebo and showed improvements in various anthropometric indices.
- Donna H. Ryan
- , Ildiko Lingvay
- & Robert F. Kushner
-
News & Views |
Using AI to improve medication safety
Large language models can translate the archaic language of pharmacy prescriptions into plain English, but reducing medication errors for patients will require interventions that go further.
- Johanna I. Westbrook
- , Nasir Wabe
- & Magdalena Z. Raban
-
Article
| Open Access
Effects of a personalized nutrition program on cardiometabolic health: a randomized controlled trial
A randomized controlled trial showed that following a personalized dietary program led to significant improvements in cardiometabolic and gut health as well as reductions in body weight compared to following standard dietary advice according to US Department of Agriculture guidelines.
- Kate M. Bermingham
- , Inbar Linenberg
- & Sarah E. Berry
-
Article |
Equitable implementation of a precision digital health program for glucose management in individuals with newly diagnosed type 1 diabetes
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.
- Priya Prahalad
- , David Scheinker
- & David M. Maahs
-
News & Views |
Adapting vision–language AI models to cardiology tasks
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.
- Rima Arnaout
-
Research Highlight |
Telemonitoring of patients with acute coronary syndrome
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.
- Sonia Muliyil
-
Article |
AI-enabled electrocardiography alert intervention and all-cause mortality: a pragmatic randomized clinical trial
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.
- Chin-Sheng Lin
- , Wei-Ting Liu
- & Chin Lin
-
Brief Communication
| Open Access
Influence of COVID-19 on trust in routine immunization, health information sources and pandemic preparedness in 23 countries in 2023
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.
- Jeffrey V. Lazarus
- , Trenton M. White
- & Ayman El-Mohandes
-
Comment |
The argument framework is a flexible approach to evidence in healthcare
An argument framework, grounded in the sciences of reasoning, provides an alternative to medicine’s measurement framework for evaluating and synthesizing evidence in healthcare.
- Jonathan Fuller
- , Benjamin Chin-Yee
- & Ross E. G. Upshur
-
Article
| Open Access
Large language models for preventing medication direction errors in online pharmacies
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.
- Cristobal Pais
- , Jianfeng Liu
- & Mohsen Bayati
-
Correspondence |
Strategies for controlling pneumococcal disease and outbreaks during humanitarian emergencies
- Molly Cliff
- , Paul Welaga
- & Brenda Kwambana-Adams
-
Correspondence |
Post-election responsibilities for public health in the Democratic Republic of the Congo
- Faraan O. Rahim
- , William C. Lieber
- & Richard M. Lukelwa
-
Comment |
Opportunities and challenges following approval of resmetirom for MASH liver disease
The US Food and Drug Administration (FDA) has approved the first drug, resmetirom, for metabolic dysfunction-associated steatohepatitis (MASH), but much work remains for the industry, practitioners and health systems so that this approval will benefit all patients.
- Jeffrey V. Lazarus
- , Dana Ivancovsky Wajcman
- & Paul N. Brennan
-
News & Views |
Using unlabeled data to enhance fairness of medical AI
AI models for tasks such as pathology and dermatology struggle to generalize to new patient groups or hospitals that they were not trained on; learning more robust features from unlabeled data could prevent overfitting to the training distribution and thereby increase fairness.
- Rajiv Movva
- , Pang Wei Koh
- & Emma Pierson
-
Article |
Demographic bias in misdiagnosis by computational pathology models
In a series of clinically relevant tasks in computational pathology, AI-driven models display marked performance disparities across demographic groups, which can only partially be mitigated by self-supervision on large training datasets and existing debiasing techniques.
- Anurag Vaidya
- , Richard J. Chen
- & Faisal Mahmood
-
Perspective |
Causal machine learning for predicting treatment outcomes
Causal machine learning methods could be used to predict treatment outcomes for subgroups and even individual patients; this Perspective outlines the potential benefits and limitations of the approach, offering practical guidance for appropriate clinical use.
- Stefan Feuerriegel
- , Dennis Frauen
- & Mihaela van der Schaar
-
Correspondence |
Nicotine e-cigarettes: considerations for healthcare providers
- Benjamin A. Toll
- , Tracy T. Smith
- & Brian A. King
-
Correspondence |
A framework for implementing patient-reported outcomes in clinical care: the PROTEUS-practice guide
- Norah L. Crossnohere
- , Nicola Anderson
- & Claire Snyder
-
Article |
Transparent medical image AI via an image–text foundation model grounded in medical literature
By learning to pair dermatological images and related concepts in a self-supervised manner, a visual-language foundation model is shown to have comparable performance to supervised models for concept annotation and is used to scrutinize model decisions for enhanced interpretability and accountability of medical imaging applications.
- Chanwoo Kim
- , Soham U. Gadgil
- & Su-In Lee
-
Article
| Open Access
Generative models improve fairness of medical classifiers under distribution shifts
By generating synthetic image samples specific to underrepresented groups, diffusion models help medical image classifiers to achieve greater fairness metrics across a variety of medical disciplines and demographic attributes.
- Ira Ktena
- , Olivia Wiles
- & Sven Gowal
-
News & Views |
Tackling heat-related mortality in aging populations
A large study of older adults in China points to physical and cognitive function — not age — as key predictors of heat-related mortality, highlighting the need for climate adaptation policies to prioritize accessibility across all age groups.
- Josiah L. Kephart
- & Safiyyah M. Okoye
-
Research Highlight |
Elevating kidney disease on the global health stage
Global nephrology societies have called on the WHO and health communities to tackle the growing burden of chronic kidney disease, which has been under-recognized for too long.
- Karen O’Leary
-
News & Views |
Large language models for reducing clinicians’ documentation burden
Evaluation of a clinical summarization method based on GPT-4 suggests that such models might reduce the documentation burden on clinicians — but prospective evaluation with high-priority tasks will be the true test of its potential.
- Kirk Roberts
-
Research Highlight |
Going the extra mile to increase vaccine uptake
Deployment of mobile vaccination teams to remote communities in Sierra Leone substantially increased COVID-19 vaccine uptake, and could potentially be bundled with other health interventions.
- Karen O’Leary
-
Article |
Risk factors associated with heatwave mortality in Chinese adults over 65 years
In a prospective cohort of Chinese participants aged 65 years and older, heatwaves doubled the risk of mortality, especially in adults with functional impairments and dependency on daily living activities.
- Di Xi
- , Linxin Liu
- & John S. Ji
-
Comment |
Promoting gender equity in the scientific and health workforce is essential to improve women’s health
Women’s health can be improved by increasing the representation of women in leadership roles in science, medicine and public health.
- Cristiani Vieira Machado
- , Cristina Araripe Ferreira
- & Maria Auxiliadora de Souza Mendes Gomes
-
Research Briefing |
Testing pooled samples enables universal screening of congenital cytomegalovirus infection
The implementation of PCR tests of pooled saliva samples for universal screening of congenital cytomegalovirus infection was assessed in 15,805 neonates over 13 months. This extensive analysis revealed the high feasibility and empirical efficiency of the pooled testing approach, which had a clinically insignificant loss of sensitivity.
-
Article |
A visual-language foundation model for computational pathology
Developed using diverse sources of histopathology images, biomedical text and over 1.17 million image–caption pairs, evaluated on a suite of 14 diverse benchmarks, a visual-language foundation model achieves state-of-the-art performance on a wide array of clinically relevant pathology tasks.
- Ming Y. Lu
- , Bowen Chen
- & Faisal Mahmood
-
Article |
Towards a general-purpose foundation model for computational pathology
Pretrained using over 100,000 diagnostic histopathological slides across 20 major tissue types, a self-supervised model is shown to outperform existing baselines across various clinically relevant computational pathology tasks.
- Richard J. Chen
- , Tong Ding
- & Faisal Mahmood
-
Article
| Open Access
Heterogeneity and predictors of the effects of AI assistance on radiologists
A large-scale study examined the heterogeneous effects of artificial intelligence (AI) assistance on 140 radiologists across 15 chest X-ray diagnostic tasks and found that conventional experience-based factors, such as years of experience, subspecialty and familiarity with AI tools, fail to reliably predict the impact of AI assistance.
- Feiyang Yu
- , Alex Moehring
- & Pranav Rajpurkar
-
News & Views |
Telehealth enables safe medication abortion in shifting health and legal contexts
Telehealth provision of medication abortion is safe and effective, but ensuring equitable access is challenging in the USA — and further compounded by an upcoming Supreme Court case.
- Dana M. Johnson
- , Abigail R. A. Aiken
- & Terri-Ann Thompson
-
Research Highlight |
Prolonged benefits of bariatric surgery for patients with Type 2 Diabetes
People with type 2 diabetes who underwent bariatric surgery compared to medical or lifestyle interventions had better long-term outcomes, such as greater diabetes remission and less reliance on medication.
- Sonia Muliyil
-
Research Highlight |
A timeline of biomarker changes before Alzheimer’s disease
Longitudinal data from the China Cognition and Aging Study map the sequential biomarker changes that begin almost two decades before clinical onset of Alzheimer’s disease.
- Karen O’Leary
-
Article
| Open Access
Self-help mobile messaging intervention for depression among older adults in resource-limited settings: a randomized controlled trial
The PRODIGITAL-D trial in adults aged 60+ years from socioeconomically deprived areas of Brazil showed that a 6-week self-help mobile messaging psychosocial intervention was effective in improving depression recovery at 3 months compared to a single message control intervention.
- Marcia Scazufca
- , Carina Akemi Nakamura
- & Ricardo Araya
Non-literacy biased, culturally fair cognitive detection tool in primary care patients with cognitive concerns: a randomized controlled trial