Radically different
A wearable smart wristband that continuously measures blood flow at the wrist may be able to detect cardiac arrest and automatically trigger emergency alerts, according to findings from the DETECT-1b study published in the journal Circulation: Arrhythmia and Electrophysiology. Researchers at Radboud University Medical Center found that the technology detected shockable cardiac arrest events with 92% sensitivity during controlled clinical procedures in patients with ventricular arrhythmias. The findings are an early indication that monitoring the condition via a wearable device technology could eventually help reduce delays in providing care for out-of-hospital cardiac arrest by automatically alerting emergency medical systems or nearby responders.
“Our findings are important because many out-of-hospital cardiac arrests are unwitnessed. A smart technology wristband capable of automatically detecting cardiac arrest and triggering an alert could function as a digital witness,” said senior author Judith Bonnes, MD, PhD, a cardiologist at Radboud University Medical Center in the Netherlands. “With the device automatically notifying emergency services or nearby trained responders, help could arrive sooner, which may significantly improve survival chances.”
The DETECT-1b study was designed to evaluate a medically certified smart wristband that uses a light-based sensing method called photoplethysmography (PPG) that is capable of measuring blood flow changes in the wrist. The wearable device, called CardioWatch, continuously monitored pulse-related blood flow signals during procedures in which dangerous heart rhythms were intentionally induced under controlled conditions in people known to have abnormal heart rhythms.
The research is a follow-on of the DETECT-1a study. “In the DETECT-1a, we developed a wrist-derived photoplethysmography (PPG) algorithm for cardiac arrest detection using patient data from induced short-lasting circulatory arrests, achieving 98% sensitivity,” the researchers wrote.
DETECT-1b was developed as a prospective multicenter validation study involving adults undergoing ventricular tachycardia ablation or subcutaneous implantable cardioverter-defibrillator implantation. During these procedures, pulseless ventricular tachycardia or ventricular fibrillation was induced briefly to test cardiac function and device response. While this was occurring, the researchers recorded electrocardiogram and invasive blood pressure measurements as reference standards while patients wore the CardioWatch.
The study enrolled 49 adults in the Netherlands. Participants had a median age of 66 years, 84% were men, and many had existing cardiovascular disease. Seven participants had a prior history of cardiac arrest, 69% had experienced myocardial infarction, and approximately half had moderately or severely reduced left ventricular function.
For this study, the researchers evaluated 125.5 hours of data from the wristbands of the participant and identified 59 shockable cardiac arrest events among 26 patients. Fifty of the identified events were pulseless ventricular tachycardia and nine involved ventricular fibrillation. The algorithm detected 92% of all cardiac arrest events overall, including 100% of ventricular fibrillation episodes and 90% of pulseless ventricular tachycardia events.
“This is the first external validation in patients of a wearable-based cardiac arrest detection model, demonstrating that wrist-derived PPG reliably detects shockable cardiac arrest, with 100% sensitivity for VF,” the researcher wrote.
The algorithm developed to detect these events works by continuously monitoring the amplitude of PPG signals collected at the wrist. When signal amplitude decreases, the embedded algorithm evaluates signal quality to determine whether pulse-related peaks remain detectable. If pulse signals disappear, the algorithm triggers a cardiac arrest alarm.
The researchers also uncovered a number of false-positive alerts. Thirty-three alerts occurred in the absence of pulseless ventricular tachycardia or ventricular fibrillation. Nevertheless, of the 33 alert, 24 occurred during hemodynamically tolerated ventricular tachycardia and were considered clinically relevant. In total, nine of the alerts from 125.5 hours of monitoring were classified as false positives.
Lead study author Roos Edgar, a technical physician at Radboud, noted that the technology differs from prior cardiac arrest detection methods because the wrist-based design allows continuous monitoring during routine daily life. While many commercially available smart watches contain similar PPG sensors, they are not equipped to detect cardiac arrest.
The technology has the potential to be used for patients at elevated risk for cardiac arrest, including patients with ventricular arrhythmias or implantable cardioverter-defibrillators. The researchers said future deployment could also involve directly integrating the wristband’s alerts with emergency dispatch systems.
“The goal is to connect the wristband to emergency dispatch centers and volunteer responder networks in the Netherlands so that nearby rescuers and ambulance services can be alerted immediately when cardiac arrest is detected,” Bonnes said.
Future studies are expected to evaluate how the system performs during everyday activities, exercise and sleep, conditions that may create additional signal noise and complicate detection.
The post Smart Wristband Detects Cardiac Arrest with 92% Sensitivity in Early Clinical Study appeared first on Inside Precision Medicine.
Google DeepMind and Edison Scientific are on an ambitious mission to build the AI scientist. These platforms propose to automate the scientific method using reasoning systems that connect hypothesis generation, experimental design, and data interpretation in one platform. In drug discovery, where traditional development timelines can stretch beyond a decade, such systems promise to dramatically accelerate the pace of biomedical research.
The AlphaFold developer and the nonprofit home organization behind Edison, FutureHouse, originally introduced their respective systems, Co-Scientist and Robin, as bioRxiv preprints in early 2025. Those studies have now been published in Nature, marking another step toward a growing ecosystem of specialized AI agents for life science research.
Led by Demis Hassabis, PhD, CEO, and 2024 Nobel laureate in Chemistry, DeepMind is no stranger to expanding biomedicine. The team published a January Nature paper describing AlphaGenome, a unifying DNA sequence model for regulatory variant-effect prediction to support understanding of genome function and disease biology.
Additionally, DeepMind drug discovery spinout, Isomorphic Labs, recently made waves after securing a whopping $2.1 billion Series B led by Thrive Capital, signaling the industry’s growing investment in AI-driven therapeutics.
“I’ve always believed the No.1 application of AI should be to improve human health,” wrote Hassabis on LinkedIn when announcing Isomorphic’s blockbuster raise.
DeepMind’s newly published AI assistant, Co-Scientist, is a general-purpose multi-agent system built with Google’s Gemini and driven by natural language prompts. The platform demonstrated initial validation across three biomedical applications: drug repurposing for acute myeloid leukemia, novel target discovery for liver fibrosis, and explaining mechanisms of anti-microbial resistance.
Co-Scientist’s design scales test-time compute to iteratively reason, evolve, and improve the output as it gathers more knowledge. Researchers can also actively steer the system by refining generated ideas or providing feedback through the natural language chat.
Vivek Natarajan, research scientist at DeepMind, emphasizes that time is a valuable commodity when tackling disease. Co-Scientist aims to support humans scientists in reaching answers to their problems much faster than before, from “months and years to minutes and hours.”
“To realize this vision, we need to build in reliability, trustworthiness and ensure a collaborative human-AI interaction paradigm. We have done a lot of research on these aspects and we are continuing to improve,” Natarajan told GEN Edge.
Edison is the commercial spinout of FutureHouse, an AI scientist non-profit backed by former Google CEO Eric Schmidt and co-founded by Sam Rodriques, PhD, former group leader at The Francis Crick Institute and Edison’s CEO. The team’s newly published platform, Robin, leverages both OpenAI o4-mini and Anthropic Claude 3.7 to aid biological discovery.
In research tasks, Robin proposed repurposing Ripasudil, an existing drug for treatment of glaucoma, to address dry age-related macular degeneration (dAMD) via a novel mechanism that enhanced retinal pigment epithelial cell phagocytosis. The platform also suggested a circadian clock modulator, KL001, as an unexpected treatment for dAMD, illustrating the ability to make new connections not found in existing literature. Both insights were experimentally validated in patient-derived retinal pigment epithelium (RPE) cells.
Since Robin’s May 2025 preprint release, Edison unveiled an updated AI scientist, Kosmos, last November. Kosmos can reason over 175 million full-text papers, clinical trials and patents, and operate interactively as a colleague that can sends updates mid-run. The system is reported to perform hundreds of research tasks in parallel to compress months of work into a single day.
Today, Edison announced a collaboration with Incyte to employ Kosmos across the global pharma’s discovery and development pipeline. The partnership will focus on enabling continuous learning from translational and clinical data, real-time synthesis of evidence, and predictive models of therapeutic performance.
Michaela Hinks, founding member of technical staff at Edison, says the main bottlenecks for AI scientist adoption are trust, validation, and the gap in end-to-end solutions.
“Most AI tools accelerate the cheaper and easier upstream work, but not the expensive and regulated downstream stages of scientific research,” Hinks told GEN Edge.
She also highlights Robin as the first demonstration of an agentic AI scientist generating a hypothesis that is tested and validated in patient-derived cells, not an immortalized cell line, supporting clinically actionable insights for patients in need.
Whether AI scientists will truly revolutionize discovery remains to be seen, but researchers are already beginning the experiment.
The post Google DeepMind and Edison Are Building the AI Scientist appeared first on GEN – Genetic Engineering and Biotechnology News.
The idea of drinking during pregnancy sounds like a generational punchline: Someone’s grandmother drank beer to fatten her fetus, another had a nightly martini to get a healthy amount of sleep — presumably unthinkable behavior in today’s America.
Yet after precipitous declines in the last 50 years, rates of alcohol use in pregnancy in the U.S. started climbing upward a decade ago. More than 1 in 8 pregnant adults reported drinking in the past month, according to STAT’s analysis of 2024 government data, making alcohol use a more common national phenomenon than gestational diabetes. Of those who drank, a quarter reported having four or more drinks in one sitting — binge drinking — in the prior month.
While rates of alcohol use in pregnancy are lower in the U.S. than those of several peer nations, the effects are all around Americans. Alcohol is the key driver of what are, by some estimates, the nation’s top neurodevelopmental conditions: fetal alcohol spectrum disorders, or FASDs.
The exact prevalence of FASDs is difficult to measure, but the most recent federally funded community studies have found as many as 1 in 20 school-aged children may have a disorder caused by prenatal alcohol exposure. By comparison, about 1 in 31 American children has autism, per recent estimates from the Centers for Disease Control and Prevention.
Not all fetuses exposed to alcohol have birth defects or go on to develop intellectual disabilities, researchers say. But every person born with an FASD was harmed by alcohol specifically. They worry this point is being glossed over as Americans question the conventional medical advice of avoiding all alcohol while pregnant.