Toggle light / dark theme

This AI tool could help curb domestic violence

The Automated Intimate Partner Violence Risk Support System (AIRS) utilizes clinical history and radiologic data to pinpoint patients seen in the emergency room who may be at a risk for intimate partner violence (IPV). Developed over the past five years, AIRS has been rolled out to the Brigham and Women’s Hospital’s Emergency Rooms in Boston as well as surrounding primary care sites. Currently, the tool has been validated at the University of California-San Francisco Medical Center and is being evaluated by the Alameda Health System for its role in clinical workflow.

“Data labeling quality is a huge concern—not just with intimate partner violence care, but in machine learning for healthcare and machine learning, broadly speaking,” says cofounder Irene Chen. “Our hope is that with training, clinicians can be taught how to spot intimate partner violence—we are hoping to find a set of cleaner labels.”

“Mirror Bacteria” Warning: A New Kind of Life Could Pose a Global Threat

Mirror life, a concept involving synthetic organisms with reversed molecular structures, carries significant risks despite its potential for medical advancements.

Experts warn that mirror bacteria could escape natural biological controls, potentially evolving to exploit resources in ways that disrupt ecosystems and pose unforeseen dangers to the environment and public health.

Mirror Life

Microplastics in the air may be leading to lung and colon cancers

Tires and degrading garbage shed tiny pieces of plastic into the air, creating a form of air pollution that UC San Francisco researchers suspect may be causing respiratory and other illnesses.

A review of some 3,000 studies implicates these particles in a variety of serious health problems. These include male and female infertility, and poor lung function. The particles also may contribute to chronic pulmonary inflammation, which can increase the risk of lung cancer.

“These microplastics are basically particulate matter air pollution, and we know this type of air pollution is harmful,” said Tracey J. Woodruff, Ph.D., MPH, a professor of obstetrics, gynecology and at UCSF.

57 Countries Confirming Measles Outbreaks

Over the past two years, the U.S. Centers for Disease Control and Prevention (CDC) has issued Travel Health Advisories focused on measles outbreaks.

These advisories highlight where there is an active health risk when people visit the highlighted countries.

On February 21, 2025, the CDC reissued a Level 1, Practice Usual Precautions, alert for 57 countries. This CDC list does not integrate the Region of the Americas, with numerous countries reporting 537 measles outbreaks this year.

New study identifies unique white matter astrocytes with regenerative potential

A research team has identified different subtypes of white matter (WM) astrocytes, including a unique type with the ability to multiply and potentially aid in brain repair. Using single-cell RNA sequencing and spatial transcriptomics, the scientists mapped astrocyte diversity across different brain regions and species, providing the first detailed molecular profile of WM astrocytes.

The team was led by Dr. Judith Fischer-Sternjak from Helmholtz Munich and Ludwig-Maximilians-Universität (LMU) München, alongside Prof. Magdalena Götz from Helmholtz Munich, LMU and the Munich Cluster for Systems Neurology (SyNergy). The research is published in the journal Nature Neuroscience.

Unveiling white matter astrocyte diversity Astrocytes, known for their crucial role in supporting neurons and maintaining brain health, have been predominantly studied in gray matter (GM), which is involved in information processing. However, white matter astrocytes, which support long-range neural connections, remain poorly understood. This study fills a major knowledge gap by showing that WM astrocytes are not a uniform population but consist of distinct subtypes with specialized roles.

Smartphone and nanotechnology enable rapid neonatal jaundice detection

A research team led by Prof. Jiang Changlong from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has developed an innovative dual-mode sensing platform using upconversion nanoparticles (UCNPs). This platform integrates fluorescence and colorimetric methods, offering a highly sensitive and low-detection-limit solution for bilirubin detection in complex biological samples.

The findings, published in Analytical Chemistry, offer a new technological approach for the early diagnosis of jaundice.

Jaundice is a critical health issue in neonates, affecting 60% of newborns and contributing to early neonatal mortality. Elevated free bilirubin levels indicate jaundice, with healthy levels ranging from 1.7 μM to 10.2 μM in healthy individuals. Concentrations below 32 μM typically don’t show classic symptoms. Rapid and accurate detection of bilirubin in neonates is critical.

Medical infusion bags can release microplastics, study shows

Microplastics have been found almost everywhere that scientists have looked for them. Now, according to research published in Environment & Health, these bits of plastic—from 1 to 62 micrometers long—are present in the filtered solutions used for medical intravenous (IV) infusions. The researchers estimate that thousands of plastic particles could be delivered directly to a person’s bloodstream from a single 8.4-ounce (250-milliliter) bag of infusion fluid.

In clinical settings, IV infusions are packaged in individual plastic pouches and deliver water, electrolytes, nutrients or medicine to patients. The base of these infusions is a that contains filtered water and enough salt to match the content of human blood. Research from the 1970s suggests IV fluid bags can contain solid particles, but few scientists have followed up on what those particles are made of.

Researchers Liwu Zhang, Ventsislav Kolev Valev and colleagues suspected that these particles could be microplastics that—upon —would enter the recipient’s bloodstream and potentially cause . So, they set out to analyze the types and amounts of particles in commercial IV fluid bags.

Domain specific architectures for AI inference


Billions of people may be continuously running AI inference for their waking hours in the near future. Satisfying this demand requires relentless focus on efficiency to reduce the required quantities of two key inputs: energy and capital. The constraints on these inputs in conjunction with the slowing and/or stagnation of both Moore’s Law and Dennard Scaling has left hardware architects no choice but to pursue Domain Specific Architectures (DSAs) — architectures tailored to the task at hand.

The current dominance of GPUs in modern deep learning is largely accidental — it was pure serendipity that the computational workload of graphics and deep learning were similar. Remnants of their graphical heritage still persist in GPU architectures today. What would AI inference hardware look like if it was redesigned carte blanche? By working backwards from the AI inference workload, we can determine some optimal properties these DSAs should have. Furthermore, we will attempt to predict the direction the inference paradigm will shift over time — a crucial exercise for hardware architects and engineers alike to ensure return on investment.

Researchers map how individual neurons encode behavioral states

National Institutes of Health researchers have mapped how individual neurons in the primary somatosensory cortex receive brain-wide presynaptic inputs that encode behavioral states, refining our understanding of cortical activity.

Neurons in the primary somatosensory cortex process different types of sensory information and exhibit distinct activity patterns, yet the cause of these differences has remained unclear. Previous research emphasized the role of motor cortical regions in movement-related processing, but also recognized that the thalamus plays a role beyond sensory relay.

Using high-resolution single-cell mapping to trace , the team revealed that thalamic input is the primary driver for movement-correlated neurons, while motor cortical input plays a smaller role.