Lifeboat Foundation

Of approximately 250,000 Americans diagnosed with acute pulmonary embolism (PE) in emergency departments each year, most are hospitalized.

But new Michigan Medicine research, published in JAMA Network Open, finds that some patients with PE, a blood clot in one or more pulmonary arteries, may be hospitalized unnecessarily due to computed tomography (CT) imaging results rather than clinical risk factors.

Approximately 40% of the patients in the study had low-risk pulmonary embolism, as defined by the Pulmonary Embolism Severity Index, or PESI score. Roughly half of the low risk patients had CT imaging features that physicians consider “concerning,” and these patients fared just as well in the hospital as those whose CT scans showed no concerning findings.

Summary: A novel study put the diagnostic prowess of generative AI, specifically the chatbot GPT-4, to the test, yielding promising results.

The study involved evaluating the AI’s diagnostic accuracy in handling complex medical cases, with GPT-4 correctly identifying the top diagnosis nearly 40% of the time and including the correct diagnosis in its list of potential diagnoses in 64% of challenging cases.

The success of AI in this study could provide new insights into its potential applications in clinical settings. However, more research is needed to address the benefits, optimal use, and limitations of such technology.

Kids soak up new skills, adults not so much. But neuroscientist Gül Dölen might have found a way—with drugs—to help grownups learn like littles.

Clinical stage generative AI-driven drug discovery company Insilico Medicine has today published a paper on a new multimodal transformer-based aging clock; the new clock is capable of processing diverse data sets and providing insights into biomarkers for aging, mapping them to genes relevant to both aging and disease, and discovering new therapeutic targets to slow or reverse both aging and aging-related diseases.

Insilico calls the aging clock Precious1GPT, in a nod to the powerful “One Ring” in Tolkien’s Lord of the Rings; the findings have been published in the journal Aging.

Longevity. Technology: Insilico has been at the forefront of both generative AI and aging research, and has been publishing studies on biomarkers of aging using advanced bioinformatics since 2014. Later, the company trained deep neural networks (DNNs) on human “multi-omics” longitudinal data and retrained them on diseases to develop its end-to-end Pharma. AI platform for target discovery, drug design, and clinical trial prediction.

Stimulants such as Ritalin and modafinil have a reputation as off-label ‘smart drugs’ that boost cognitive performance. New research suggests they have the opposite effect.

Understanding the mechanisms of interaction between plasma and microparticles is of a critical importance in various fields, including astrophysics, microelectronics, and plasma medicine. A common experimental approach for studying interactions between plasma and microparticles is to place microparticles in a flowing plasma of a gas discharge. In order to achieve a more accurate understanding of the processes occurring in such systems, scientists need fast and efficient tools for calculating forces acting on microparticles in a plasma flow.

Typically, plasma-physicists have to independently develop software tailored to a specific task, which is a significant investment of time and resources. Existing open-source programs frequently encounter challenges related to installation, documentation, and sluggish performance. A group of scientists from the JIHT, the HSE and, MIPT have developed a novel solution: a fast, open-source code which is easy to install and extensively documented.

The outcome—OpenDust—performs ten times faster than existing analogues. In order to accelerate calculations, the algorithm uses multiple GPUs simultaneously.

Researchers at the RIKEN Center for Brain Science (CBS) in Japan have discovered a set of related mutations that lead to intracranial aneurysms—weakened blood vessels in the brain that can burst at any time. The mutations all appear to act on the same biological signaling pathway, and the researchers report the first ever pharmaceutical treatment in a mouse model, which works by blocking this signal. The study was published in Science Translational Medicine.

About 5% of the population have unruptured intracranial aneurysms in blood vessels on the surface of the brain. Despite being ballooned arteries with weakened walls, intracranial aneurysms often go undetected—until a rupture leads to deadly bleeding around the brain.

Even when they are detected in advance, the only currently available treatment options involve surgery, which has its own set of risks, especially if the aneurysm is in a sensitive location. Finding other, non-surgical options is thus a high priority, and research into the origin of intracranial aneurysms has led the RIKEN CBS team to one such potential treatment.

Mitochondria that power cellular activity fragment and change shape in breast cancer cells that migrate to the brain, an adaptation that appears necessary for the cells to survive, UT Southwestern Medical Center researchers report in a new study. The findings, published in Nature Cancer, could lead to new ways to prevent brain metastases, or the spread of cells from primary tumors to the brain.

“Through mitochondrial plasticity, these cancer cells undergo metabolic reprogramming that aids their survival in the brain niche that otherwise would not be available to them. Exploiting this vulnerability could offer a way to prevent brain metastases,” said study leader Srinivas Malladi, Ph.D., Assistant Professor of Pathology at UT Southwestern and a member of the Harold C. Simmons Comprehensive Cancer Center.

Metastatic cancer, which is treated as stage IV cancer, is responsible for the majority of cancer deaths.

In short, data-driven solutions themselves are only part of the overall approach. It is the effective integration of this fast-evolving technology into existing workflows and processes that leads to successful business outcomes.

The first step to integrating AI is identifying places and processes where it can help increase efficiency or accuracy. Businesses should step back and identify their pain points, creating a list of processes that are slow, tedious, cumbersome or suffering from a lack of staff. They should also analyze where additional data or information could help make better decisions.

In the pharma industry, data-driven AI solutions have been widely adopted in sales and marketing processes. For example, by analyzing patient and physician data, electronic medical records and demographic information, AI algorithms can identify trends, patterns and insights that help sales representatives tailor their messaging and presentations to specific HCPs.