Last year, artificial intelligence (AI)-focused Caption Health Inc. won the U.S. FDA’s nod for software that guides untrained clinicians step-by-step in providing a cardiac ultrasound exam, a process normally performed by a highly skilled specialist. Now, the Brisbane, Calif.-based company has published data showing nurses without prior ultrasound experience who used Caption Guidance software captured ultrasound images of diagnostic quality to assess known cardiac conditions.

Emitbio Inc., a life science company developing light-based therapies, is seeking emergency use authorization (EUA) from the U.S. FDA for its investigational device to treat mild to moderate COVID-19 infection at home. The portable, hand-held device works by directing precise wavelengths of visible light to the back of the throat and surrounding tissues. It is not yet available for sale in the U.S.

An artificial intelligence (AI) algorithm developed by Geisinger researchers that uses echocardiogram videos predicted all-cause mortality at one year more accurately than three out of four expert cardiologists and other predictors commonly used in clinical practice, a study in Nature Biomedical Engineering demonstrated.

As COVID-19 variants have emerged, so have questions about the effectiveness of tests for infection. While the risk of mutations significantly limiting their ability to detect the novel coronavirus is thought to be relatively low, companies that make COVID-19 tests are moving quickly to enhance and revalidate their products.

By mid-January 2021, the U.K., South Africa and Brazil had confirmed that “variants of concern” were driving massive surges in COVID-19 cases in their countries. Once alerted, other nations found these troubling strains rapidly multiplying within their populations as well. At the time, the world had reported 90 million cases, creating abundant opportunities for the coronavirus to mutate. Of those cases, the virus in just 360,000 had been sequenced – and nearly all of them from just a handful of countries.

As of the end of January, SARS-CoV-2 has demonstrably infected more than 100 million individuals globally. It has killed more than 2 million. And the long-term sequelae of COVID infections – to say nothing of the health consequences of grief, social isolation and widespread economic distress – are still unfolding and will be for years to come.

KRAS is the most frequently mutated oncogene in solid tumors in general, and in lung tumors in particular. There are more patients whose lung tumors are driven by KRAS mutations than by ALK, Ros, Ret and TRK alterations. Combined. And after 40 years, they look to be getting a targeted therapy, or even two.

Mckesson Corp. has brought together several oncology organizations, life sciences companies, and patient advocacy groups to increase understanding of non-small-cell lung cancer (NSCLC) and leverage targeted therapies to improve outcomes. The Molecularly Informed Lung Cancer Treatment in a Community Cancer Network: A Pragmatic Consortium (MYLUNG) study will observe and analyze 12,000 community-based, metastatic NSCLC patients to learn more about barriers to molecular testing for targeted therapies, how those therapies are being used, and to expand opportunities for participation in clinical trials.

The Human Skin Cell Atlas, comprising transcriptomes of 528,253 single cells, shows that cellular processes involved in skin development in embryos are reactivated in inflammatory skin diseases. In addition to suggesting potential new drug targets for atopic dermatitis and psoriasis, the transcriptomes provide a new route to understanding other inflammatory diseases, and provide a template for culturing skin for wound repair, according to the authors of a paper published in the Jan. 22, 2021, issue of Science.

Using Rhythm AI Ltd.'s stochastic trajectory analysis of ranked signals (STAR) mapping system with pulmonary vein isolation terminated and eliminated recurrence of persistent atrial fibrillation (AF) at much higher rates than other ablation procedures in a study published in the Journal of Cardiovascular Electrophysiology. The artificial intelligence-driven STAR mapping process collects and analyzes thousands of heart signals to precisely identify the areas of the heart responsible for the errant electrical signals causing atrial fibrillation, enabling more thorough and accurate ablation.