LONDON – Behold.ai Ltd. has secured U.S. FDA 510(k) approval for use of its Red Dot image recognition algorithm in the automatic diagnosis of life-threatening pneumothorax (collapsed lung). The product completes the analysis immediately, sending an alert to the radiologist as soon as an X-ray is taken. “It does in 30 seconds what would normally take up to 30 minutes,” said Simon Rasalingham, CEO of London-based Behold.ai.
Nantomics LLC, of Culver City, Calif., reported that research based on the company’s deep learning system has been published in a peer-reviewed journal, highlighting the algorithm’s ability to discern which mutation drives a patient’s breast cancer. The company said their approach is a rapid and cost-effective way to establish the breast cancer subtype, thus giving clinician and patient alike a good understanding of which therapies would be ineffective for that cancer and maximizing the chances for a cure.
TORONTO – Calgary, Alberta-based Orpyx Medical Technologies Inc. has launched a sensory insole with remote patient monitoring to prevent potentially fatal diabetic foot ulcers (DFU) and neuropathy-related ulcers. According to Orpyx CEO Breanne Everett, development of the Orpyx SI sensory insole system follows years of study on how DFUs occur and how best to share information with patients and doctors so they can react quickly to first signs of the condition.
Dublin-based Medtronic plc is highlighting results from the MARVEL 2 study showing that an investigational set of algorithms in the Micra Transcatheter Pacing System (TPS) helps those with normal sinus node function and atrioventricular (AV) block.
Deciding which patients should go into the intensive care unit (ICU) after surgery is a difficult call and typically made entirely at the surgeon's discretion. The result is that surgeons typically err on the side of caution by putting more post-operative patients in the ICU than necessary. To aid in better ICU decision-making, physicians at New York University Langone Hospital System (NYU Langone) developed a machine learning algorithm that combs through a patient's electronic medical record to identify relevant factors to determine if they needed the ICU after surgery.
The U.S. FDA has cleared the way for Physiq Inc., of Naperville, Ill., to market its continuous ambulatory respiratory rate algorithm, adding to the company's portfolio of cloud-based analytics for biopharma and health insurance companies. The 510(k) notification will allow Physiq to boost its higher-level artificial intelligence (AI) platform with validated vital signs inputs.
HONG KONG – Olive Healthcare Inc., a South Korean biotech startup, said its abdominal fat scanner Bello has received an FDA approval to sell the device in the U.S. The company said it plans to launch the scanner in the country this December, after a market test. The miniature device is portable with a weight of 3.8 oz (107 g), measuring 3.9 inches (10 centimeters) long, 3.1 inches wide and 1.9 inches high.
Deep learning algorithms developed at the Memorial Sloan Kettering Cancer Center (MSK) were able to distinguish prostate, skin and breast cancer with nearly perfect accuracy in a recent clinical trial. The technology has already been licensed exclusively by New York-based startup Paige.AI, which snapped up a $25 million series A early last year to continue to advance it.
Getting on top of the persistent HIV epidemic requires getting ahead of new cases, but only about 7% of at-risk patients have been advised of a prophylactic drug regime approved by the FDA seven years ago. Two new studies appearing in The Lancet HIV suggest that an algorithm that uses electronic health record (EHR) data can help physicians identify their at-risk patients who are good candidates for pre-exposure prophylaxis (PrEP), thus improving the odds that modern medicine might finally put an end to the scourge of acquired immunodeficiency syndrome.
A fast response with cardiopulmonary resuscitation (CPR) for cardiac arrest victims can save their lives, but older adults often are alone in their home or a bedroom when symptoms strike. Researchers at the University of Washington (UW) have developed a machine learning-based system that listens to ambient audio via dedicated smart speakers or smartphones for agonal breathing, the distinctive sound that a person in cardiac arrest makes.