By analyzing patients’ reactions to treatment, Oncohost Ltd.’s proteomics-based platform enables earlier prediction of paradoxical responses to immunotherapy that promote tumor growth in certain cancers. The artificial intelligence-powered host response profiling platform, called Prophet, could help identify the best combination of therapies and minimize adverse effects from treatments that are unlikely to be beneficial.

Castle Biosciences Inc.'s Decisiondx Diffdx-Melanoma test is now commercially available to help dermatopathologists better characterize melanocytic lesions. About 15% of suspicious pigmented skin lesions cannot be definitively determined to be benign or malignant using common methods. The new gene expression profile test reduces the number of indeterminate results by more than 70%.

Tencent Holdings Ltd. has launched two med-tech solutions to facilitate data sharing and management with artificial intelligence capabilities, marking an additional step into the smart health care realm for the company. The Chinese tech giant unveiled the two products at the 83rd China International Medical Device Expo Oct. 20.

A new tool for mobile devices can diagnose stroke as accurately as an emergency medicine specialist in just minutes, enabling patients to get brain-saving therapies in time for maximum benefit. According to researchers from Pennsylvania State University and Houston Methodist Hospital, the artificial intelligence (AI)-based tool could counterbalance physician biases, reducing both overuse of CT scans and underdiagnosis of mild and moderate stroke.

Researchers at Ontario’s University of Waterloo have developed a palm-sized device that uses radio waves to read blood glucose levels, as well as artificial intelligence (AI) software to get near instantaneous results.

Aidoc Inc., a provider of artificial intelligence (AI) solutions in radiology, has won U.S. FDA clearance to market the first software solution for flagging and triaging incidental pulmonary embolism (PE). The AI technology, which includes triaging and notification algorithms, is an “always on” technology that analyzes chest CT scans in real time and alerts the radiologist to any potentially abnormal findings – possibly speeding up diagnosis by hours.

Patient engagement is increasingly the order of the day in the device development process as the U.S. FDA has made clear, a consideration that drove the Oct. 22 FDA advisory hearing. A patient representative said patients want to take part as early as possible in the development process for software as a medical device (SaMD), and Pat Baird, director of global software standards for Royal Pillips NV, said industry is very much open to ideas about bringing the patient perspective on board earlier in that process.

Researchers at Israel’s Ben-Gurion University have launched a machine learning platform that aims to streamline the clinical trial process using predictive analytics. The technology has been licensed to Panacea, a startup company formed by BGN Technology.

The U.S. FDA cleared Ezra AI Inc.'s artificial intelligence (AI) system for prostate cancer and its cloud-based picture archiving and communication system (PACS) that enables radiologists to use the Prostate AI from their browser. The New York-based company’s Prostate AI is the first prostate-focused artificial intelligence system to gain clearance. The Prostate AI accurately quantifies prostate volume, lesion size, and renders 3D volumes of the prostate gland and lesions.