Issue link: https://beckershealthcare.uberflip.com/i/1058375
38 CIO / HEALTH IT Google creates AI to detect when breast cancer spreads By Jessica Kim Cohen G oogle's new artificial intelligence al- gorithm, dubbed LYNA, accurately detects the spread of breast cancer — but the company is taking pains to highlight that the tool is meant to assist, not replace, human pathologists. LYNA, which stands for "LYmph Node Assis- tant," uses a type of AI modeled on how the human brain processes information, called "deep learning." A deep learning algorithm learns over time by extracting patterns from a data set. For Google's project, that means researchers "trained" it on pathology slides from patients with metastatic breast cancer, or the stage of breast cancer where the dis- ease has spread from the primary tumor site to nearby lymph nodes. In an Oct. 12 post on the company's research blog, Google outlined findings from two stud- ies related to LYNA, which it calls a "proof-of- concept pathologist assistance tool." e first study, published in the Archives of Pathology and Laboratory Medicine, applied the AI algorithm to two new sets of pathol- ogy slides to assess LYNA's accuracy. Google reported LYNA correctly distinguished slides with metastatic cancer from slides without the disease 99 percent of the time in both data sets. e algorithm could also pinpoint the location of cancers and other "suspicious regions" within each slide, some of which were too small to be consistently detected by the human eye. Today, a pathologist's examination of a tu- mor using a microscope is considered the "gold standard" for cancer diagnosis, accord- ing to Google's blog post, despite the reality that small metastases, or micrometastases, are difficult to detect. Based on the findings from its first study, Google's research team suggested LYNA might prove a successful tool to highlight areas of concern for hu- man pathologists to review before delivering their final diagnosis. e second study, published in e American Journal of Surgical Pathology, explored the potential clinical or workflow benefits the AI algorithm provides. Six board-certified pathologists completed a simulated clinical assessment during the study, in which they reviewed images of lymph nodes for meta- static breast cancer both with and without as- sistance from LYNA. Using the AI algorithm improved diagnostic accuracy for the physi- cians, reducing the rate of missed microme- tastases by a factor of two. e pathologists also reported that diagnos- ing micrometastases was "easier" with LYNA, according to the study results. With LYNA, the average time for a pathologist to review a slide was only one minute, compared to two minutes without the tool. "Encouragingly, pathologists with LYNA as- sistance were more accurate than either un- assisted pathologists or the LYNA algorithm itself," according to Google's blog post. "is suggests the intriguing potential for assistive technologies such as LYNA to reduce the bur- den of repetitive identification tasks and to allow more time and energy for pathologists to focus on other, more challenging clinical and diagnostic tasks." n Anthem snags former Google leader to manage AI By Morgan Haefner A nthem hired former Google leader Udi Manber to head up its artificial intelligence program, a spokesperson from the health insurer confirmed with CNBC. Mr. Manber ran engineering for Google's search products. Prior to joining Google, he served in senior roles at Amazon and Yahoo. People familiar with the matter told CNBC Mr. Manber will lead and is expected to build out Anthem's AI group. He is the first person to take the role at Anthem, and is the latest tech- nologist to move into the healthcare space. Other insurers, such as UnitedHealth Group, have posted dozens of job openings for data scientists. Health insurance startups De- voted Health and Oscar Health are also on the prowl for digital experts as they look to modernize the industry. n LabCorp joins Apple's Health Records project, increasing patient access to lab results By Jessica Kim Cohen L abCorp, a network of clinical testing laboratories, has joined Apple's Health Records project. Earlier this year, the Cupertino, Calif.-based tech giant unveiled plans to integrate patient health records into the iPhone's Health app as part of its iOS 11.3 beta rollout. The pilot program launched in January at 12 hospitals, including such leading providers as Danville, Pa.-based Geisinger and Baltimore-based Johns Hopkins Medicine. Since then, more than 100 hospitals have signed on to the project, ac- cording to Apple's tally in October. With the new feature, patients who undergo clinical testing at a LabCorp facility will have the option to access their diagnostic results from within the iPhone's Health app, along with other details of their medical history — such as allergies, immunization history and medications — from participating providers. "LabCorp on Health Records will help provide healthcare consumers with a more holistic view of their health," said David P. King, LabCorp's chairman and CEO. "Laboratory test results are central to medical decision making, and broadening access to this information will help patients take charge of their health and wellness." n