2 . A robot created by Washington State University (WSU) scientists could help elderly people with dementia (痴呆) and other limitations live independently in their own homes.

The Robot Activity Support System, or RAS, uses sensors installed in a WSU smart home to determine where its residents are, what they are doing and when they need assistance with daily activities. It navigates (定位) through rooms and around obstacles to find people on its own, provides video instructions on how to do simple tasks and can even lead its owner to objects like their medication or a snack in the kitchen.

“RAS combines the convenience of a mobile robot with the activity detection technology of a WSU smart home to provide assistance in the moment, as the need for help is detected,” said Bryan Minor, a postdoctoral researcher in the WSU School of Electrical Engineering and Computer Science.

Currently, an estimated 50 percent of adults over the age of 85 need assistance with every day activities such as preparing meals and taking medication and the annual cost for this assistance in the US is nearly $2 trillion. With the number of adults over 85 expected to triple by 2050, researchers hope that technologies like RAS and the WSU smart home will relieve some of the financial strain on the healthcare system by making it easier for older adults to live alone.

RAS is the first robot researchers have tried to incorporate into their smart home environment. They recently published a study in the journal Cognitive Systems Research that demonstrates how RAS could make life easier for older adults struggling to live independently.

“While we are still in an early stage of development, our initial results with RAS have been promising,” Minor said. “The next step in the research will be to test RAS’ performance with a group of older adults to get a better idea of what prompts, video reminders and other preferences they have regarding the robot.”

3 . Google previously announced successful tests of machine learning systems designed to assist doctors. In one case, Google reported AI had examined eye diseases with equal accuracy to doctors. Other tests showed that machine learning can be used to study large amounts of patient data to predict future medical events.

Now the company has published two new studies showing a high level of success in identifying metastatic breast cancer. Metastatic means that cancer has spread from its main area to other parts of the body. Metastatic breast cancer is one of the deadliest, causing about 90 percent of all breast cancer deaths worldwide.

In metastatic breast cancer patients, the cancer often travels to nearby lymph nodes(淋巴结). Usually doctors examine lymph node tissue under a microscope to see whether cancer is present. Google notes that previous studies have shown that up to one-fourth of metastatic lymph node classifications end up being changed after a second examination. In addition, studies show that small metastatic material can be missed up to 67 percent of the time when examinations happen under extreme time restrictions.

Google says it created a mathematical algorithm(算法). The algorithm, called Lymph Node Assistant, is trained to find characteristics of tissue affected by metastatic cancer. When the system examined tissue images(图像), it was able to differentiate between metastatic cancer and non-cancer 99 percent of the time. In addition, the Lymph Node Assistant is highly effective at finding the positions of the cancers. Some of these positions would be too small for doctors themselves to identify. The research also showed that the algorithm method can reduce the usual time needed to examine the disease by about 50 percent.

But Google makes clear the AI-based system is not meant to replace the work of medical professionals. Instead, it is designed to reduce the number of false identifications and help doctors work faster and more effectively.