FDA


Autonomous Robots Coming To U.S. Hospitals

#artificialintelligence

The FDA approved the country's first human-interacting autonomous robot for hospitals on Thursday. The RP-VITA, made by iRobot (best known to consumers as the makers of the Roomba) and InTouch Health, is a human-sized telepresence robot which allows doctors to remotely interact with hospital patients. The robot can navigate hospital corridors autonomously, while medical professionals talk and interact with patients through a special iPad app. The Food and Drug Administration has given the RP-VITA full 510(k) clearance for hospital use.


Healthcare Industry Will Stagnate Without AI – Know Why! - HIE Answers

#artificialintelligence

In healthcare, the opportunity for AI is not just limited to making doctors and medical providers more competent in their work; in fact, it's about saving lives and making the lives of the patients better. It enhances the digital healthcare experiences of patients by offering them conversational and personalized engagement. Moreover, doctor's efforts will be greatly supported, especially when conducting differential diagnosis and evidence-based treatment and precision medicine practice using artificial intelligence with IBM's Watson. Whether it is a voice-based medical intelligence system for remotely monitoring a patient, or diagnosing disease symptoms, or sending alerts for medical appointments and medications and more.


AI diagnostics are coming

#artificialintelligence

Earlier this year, artificial intelligence scientist Sebastian Thrun and colleagues at Stanford University demonstrated that a "deep learning" algorithm was capable of diagnosing potentially cancerous skin lesions as accurately as a board-certified dermatologist. Unlike more-traditional vision software, where a programmer defines rules--for example, a stop sign has eight sides--in deep learning the algorithm finds the rules itself, but often without leaving an audit trail to explain its decisions. The FDA required Arterys to do extensive testing to make sure the results from its algorithm were on par with those generated by physicians. These covered 2,032 different diseases and included 1,942 images of confirmed skin cancers.