Google I/O event highlights AI for accessibility, algorithm detects depression in children's voices and more digital health news briefs

Also: Clarigent Health, Children's Home of Cincinnati launch app pilot; Demo version of ambulatory care app released for free.
By Dave Muoio
03:39 pm
Share

Google goes big on AI for accessibility. A substantial portion of yesterday’s Google I/O developer conference keynote was devoted to the tech giant’s efforts on increasing device accessibility for those with speech, vision and hearing impairments.

During its onstage presentation, the company demonstrated how artificial intelligence could record, interpret and ultimately transcribe the speech of patients with amyotrophic lateral sclerosis (ALS), stroke, traumatic brain injury or other conditions to aid communication. Other highlights included live captioning of phone conversations or online videos for the deaf, and computer vision application that uses a smartphone camera to read aloud written text for users with impaired vision or who are otherwise unable to read.

“Building for everyone also means ensuring that everyone can access our products,” Google CEO Sundar Pichai said during the keynote. “The World Health Organization estimates that 15% of the world’s population, over 1 billion people, has a disability. We believe technology can help us be more inclusive, and AI is providing us with new tools to dramatically improve experience for those with disabilities.”

Google also gave a shoutout to the diabetic retinopathy detection tool it demonstrated during last year’s conference, and hinted at early work on an AI designed for radiology image analysis.

An open ear. Researchers have detailed a novel machine learning algorithm that could identify potential signs of depression among children based on their vocal inflections, speech patterns and subjects of discussion. Detailed in a Journal of Biomedical and Health Informatics paper, the tool could help identify early signs of mental health problems within a population that often can’t articulate their condition.

"The algorithm was able to identify children with a diagnosis of an internalizing disorder with 80% accuracy, and in most cases that compared really well to the accuracy of the parent checklist,” Ryan McGinnis, a biomedical engineer at the University of Vermont and the study’s senior author, said in a statement.

Pilot explores mental health therapy app in students. Clinical decision support toolmaker Clarigent Health and the Children’s Home of Cincinnati are conducting a pilot of the former’s AI app for mental health professionals. The tech will be deployed to 20 therapists working with students in southwest Ohio, who will use the mobile app to record sessions for later linguistic and vocal characteristic analysis. The groups are aiming to obtain 400 to 600 recordings within the pilot’s first phase before escalating the effort to thousands of students later this year.

"This technology was invented in response to a need expressed by medical professionals who work with young people in crisis," Don Wright, CEO of Clarigent Health, said in a statement. "Are there early warning signs that, if detected, can guide a young person's treatment to the correct options and avert a crisis? This study is an important first step in moving the technology from the hospital and research bench, into the real world where kids are every day."

Take it for a spin. Healthcare software maker NextGen Healthcare has announced a free version of its provider-facing clinical workflow tool to enterprise clients. Available for use on iOS and Android devices, the NextGen Mobile cloud platform connects to EHR systems to help providers access a range of care coordination and documentation features, including clinical image capture, voice documentation and secure texting.

Share