Experts see advances in AI helping diagnose, find cures for hard-to-treat diseases

The Japan Times

Scientists from Harvard and the University of Vermont developed a machine learning tool -- a type of AI that enables computers to learn without being explicitly programmed -- to better identify depression by studying Instagram posts, suggesting "new avenues for early screening and detection of mental illness." NYU researchers analyzed medical and lab records to accurately predict the onset of dozens of diseases and conditions including Type 2 diabetes, heart or kidney failure and stroke. When IBM's Watson computing system won the TV game show "Jeopardy" in 2011, "there were a lot of folks in health care who said that is the same process doctors use when they try to understand health care," said Anil Jain, chief medical officer of Watson Health. Research firm CB Insights this year identified 106 digital health startups applying machine learning and predictive analytics "to reduce drug discovery times, provide virtual assistance to patients, and diagnose ailments by processing medical images."

Google working with Aravind Eye Hospital to train its AI in diabetic retinopathy screening FactorDaily


India's largest eye care provider, Aravind Eye Hospital, has been quietly working for over four years with Google on a project to use artificial intelligence (AI) in ophthalmology. "With AI, we will be able to grade diabetic retinopathy to a certain level of identification, mainly for screening" -- Dr R Kim, chief medical officer at Aravind Eye Hospital "With AI, we will be able to grade diabetic retinopathy to a certain level of identification, mainly for screening. It will be seen at a patient care level, a diabetes management level," said Anand Sivaraman, director of Bengaluru-based Remidio, maker of a smartphone-based ophthalmic imaging system. It will be seen at a patient care level, a diabetes management level" -- Anand Sivaraman, director, Remidio However, Sivaraman said the challenge lies in making sure there are no false negatives, which could deprive patients of treatment or consultation.

Provider Coalition to Use Machine Learning for Type 1 Diabetes


"We can no longer be a'wait and see' industry," D'Avolio said. "Instead we're pulling real insights from disparate data sources and using these to inform clinical care. We're thrilled to partner with these leading institutions to serve such a critical patient population, and believe that the work this new learning health system will accomplish could fundamentally change how we care for people with T1D and their families."

Leading Institutions to Focus on Improving Type 1 Diabetes Care with Machine Learning


Children's Mercy is advancing care for children with diabetes through the Children's Mercy Diabetes Center by providing comprehensive care for children as well as support and resources for family members. About Joslin Diabetes Center Joslin Diabetes Center is world-renowned for its deep expertise in diabetes treatment and research. Joslin is an independent, non-profit institution affiliated with Harvard Medical School, and one of only 11 NIH-designated Diabetes Research Centers in the U.S. About Cyft Based in Cambridge, Mass., Cyft partners with leading care organizations to identify opportunities to optimize care management efforts for chronic / complex, behavioral health, and dual-eligible populations. About the Helmsley Charitable Trust The Leona M. and Harry B. Helmsley Charitable Trust aspires to improve lives by supporting effective organizations in health and select place-based initiatives.

'Alexa, what's my blood sugar level and how much insulin should I take?'

Los Angeles Times

Apple, Google and Amazon have announced or are reported to be developing cutting-edge technologies for managing diabetes, one of the fastest-growing chronic illnesses, affecting more than 420 million people worldwide. The latest diabetes-related tech endeavor to be announced is the Alexa Diabetes Challenge, which focuses on finding ways for the Amazon Echo smart speaker -- and its Alexa digital assistant -- to assist people with Type 2 diabetes in living healthier lives. CNBC reported last month that Apple Chief Executive Tim Cook was spotted "wearing a prototype glucose-tracker" with his Apple Watch. The global market for diabetes care will be worth $35.5 billion by 2024, according to Grand View Research, and this represents a natural business opportunity for anyone in the information technology space.

Curatio wants to be Tinder plus Facebook for health and disease communities


"It's a pain point every single person has at some point in their lives, for themselves or for a family member or friend," said Curatio founder Lynda Ganzert-Brown. "It's a pain point every single person has at some point in their lives." There's also an AI concierge to answer questions about health information and a section for personal disease management and health tracking. So there are a lot of moving parts, especially when you consider that there are various different communities on Curatio: menopause, traumatic brain injury, heart disease, the blood disease Thalassemia, Crohn's disease and colitis, Type 1 diabetes, and a community for caregivers.

How Machine Learning Is Helping Us Predict Heart Disease and Diabetes


For example, by preventing hospitalizations in cases of just two widespread chronic illnesses -- heart disease and diabetes -- the United States could save billions of dollars a year. The hospitals provide patients' anonymized electronic health records (EHRs) that contain all of the information the hospital has about each patient, including demographics, diagnoses, admissions, procedures, vital signs taken at doctor visits, medications prescribed, and lab results. Using the Framingham Study 10-year cardiovascular risk score, one can predict hospitalizations with an accuracy of about 56%, which is substantially lower than the 82% rate we achieved. My team has developed methods to automatically titrate medications in intensive care units in response to the patient's condition.

Three Ways Machine Learning Will Drive Behavior Change in Mobile Health


In this case, I'm referring to machine learning algorithms that create behavioral profiles of end-users based on their actions in the physical world. Likewise, if the medication adherence app regularly wakes the user from a deep sleep in the morning, the user will likely delete it. Because they know a user's habits, activities, and meaningful locations, they issue "moment-based" notifications. The fact that mobile apps and fitness trackers automatically log people's activities is an important step in engaging people in their own health.

How artificial intelligence is going to cure America's sick health care system


Phinney and Volek wrote two books together about low-carbohydrate diets and published scientific papers describing how constant adjustments to diet and lifestyle can reverse diabetes in many patients. On the back end, Virta hires doctors who get streams of updates from Virta's software and use the data to help them make decisions about how to adjust each patient's diet and medications or anything else that might affect that person's health. AI software learns about the patient and sends a stream of tips and information intended to help the diabetic manage the disease and stay out of hospitals. "If we want to massively lower health care costs, we need to figure out how to address metabolic health issues [like diabetes] at their core," Inkinen says.

Science and Technology links (May 18th, 2017)


And, of course, you and I cannot have access to China's Sunway TaihuLight whereas, for the right price, Google gives us access to its computing pods. However, it looks like Google is within striking distance of matching the human brain in raw computing power with a single rack of computers. Even though I am not diabetic (to my knowledge), I would love an Apple watch that monitors my blood glucose. There are countries with low fertility but high longevity (e.g., Japan) and countries with high fertility and short lives (e.g., many countries in Africa).