A year ago, U.S. military researchers presented an algorithm that can tell an individual how much caffeine to consume, and when, to achieve optimal alertness. Now they’ve turned the technique into a freely available tool for “designing effective strategies to maximize alertness while avoiding excessive caffeine consumption.”

Cancer patients undergoing chemotherapy often share word of their adverse reactions to the drugs in online health forums. Researchers at Stanford have used natural language processing to mine these posts, accurately flagging detrimental side effects well before clinical journals advise caution.

A convolutional neural network has proven better than traditional equations, indexes and scoring systems at predicting which hospitalized patients will face readmission not long after being sent home.  

Retail giant Walmart has joined a blockchain group that aims to track and verify prescription drugs, the company confirmed to CoinDesk.

The vast majority of healthcare executives––89%––are experimenting with emerging technologies such as AI, according to Accenture’s Digital Health Technology Vision report.

Proposed rules to mitigate one of the biggest obstacles to value-based care––interoperability––and provide patients with access to their own health information for free are being met with privacy and security concerns from industry stakeholders.

Electronic wearables that can monitor heart rates, steps and more vital signs are becoming more prevalent across the healthcare space, but the use of these devices is not all on the up and up. Instead of helping people stay on track with their health goals, meticulously tracking symptoms can actually sometimes make them feel worse, Wired reported.

Using a deep neural network equipped with all patient information relevant to diagnosing adult asthma, researchers in Japan have achieved 98% diagnostic accuracy.