Recent quotes:

First systematic review and meta-analysis suggests artificial intelligence may be as effective as health professionals at diagnosing disease -- ScienceDaily

"We reviewed over 20,500 articles, but less than 1% of these were sufficiently robust in their design and reporting that independent reviewers had high confidence in their claims. What's more, only 25 studies validated the AI models externally (using medical images from a different population), and just 14 studies actually compared the performance of AI and health professionals using the same test sample," explains Professor Alastair Denniston from University Hospitals Birmingham NHS Foundation Trust, UK, who led the research.  "Within those handful of high-quality studies, we found that deep learning could indeed detect diseases ranging from cancers to eye diseases as accurately as health professionals. But it's important to note that AI did not substantially out-perform human diagnosis."

Popular mobile games can be used to detect signs of cognitive decline -- ScienceDaily

Their research put 21 healthy participants through standard paper-based cognitive assessment tests, followed by 10-minute sessions of playing Tetris, Candy Crush Saga and Fruit Ninja over two separate periods, a fortnight apart. The three games selected were chosen because they are easy to learn, engaging for most players and involve intensive interactions using multiple gestures. Using the sensors built into the mobile phones to collect data, the team showed how users interacted with the games and illustrated a clear link between the subjects' touch gestures, or taps and swipes, their rotational gestures and their levels of cognitive performance. The study revealed the participants' ability to perform visuo-spatial and visual search tasks, as well as testing their memory, mental flexibility and attention span.

The 'pathobiome' -- a new understanding of disease -- ScienceDaily

The concept acknowledges that all organisms are in fact complex communities of viruses, microbes and other small organisms (e.g. parasites) which can interact to affect health or disease status at any given time. These complex communities continually interact with their hosts, sometimes conferring benefits (e.g. "good" bacteria in the human gut microbiome), and at other times causing harm by contributing to disease. When these communities combine to cause disease they are termed "pathobiomes" -- a recognition of their collective shift away from the healthy-state "symbiome."

Facebook posts better at predicting diabetes, mental health than demographic info -- ScienceDaily

Using an automated data collection technique, the researchers analyzed the entire Facebook post history of nearly 1,000 patients who agreed to have their electronic medical record data linked to their profiles. The researchers then built three models to analyze their predictive power for the patients: one model only analyzing the Facebook post language, another that used demographics such as age and sex, and the last that combined the two datasets. Looking into 21 different conditions, researchers found that all 21were predictable from Facebook alone. In fact, 10 of the conditions were better predicted through the use Facebook data instead of demographic information.

Facebook’s cardiologist on social media's role in health research

But at a high level, he said, “I can tell you what we do — which is really focus on public health evidence-base-driven interventions and analyses.” Facebook has a relatively flat organizational structure, he said, and there are a number of different people across the company working on different aspects of health. Abnousi, for example, isn’t closely involved in the work to crack down on vaccine misinformation, he said.

Study suggests overdiagnosis of schizophrenia: Reported symptoms of anxiety and hearing voices most common reasons for misdiagnosis by non-specialty physicians -- ScienceDaily

In speculating about other reasons why there might be so many misdiagnoses, the researchers say that it could be due to overly simplified application of criteria listed in the Diagnostic Statistical Manual of Mental Disorders, a standard guide to the diagnosis of psychiatric disorders. "Electronic medical record systems, which often use pull-down diagnostic menus, increase the likelihood of this type of error," says Margolis, who refers to the problem as "checklist psychiatry." "The big take-home message from our study is that careful consultative services by experts are important and likely underutilized in psychiatry," says Margolis. "Just as a primary care clinician would refer a patient with possible cancer to an oncologist or a patient with possible heart disease to a cardiologist, it's important for general mental health practitioners to get a second opinion from a psychiatry specialty clinic like ours for patients with confusing, complicated or severe conditions. This may minimize the possibility that a symptom will be missed or overinterpreted."

Investors have been snubbing the microbiome. That may be changing

The field needed to find some basic tools before it had a chance of developing a drug successfully, she said, like better biomarkers to determine how and where a drug was working. For example, in one paper, Synlogic scientists showed that their drug was working by tracking an isotope markers through the bacteria’s metabolic pathway and by measuring levels of a chemical produced by their bacterial “drug,” SYNB1618. “One of the challenges that microbiome companies face is that you can tell what goes in the top end, you can tell what comes out the bottom end, but you can’t tell what happens in the middle,” Brennan said during a presentation earlier this month. “There’s a lot of groundwork that’s required. Papers don’t make good drugs,” she said in an interview afterward.