Editor’s Note: This is a trend that we’ve been discussing at Activist Post for some time – predictive modeling in healthcare. A series of apps have been developed that are aimed at tracking mental health and “well being” in real-time. Some of these apps are even designed to connect with medical staff to determine if an intervention is required. Please read the following articles from Nicholas West in addition to the one posted below from Anti-Media in order to get a full picture of what this means for the future of healthcare and insurance, as well as enhanced social media surveillance.
- Predictive Medicine Apps In Development to Judge Mental Health
- Researchers Developing Smartphone Mental Health Surveillance App For University Students: iSee
Written by Anti-Media Team
“Who is going to be accessing the data? Who is going to be scanning the data? How will it be used? These are really incredibly difficult questions. Who is going to be giving permission to study what is supposedly private information?”
Those “incredibly difficult questions” are ones patients may soon have to ask themselves, Dr. Igor Galynker, associate chairman of research at Mount Sinai Beth Israel’s psychiatry department in New York, told CBS News Tuesday. That’s because a recent study has shown that current software may be better at detecting depression in patients than actual human doctors.
The study, conducted by Andrew Reece, a graduate student at Harvard University’s psychology department, and Chris Danforth, a professor at the University of Vermont College of Engineering and Mathematical Sciences, aimed to discover how accurately clinical depression could be detected through visual cues in the photos people post to social media.
Reece and Danforth asked 166 people to share their Instagram feeds and their mental health histories. All told, the pair was able to collect nearly 44,000 photos from volunteers, along with answers to individual questionnaires.
They then scanned the photos using software designed to look for visual signs of depression. Based on volunteers’ mental health history, the software was able to accurately diagnose depressed individuals 70 percent of the time. By comparison, previous research suggests human physicians are correct only about 42 percent of the time.
Reece told CBS News that the study results are preliminary and much more testing must be done, but he foresees machine learning eventually being an aid to doctors as opposed to a replacement for them:
It’s clear that depression isn’t easy to diagnose, and the computational approach we’ve taken here may end up assisting, rather than competing with, health care professionals as they seek to make accurate mental health assessments.
Reece says photos of depressed individuals in the study tended to contain fewer people — hinting at limited social interaction — and were often edited with filters that drain the color out of images.
“Our results suggest that depression quite literally makes people see their world through a darker, grayer lens,” he told CBS News.
Dr. Galynker says that makes perfect sense.
“There are reasons why depression is called blue, and why people associate red with raging, and why people say depression is like a dark or black cloud,” he said. “Patients with depression choose to wear darker colors. They generally avoid bright stimulation altogether.”
But patients consenting to be treated through machine learning technology, even just in part, would have to wrestle with tough questions regarding privacy, as Dr. Galynker intimated to CBS News — and as the outlet noted in the closing of its article on Tuesday:
More than 500 participants initially were recruited for the study, the researchers noted, but many dropped out because they would not consent to sharing their social media data.