Tag Archives: software
Expert wary over collecting trend of apps, sharing health data
As of 2016 there were more than 165,000 health and wellness apps available though the Apple App Store alone. According to Rice University medical media expert Kirsten Ostherr, the Food and Drug Administration (FDA) regulates only a fraction of those. Americans should be concerned about how these apps collect, save and share their personal health data, she said.
On Oct. 26 the U.S. Department of Health and Human Services will host a gathering of national experts to discuss “Data Privacy in the Digital Age.” Ostherr, who is a professor of English and director of Rice’s Medical Futures Lab, has been doing research on health and medical media for over 20 years, from “old” media like celluloid films used for medical education to “new” media like smartphone apps. She will present “Trust and Privacy in the Ecosystems of User-Generated Health and Medical Data” during a panel discussion.
“Members of the general public, including patients, have begun to play a newly important role in collecting data about health and disease,” Ostherr said. “With the rise of mobile apps and the growth of smartphone and wearable-device use, people’s daily lives have become experiments ‘in the wild.'”
The data collected through these devices offer new opportunities and challenges to researchers who want to gather information about human behavior outside the controlled settings of lab-based studies, she said. However, what the researchers can achieve with the user-generated health data relies heavily on participants’ willingness to share their data, even when doing so may not serve their own best interests.
“Part of my research is looking at ways the boundaries between medical and nonmedical environments are dissolving through the proliferation of apps that allow people to manage their own care outside of clinical settings,” she said. “In some ways those boundaries are breaking down because a lot of things that used to only happen inside of hospitals can happen outside of them now.”
Federal and state policy regulations that shape how personal health data is shared are currently in place. They set rigid boundaries between traditional clinical settings or “medical domains” and domains outside of traditional clinical settings, Ostherr said. But depending on how an app is classified by the FDA, the health-related data an app collects might not be protected.
She said apps that make medical or therapeutic claims are considered a medical device and must go through the FDA procedures for approval and regulation. For some companies, that process is worth the time and effort, because their product could become covered by insurance.
But the vast majority of apps provide “helpful hints” in response to user-entered data, such as ideas for alleviating symptoms of a migraine.
“If your app carefully sidesteps claiming any kind of medical intervention, then it’s a health and wellness app and not a medical device — and it is not regulated,” Ostherr said.
Regardless of whether an app is regulated, Ostherr said, they are all “capturing tons of personal data, some of which would be classified as personal health information if it were subject to oversight by the Health Insurance Portability and Accountability Act.”
And, she said, the likelihood that the data from the unregulated health apps makes its way back into a medical setting where a patient could benefit from a physician’s review of that data is “almost nil.”
New software can detect when people text and drive
Computer algorithms developed by engineering researchers at the University of Waterloo can accurately determine when drivers are texting or engaged in other distracting activities.
The system uses cameras and artificial intelligence (AI) to detect hand movements that deviate from normal driving behaviour and grades or classifies them in terms of possible safety threats.
Fakhri Karray, an electrical and computer engineering professor at Waterloo, said that information could be used to improve road safety by warning or alerting drivers when they are dangerously distracted. And as advanced self-driving features are increasingly added to conventional cars, he said, signs of serious driver distraction could be employed to trigger protective measures.
“The car could actually take over driving if there was imminent danger, even for a short while, in order to avoid crashes,” said Karray, a University Research Chair and director of the Centre for Pattern Analysis and Machine Intelligence (CPAMI) at Waterloo.
Algorithms at the heart of the technology were trained using machine-learning techniques to recognize actions such as texting, talking on a cellphone or reaching into the backseat to retrieve something. The seriousness of the action is assessed based on duration and other factors.
That work builds on extensive previous research at CPAMI on the recognition of signs, including frequent blinking, that drivers are in danger of falling asleep at the wheel. Head and face positioning are also important cues of distraction. Ongoing research at the centre now seeks to combine the detection, processing and grading of several different kinds of driver distraction in a single system.
“It has a huge impact on society,” said Karray, citing estimates that distracted drivers are to blame for up to 75 per cent of all traffic accidents worldwide.
Another research project at CPAMI is exploring the use of sensors to measure physiological signals such as eye-blinking rate, pupil size and heart-rate variability to help determine if a driver is paying adequate attention to the road.
Karray’s research — done in collaboration with PhD candidates Arief Koesdwiady and Chaojie Ou, and post-doctoral fellow Safaa Bedawi — was recently presented at the 14th International Conference on Image Analysis and Recognition in Montreal.