By John Salak –
The millions of Americans walking around with bipolar disease may have a treatment aid at hand without realizing it. Research indicates that smartphones, fitness trackers and other digital devices that can collect personal data can be used to detect mood episodes, helping to drive earlier and more effective care. In this way, digital devices spur bipolar treatments..
Investigators from Brigham and Women’s Hospital report that it is possible to use these devices to detect time intervals when these patients are experiencing depression or mania with high accuracy. They now believe that algorithms can be built off the data collected that will signal when treatment is needed to help offset debilitating episodes.
The development could be a boon to the nearly six million Americans who suffer from bipolar disease. A chronic psychiatric disorder characterized by extreme mood swings, including depression, mania and hypomania followed by periods of remission, bipolar disease is the sixth leading cause of disability worldwide. It also cuts patient life expectancy by nearly 10 years on average and causes up to 20 percent of sufferers to contemplate suicide, according to the Depression and Bipolar Support Alliance.
“Most people are walking around with personal digital devices like smartphones and smartwatches that capture day-to-day data that could inform psychiatric treatment. Our goal was to use that data to identify when study participants diagnosed with bipolar disorder were experiencing mood episodes,” said the study’s corresponding author Jessica Lipschitz, PhD, an investigator in the Brigham’s Department of Psychiatry.
“In the future, our hope is that machine learning algorithms like ours could help patients’ treatment teams respond fast to new or unremitting episodes in order to limit negative impact.”
Brigham’s findings are significant because the identification and treatment of new and unremitting mood episodes is essential for limiting the impact of the disease on patients’ lives.
Previous research has indicated that personal digital devices can accurately detect mood episodes, but they fell short of Brigham’s work because they did not apply methods designed for broad application in clinical settings. The research team therefore focused on using methods that could be broadly implemented in clinical practice. They also used commercially available personal digital devices, limited data filtering and passively collected and noninvasive data.
Via a new type of machine learning algorithm, Brigham researchers were able to detect clinically significant symptoms of depression with 80.1 percent accuracy and clinically significant symptoms of mania with 89.1 percent accuracy.
“Overall, results move the field a step toward personalized algorithms suitable for the full population of patients, rather than only those with high compliance, access to specialized devices, or willingness to share invasive data,” the team reported.
The next step is to apply these predictive algorithms in routine care where they could be used to improve treatment by informing clinicians when their patients are experiencing depressive or manic episodes between scheduled appointments.
