Smartphones can differentiate bipolar from borderline personality disorder
FROM ECNP 2020
‘Mr. Jones, the doctor is ready to see your phone now.’
The app’s accelerometry and geolocation capabilities can also enhance diagnostic accuracy, as has been shown in the AMoSS study.
The geolocation analysis generates data on the places a patient has gone and how much time was spent there. Feeding that information into the machine learning model predicted the presence or absence of depression with 85% accuracy for bipolar disorder, but couldn’t predict depression at all in borderline personality disorder.
“So we get a sense that people with bipolar disorder have behavioral manifestations of their mood symptoms which are much more consistent with one another and appear to change very consistently with their mood state, whereas borderline personality disorder seems to be characterized by something that’s much more unstable and unpredictable – and we can pick up these predictive variables using our smartphones,” Dr. Saunders said.
As depressive symptoms arise in patients with bipolar disorder, affected individuals display much less day-to-day variability in movement as measured by accelerometry. These changes predicted bipolar disorder with 76% specificity and 48% sensitivity.
“That’s OK. But we can’t do that at all in people with borderline personality disorder, again highlighting the fact that behavioral manifestations and symptoms in these groups are very, very different,” Dr. Saunders observed.
In AMoSS, analysis of activity, geolocation, and distal temperature rhythms showed that the individuals with borderline personality disorder displayed evidence of delayed circadian function, with a distinctive rest-activity pattern that differed from persons with bipolar disorder. This delayed circadian function might provide a novel therapeutic target in borderline personality disorder, a condition for which there is a notable lack of effective pharmacologic and psychotherapeutic interventions.
Phone use patterns were revealing. Patients with bipolar disorder had an increased total telephone call frequency relative to the healthy controls, whereas those with borderline personality disorder used text messaging much more frequently, consistent with the notion that borderline patients have difficulty in interpersonal communication.
Smartphone-based diagnostic differentiation between bipolar disorder and borderline personality disorder isn’t ready for prime time use in clinical practice, Dr. Saunders said. This is groundbreaking work that needs to be refined and replicated in larger studies. There are important ethical and data protection issues that require attention. But patients are gung-ho. Dr. Saunders noted that participant compliance in AMoSS was “extraordinarily good,” at 82%. Moreover, even though the study lasted for 3 months, more than 60% of subjects continued filing mood reports for 12 months.
“Smartphones may also give us an improved understanding of the lived experience of people with mental health problems. That’s certainly the feedback we got a lot from patients. They enjoy using this technology. They feel it’s helpful to be able to show their clinician this is what it’s like for them,” Dr. Saunders said.
Clinical usefulness is limited
The study was interesting as a pilot, and it is technologically very innovative. However, at this stage, it is unclear how the results can be used clinically, said Igor Galynker, MD, PhD, when asked about the findings.
There is a place for using this type of technology for patients living in remote areas, for example. However, Dr. Galynker, director of the Richard and Cynthia Zirinsky Center for Bipolar Disorder in New York, said such technology should be viewed as augmentation rather than as a substitute for face-to-face treatment.
“Typically, if clinicians have enough time to speak to the patient and to take history, they can differentiate between bipolar disorder and borderline personality disorder: The former is cyclical, the latter is less so. However, this is hard to do without face-to-face contact, or when you only have 10 minutes,” said Dr. Galynker, professor of psychiatry at the Icahn School of Medicine and director of the Galynker Research and Prevention Laboratory, both at Mount Sinai in New York.
Dr. Saunders’ work is funded by the Wellcome Trust and the National Institute for Health Research. Dr. Galynker reported receiving funding from the National Institute of Mental Health and the American Foundation for Suicide Prevention. He has no other disclosures.
SOURCE: ECNP 2020. Session S21.
