An algorithm that examined heart range changes during sleep distinguished people with depression from healthy control subjects with high accuracy, according to a study published in BMC Psychiatry.
“The heart rate profiling algorithm classified individuals with an accuracy of 79.9%. Specifically, the algorithm was able to detect 82.8% of the depression cases, and rule out 77.0% of healthy controls,” researchers wrote. “In comparison, the detection rate of depression amongst primary care practitioners is thought to be approximately 47%.”
The algorithm was created using machine-learning methods based on polysomnograms for 664 people with depression and 529 control subjects who were mentally healthy. Researchers then tested the validity of the algorithm by using it to categorize 174 additional people as having depression or not. The algorithm’s categorizations were compared to medical record diagnoses.
In addition to achieving an overall classification accuracy of nearly 80%, the algorithm demonstrated high sensitivity across subgroups based on age, sex, depression severity, additional psychiatric disorders, cardiovascular disease, and smoking status.
“This study demonstrates, for the first time, that changes in heart rate across sleep-wake states may be valid physiological markers for the identification of depression in a sample of people with sleep complaints,” researchers wrote.
Using specific physiological variables as depression biomarkers could also help emphasize the link between mental and physical health to the public, they added.
“This may contribute to reducing the stigma associated with depression,” researchers observed, “lifting some social barriers to accessing psychiatric treatment, and allowing for more holistic patient care.”