User login
A heart rate–profiling algorithm shows promise at distinguishing differences in heart rate patterns during sleep between people with depression and healthy controls, research shows.
The algorithm was modeled using machine learning based on 1,203 polysomnograms from either people with depression or healthy controls, according to Mysa Saad, of the sleep research unit of the Royal’s Institute of Mental Health Research in Ottawa, and associates. That final algorithm was then tested on a new sample of 174 individuals (87 controls, 87 with depression) to categorize each person as either depressed or not depressed. This result was compared with medical record diagnoses. The study was published in BMC Psychiatry.
Compared with the control group, and in overall time. The algorithm incorrectly identified 15 patients with depression as being in the control group, and incorrectly identified 20 controls as having depression. The overall accuracy was 79.9%, with a sensitivity of 82.8% and a specificity of 77%.
“In addition to providing an improved biological underpinning for the diagnosis of depression, this [tool] could possibly offer supplemental information to psychiatric clinical assessment, and objective measures for early screening. Moreover, the use of distinct physiological variables as biomarkers of depression may help emphasize the interactions between mental and physical health. This may contribute to reducing the stigma associated with depression, lifting some social barriers to accessing psychiatric treatment, and allowing for more holistic patient care,” the investigators concluded.
Medibio provided partial funding for the salaries of research assistants; no other conflicts of interest were reported.
SOURCE: Saad M et al. BMC Psychiatry. 2019 Jun 7. doi: 10.1186/s12888-019-2152-1.
A heart rate–profiling algorithm shows promise at distinguishing differences in heart rate patterns during sleep between people with depression and healthy controls, research shows.
The algorithm was modeled using machine learning based on 1,203 polysomnograms from either people with depression or healthy controls, according to Mysa Saad, of the sleep research unit of the Royal’s Institute of Mental Health Research in Ottawa, and associates. That final algorithm was then tested on a new sample of 174 individuals (87 controls, 87 with depression) to categorize each person as either depressed or not depressed. This result was compared with medical record diagnoses. The study was published in BMC Psychiatry.
Compared with the control group, and in overall time. The algorithm incorrectly identified 15 patients with depression as being in the control group, and incorrectly identified 20 controls as having depression. The overall accuracy was 79.9%, with a sensitivity of 82.8% and a specificity of 77%.
“In addition to providing an improved biological underpinning for the diagnosis of depression, this [tool] could possibly offer supplemental information to psychiatric clinical assessment, and objective measures for early screening. Moreover, the use of distinct physiological variables as biomarkers of depression may help emphasize the interactions between mental and physical health. This may contribute to reducing the stigma associated with depression, lifting some social barriers to accessing psychiatric treatment, and allowing for more holistic patient care,” the investigators concluded.
Medibio provided partial funding for the salaries of research assistants; no other conflicts of interest were reported.
SOURCE: Saad M et al. BMC Psychiatry. 2019 Jun 7. doi: 10.1186/s12888-019-2152-1.
A heart rate–profiling algorithm shows promise at distinguishing differences in heart rate patterns during sleep between people with depression and healthy controls, research shows.
The algorithm was modeled using machine learning based on 1,203 polysomnograms from either people with depression or healthy controls, according to Mysa Saad, of the sleep research unit of the Royal’s Institute of Mental Health Research in Ottawa, and associates. That final algorithm was then tested on a new sample of 174 individuals (87 controls, 87 with depression) to categorize each person as either depressed or not depressed. This result was compared with medical record diagnoses. The study was published in BMC Psychiatry.
Compared with the control group, and in overall time. The algorithm incorrectly identified 15 patients with depression as being in the control group, and incorrectly identified 20 controls as having depression. The overall accuracy was 79.9%, with a sensitivity of 82.8% and a specificity of 77%.
“In addition to providing an improved biological underpinning for the diagnosis of depression, this [tool] could possibly offer supplemental information to psychiatric clinical assessment, and objective measures for early screening. Moreover, the use of distinct physiological variables as biomarkers of depression may help emphasize the interactions between mental and physical health. This may contribute to reducing the stigma associated with depression, lifting some social barriers to accessing psychiatric treatment, and allowing for more holistic patient care,” the investigators concluded.
Medibio provided partial funding for the salaries of research assistants; no other conflicts of interest were reported.
SOURCE: Saad M et al. BMC Psychiatry. 2019 Jun 7. doi: 10.1186/s12888-019-2152-1.
FROM BMC PSYCHIATRY