The Official Webpage for Turkish Audio-Visual Bipolar Disorder Database
Bipolar disorder (BD) is a mental health condition that causes extreme mood swings from elevated (mania, hypomania) to diminished state (depression), as well as mixed episodes, where depression and manic symptoms occur together. Its diagnosis is performed through a set of medical examinations administered by the psychiatrist but may require lengthy observations of the patient as there is no comprehensive test. There is a lot of co-morbidity with other mental disorders including, but not limited to, any anxiety disorder, conduct disorder, and substance use disorder. The disease affects 2% of the population, sub-threshold forms (recurrent hypomania episodes without major depressive episodes) affect an additional 2%, and together, the lifetime prevalence estimates are 4.4%. It is ranked as one of the top ten diseases of disability-adjusted life year indicator among young adults, and as the 17th leading source of disability among all diseases worldwide.
Diagnosis of mental health disorders rely on medical examinations administered by psychiatrists and reports from patients and their relatives or friends. But there is a need for more systematic and objective diagnosis methods, for remote treatment and diagnosis approaches assisted using automated methods. It is possible to collect behavioral data from people during their everyday lives, which creates an opportunity to create tools to monitor the symptoms of the patients for longer periods, screen patients before they see the psychiatrists, assist clinicians in the diagnosis, and capture patient behaviors in situations where they cannot act or hide the symptoms.
Aim
A corpus is collected from 46 patients and 49 healthy controls at Erenköy Psychiatric and Neurological Diseases Training and Research Hospital, University of Health Sciences, İstanbul with prior approval from the hospital's Ethics Committee. The core aim of the efforts on the corpus is to find biological markers/predictors of treatment response via signal processing and machine learning techniques to reduce treatment resistance. During treatment period, these biological markers can also help early detection of relapses. These discriminative markers are intended for early recognition of the bipolar disorder. Collectively, they are expected to provide an insight for personalized treatment of bipolar patients.
According to the informed consents and the University Ethics Committee approval, the deadline to use the dataset is 31-12-2022. Thus, we can no longer share the dataset. Any researchers having the dataset should completely remove the dataset from their computers. The results that are obtained up to this deadline can later be published.