AI-based Multi-center Research on Identification/Classification/Aided Diagnosis of Mood Disorder

First Affiliated Hospital of Zhejiang University960 enrolled

Overview

At present, diagnosis and recognition of depression and bipolar disorder are mainly based on subjective evidence such as clinical interview and scale evaluation. The corresponding diagnosis basis has some shortcomings, such as poor diagnostic reliability and failure in early identification of bipolar disorder. Therefore, it is of great significance to explore objective diagnostic indicators to remedy the deficiencies. Therefore，the investigators collect psychological and physiological information data of patients with bipolar disorder and depression.Then the investigators aim to construct and verify the multidimensional emotion recognition model to analyze the personality characteristics, negative emotions and cognitive reactions of different individuals, and form a systematic accurate recognition and evaluation tool.

Study Type

OBSERVATIONAL

Enrollment

960

Conditions

Bipolar Disorder Depression Major Depression

Eligibility

Sex: ALLMin age: 15 YearsMax age: 55 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: 1. Age 15-55, regardless of gender; 2. The brief International Neuropsychiatric Interview Chinese version (MINI) was used to meet the diagnostic criteria for DSM-IV-TR depressive disorder or bipolar disorder (type I); 3. Total score of Hamilton Depression Scale (HAMD-17) ≥17, and Young's Manic Scale (YMRS) ≤6; 4. Junior high school or above. Exclusion Criteria: 1. The patient conforms to DSM-IV schizophrenia and related spectrum disorders. 2. The patient has a history of severe head trauma (loss of consciousness for more than 5 minutes), current or previous history of epilepsy, intracranial hypertension, or other serious neurological diseases; 3. Had a history of alcohol or psychoactive substance abuse/dependence in the 6 months prior to the test; 4. Those considered unsuitable for inclusion by the researcher.

Outcomes

Primary Outcomes

facial action unit detection

The research recruits subjects to look at pictures and videos and then use cameras to record facial microexpressions. Finally, the research uses machine learning methods to analyze facial micro-expressions. Facial micro-expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, typically found in a high-stakes environment.

Time frame: Baseline

event-related potentials

An electroencephalogram (EEG) is a test that measures electrical activity in the brain using small, metal discs (electrodes) attached to the scalp. Brain cells communicate via electrical impulses and are active all the time, even during asleep. This activity shows up as wavy lines on an EEG recording. The research recruits subjects to look at videos and pictures and use electroencephalography to record event-related potentials. Finally, we use time domain analysis and frequency analysis to get the results

Time frame: Baseline

Galvanic skin response

The skin also has electrical activity, which is in constant, slight variation, and can be measured and charted. The skin's electrical conductivity fluctuates based on certain bodily conditions, and this fluctuation is called the galvanic skin response.We recruited subjects to watch videos and pictures and record galvanic skin response. Finally, we use time domain analysis and frequency analysis to get the results

Time frame: Baseline

AI-based Multi-center Research on Identification/Classification/Aided Diagnosis of Mood Disorder

Overview

Conditions

Eligibility

Locations (1)

Outcomes

Primary Outcomes

Central Contacts