Development of objective measures for depression, bipolar disorder and dementia by quantifying facial expression, body movement, and voice data during clinical interview and daily activity utilizing wearable device

UMIN ID: UMIN000023764

Registered date:25/08/2016

Basic Information

• Recruitment status: Complete: follow-up continuing
• Health condition(s) or Problem(s) studied: 1. Patients with depressive disorder or bipolar disorder 2. Patients with dementia, mild cognitive impairment, or subjective cognitive impairment 3. Healthy volunteers
• Date of first enrollment: 2016/09/01
• Target sample size: 500
• Countries of recruitment: Japan
• Study type: Interventional
• Intervention(s): 1)Collect demographical/clinical characteristics from chart, participant and treating physician 2)Video/infrared/voice recording during a 10-minute conversation with psychiatrist and/or psychologist. Total number of recordings will be up to 10 times during the study period. Recording will be done during the doctor visit and the interval of the recording will not be fixed 3)Clinical severity assessment using rating scales as follows. Hamilton Rating Scale for Depression (HAM-D): 20 minutes* Montgomery Asberg Depression Rating Scale (MADRS): 10 minutes* Young mania rating scale (YMRS): 10 minutes* Beck depression inventory (BDI): 3 minutes* Pittsburgh sleep quality index (PSQI): 2 minutes* Clinical Dementia Rating(CDR): 15 minutes** Mini-mental Scale Examination (MMSE): 15 minutes** Wechsler Memory Scale-Logical Memory Subtest: 5 minutes** Clock drawing test (CDT): 3 minutes** Neuropsychiatric Inventory (NPI): 10 minutes** Geriatric Depression Scale (GDS): 5 minutes** (*Applied to patients with depression and bipolar disorder. **Applied to patients with dementia, mild cognitive impairment, or subjective cognitive impairment. All rating scales including * and ** will be applied to healthy volunteers) 4)To those who are willing to consent to the optional part: Wear wrist band type sensor to collect daily activity data until the next assessment. 5)except healthy volunteers are diagnosed using Structured Clinical Interview for DSM-IV-TR (SCID) any time during the follow up.

Outcome(s)

• Primary Outcome: Comprehensive severity score based on facial expression, body movement, voice, and daily activity data produced by machine learning
• Secondary Outcome: 1)Machine learning-severity score based on facial expression data 2)Machine learning-severity score based on body movement data 3)Machine learning-severity score based on voice data (mainly using the acoustic features) 4)Machine learning-severity score based on voice data (mainly using the features such as speed of speech, time to reply) 5)Machine learning-severity score based on text data 6)Machine learning-severity score based on daily activity data

Key inclusion & exclusion criteria

• Age minimum: 20years-old
• Age maximum: Not applicable
• Gender: Male and Female
• Exclude criteria: Exclusion Criteria: As patients (1) Patients whose illness can be exacerbated by interview of the study. (2) Patients who have comorbidities that can interfere with measurements in the study; such as patients with facial palsy or involuntary movement, patients with quadriplegic palsy or involuntary motion, patients with dysphonia by laryngectomy. (3) Those who are considered to be ineligible by the PI or investigators.

Related Information

• Primary Sponsor: Keio University School of Medicine
• Secondary Sponsor: Keio University Science and Technology Oizumi hospital Oizumi mental clinic Asakadai mental clinic Tsurugaoka garden hospital Nagatsuta ikoinomori clinic Sato hospital Biwako hospital Komagino hospital Asaka hospital Tokyo Institute of Technology
• Source(s) of Monetary Support: Japan Agency for Medical Research and Development (AMED)