Correlation of Audiovisual Features With Clinical Variables and Neurocognitive Functions in Bipolar Disorder, Mania

The aim of this study is to show the physiological changes during manic episode in bipolar mania how much they differentiate from remission and healthy control. Relation of audio-visual features as physiological changes and cognitive functions and clinical variables will be searched. The aim is to find biologic markers for predictors of treatment response via machine learning techniques to be able to reduce treatment resistance and give an idea for personalized treatment of bipolar patients.

Study Overview

• Status: Completed
• Conditions: Artificial Intelligence; Bipolar Disorder, Manic; Neurocognition; Treatment Resistant Disorders; Affective Computing; Multi- Modal Analysis
• Intervention / Treatment: Drug: Ongoing treatment for bipolar mania; Diagnostic test: Audiovisual recording during guided presentation

Detailed Description

The objective of this research protocol is to find audio-visual features which differentiates bipolar mani/ remission/ health/ simulation and predicts treatment response earlier and detect neurocognitive changes during mania/ remission and difference from the healthy control. During hospitalization in every follow up day (0th- 3rd- 7th- 14th- 28th day) and after discharge on the 3rd month, presence of depressive and manic features for patients was evaluated using Young Mania Rating Scale(YMRS) and Montgamery- Asberg Depresyon Scale (MADRS). Audiovisual recording is done by a video camera in every follow up day for patients and for healthy controls which includes also depression and mania simulation. Cambridge Neurophysiological Assessment Battery (CANTAB) were administered to both groups( for patients both in the manic phase and in the remission) to assess neurocognitive functions.

• Study Type: Observational
• Enrollment (Actual): 89

Contacts and Locations

Study Locations

• Turkey
  • Istanbul, Turkey, 34736
    • SBU Erenkoy Mental State Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 65 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

Bipolar mania patients from the inpatient service Healthy controls from the community around hospital

Description

Inclusion Criteria:

• diagnosis of BD type I, manic episode according to DSM-5 [10] given by the following doctor,
• being informed of the purpose of the study and having given signed consent before enrollment.

Exclusion Criteria:

• being younger than 18 years or older than 60 years,
• showing low mental capacity during the interview
• expression of hallucinations and disruptive behaviors during the interview,
• presence of severe organic disease,
• presence of any organic disease that may affect cognition
• having less than five years of public education
• diagnosis of substance or alcohol abuse in the last three months (except nicotine and caffeine)
• presence of cerebrovascular disorder, head trauma with longer duration of loss of consciousness, severe hemorrhage and dementia,
• having electroconvulsive therapy in the last one year.

For the healthy control group, the following additional criteria were considered for exclusion

• presence of family history of mood or psychotic disorder,
• presence of psychiatric disorder during interview or in the past.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Bipolar Mania; Diagnosis of BD type I, manic episode according to DSM-5 given by the following doctor	Drug: Ongoing treatment for bipolar mania; Prescribed by the following doctor during hospitalization and after discharge; Diagnostic test: Audiovisual recording during guided presentation; Seven tasks such as explaining the reason to come to hospital/participate in the activity, describing happy and sad memories, counting up to thirty, explaining two emotion eliciting pictures
Healthy Control; showing normal mental capacity during interview, have more than five years of public education, no diagnosis of substance or alcohol abuse in the last three months (except nicotine and caffeine, no presence of family history of mood or psychotic disorder, and no presence of psychiatric disorder during interview or in the past, no presence of severe organic disease.	Diagnostic test: Audiovisual recording during guided presentation; Seven tasks such as explaining the reason to come to hospital/participate in the activity, describing happy and sad memories, counting up to thirty, explaining two emotion eliciting pictures

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Treatment response	The proportion of Young Mania Rating Scale(YMRS) score ( at baseline to 3rd- 7th- 14th- 28th day and 3rd month ( Baseline scale/ Follow-up day scale) YMRS score utilized rating scales to assess manic symptoms ranged between 0-76; Remission: Yt <= 7; Hypomania: 7 < Yt < 20; Mania: Yt >= 20.	from baseline until 3rd month
Changes in visual features	Functionals of appearance descriptors extracted from fine-tuned Deep Convolutional Neural Networks (DCNN), geometric features obtained using tracked facial landmarks (Unweighted Average Recall) Geometric frame level 23 geometric features and apperance descriptors 4096 dimensional features from the last convolutional layer of the FER fine-tuned CNN which are summarized via mean and range functionals over sub-clips and the decisions are voted at video level, an UAR performance is obtained. Feature vectors extracted from video is modelled using Partial Least Squares (PLS) regression and Extreme Learning Machines classifiers Unweighted Average Recall (UAR), which is mean of class-wise recall scores, is commonly used as performance measure, instead of accuracy, which can be misleading in the case of class-imbalance	Baseline and 3rd month
Changes in audio features	Functionals of acoustic features extracted via openSMILE tool (Unweighted Average Recall) Acoustic low level descriptors including prosody (energy, Fundamental Frequency - F0), voice quality features (jitter and shimmer), Mel Frequency Cepstral Coefficients, which are commonly used in many speech technologies from audio, we use the 76-dimensional standard feature set used in the INTERSPEECH 2010 paralinguistic challenge as baseline. The second is our proposed set of 10 functionals, Mean, standard deviation, curvature coefficient , slope and offset , minimum value and its relative position, maximum value and its relative position, and the range Feature vectors extracted from audio is modelled using Partial Least Squares (PLS) regression and Extreme Learning Machines classifiers.	Baseline and 3rd month
in Stop Signal Test	(milisecond) SST- Succesful Stop Ratio SST- go- Reaction Time SST- Stop Signal Delay SST- Stop Signal Reaction Time SST- Total Correct	Baseline and 3rd month
Changes in Rapid Visual Processing	RVP A' (A prime) is the signal detection measure of sensitivity to the target, regardless of response tendency (range 0.00 to 1.00; bad to good). RVP B'' (B double prime) is the signal detection measure of the strength of trace required to elicit a response (range -1.00 to +1.00)	Baseline and 3rd month
in Cambridge Gambling Task	(milisecond) CGT Quality of decision making CGT Deliberation time CGT Delay aversion CGT Overall proportion bet	Baseline and 3rd month
Changes in Emotion Recognition Test	(rate of emotion prediction) Percent and numbers correct/incorrect prediction	Baseline and 3rd month

Collaborators and Investigators

• Sponsor: Istanbul Saglik Bilimleri University
• Collaborators: Namik Kemal University; Bosphorus University
• Investigators: Principal Investigator: Heysem Kaya, Ass Prof, Namik Kemal University; Study Chair: Ali A Salah, Ass Prof, Bogazici University; Study Chair: Hüseyin Gülec, Ass Prof, İstanbul Sağlık Bilimleri University; Principal Investigator: Elvan Ciftci, MD PhD, İstanbul Sağlık Bilimleri University

Publications and helpful links

General Publications

• Ciftci E, Kaya H, Gulec H, Salah AA (2018) The Turkish Audio-Visual Bipolar Disorder Corpus. In: 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia), pp 1-6. IEEE. Available at: https://ieeexplore.ieee.org/document/8470362/
• Çiftçi E, Kaya H, Güleç H and Salah AA Potential audio treatment predictors for bipolar mania Psychiatry and Clinical Psychopharmacology Supplementary

Study record dates

Study Major Dates

• Study Start (ACTUAL): September 30, 2016
• Primary Completion (ACTUAL): February 20, 2017
• Study Completion (ACTUAL): July 8, 2017

Study Registration Dates

• First Submitted: April 15, 2018
• First Submitted That Met QC Criteria: February 25, 2019
• First Posted (ACTUAL): February 28, 2019

Study Record Updates

• Last Update Posted (ACTUAL): February 28, 2019
• Last Update Submitted That Met QC Criteria: February 25, 2019
• Last Verified: February 1, 2019

More Information

Terms related to this study

• Keywords: Mood Disorders; Mental Disorders; Simulation; Behavioral Symptoms; Cognitive functions; Bipolar and Related Disorders
• Additional Relevant MeSH Terms: Mental Disorders; Pathologic Processes; Bipolar and Related Disorders; Disease; Bipolar Disorder
• Other Study ID Numbers: BipolarAI

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The database will be introduced in AVEC 2018 competition and shared with participants. After the competition the databese will be shared under the special EULA permission.
• IPD Sharing Time Frame: 5 years
• IPD Sharing Access Criteria: EULA permission
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No