Please note that the copy function is not enabled for this field.
If you wish to
modify
existing outcomes, please copy and paste the current outcome text into the Update field.
LOGIN
CREATE ACCOUNT
LOGIN
CREATE ACCOUNT
MY TRIALS
REGISTER TRIAL
FAQs
HINTS AND TIPS
DEFINITIONS
Trial Review
The ANZCTR website will be unavailable from 1pm until 3pm (AEDT) on Wednesday the 30th of October for website maintenance. Please be sure to log out of the system in order to avoid any loss of data.
The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this
information for consumers
Download to PDF
Trial registered on ANZCTR
Registration number
ACTRN12621000803897
Ethics application status
Approved
Date submitted
27/04/2021
Date registered
25/06/2021
Date last updated
24/06/2022
Date data sharing statement initially provided
25/06/2021
Type of registration
Prospectively registered
Titles & IDs
Public title
Real-time assessment comparing mood changes and machine learning in adults with mild-moderate depression and a group of healthy volunteers
Query!
Scientific title
Real-time assessment comparing mood changes and machine learning in adults with mild-moderate depression and a group of healthy volunteers
Query!
Secondary ID [1]
304013
0
Health Research Council of New Zealand Reference ID: 20/1247
Query!
Universal Trial Number (UTN)
Query!
Trial acronym
Query!
Linked study record
Query!
Health condition
Health condition(s) or problem(s) studied:
Depression
321636
0
Query!
Condition category
Condition code
Mental Health
319374
319374
0
0
Query!
Depression
Query!
Intervention/exposure
Study type
Interventional
Query!
Description of intervention(s) / exposure
Intervention -
All participants with depression will be provided study-specific smartphones and smartwatches at the start of the study (once off) that will passively acquire physiological and behavioural data through the built-in sensors in these smartdevices. Participants would not have otherwise been given these devices in the absence of the study.
Materials -
Each participant will be provided with a commercially available smartphone (OneNord) based on the Android platform and a commercially available wearable smartwatch/fitness tracker manufactured by Fitbit.
Data captured -
Physiological data captured passively includes breathing/heart rates, heart rate variability, sleep quality, and step activity. Behavioural data includes the acoustic features of speech when participants complete daily 2-5 minute audio diaries.
Procedures -
Participants will complete an initial screening in person to assess for suitability to participate in this study. If considered suitable, there will be a demonstration of how to use the devices (both smartwatch and smartphone). They will then be provided with the smartdevices and a SIM card for the study-supplied smartphone. They will also be provided with the Fitbit smartwatch to wear during sleep and for most of the day.
Fitbit smartwatches will potentially capture physiological data continuously and passively (as long as the participant is wearing it) - given the potential confounder of movement artefacts during the day, overnight measurements will be of particular interest. The smartphones will be used to capture interactive data - these include daily audio diaries (once a day) and ecological momentary assessments (up to five times daily).
Participants are expected to record short audio diaries (2-5 mins in length) once a day on their smartphone. Tasks they would have to complete as part of the audio diaries include describing their day in general and then specific questions on bad aspects of the day and good aspects of the day respectively. These tasks will capture unstructured speech rather than structured speech (e.g. reading a stock sentence out loud daily).
Ecological momentary assessments (EMAs) will be captured up to 5 times a day and will take less than a minute each to complete. EMAs will be on a Likert scale which the participant can select indicating how they are feeling at the time of completing the EMA.
Who will provide the smartdevices -
Clinical screening will be undertaken by the clinicians in the team with mental health expertise while the demonstration of how to use the smartdevices and support during the study will be provided by team members with a computer and software engineering background.
Mode of delivery -
Smartdevices will be provided to individual participants face to face and will be collected from participants at the end of the study.
Location of intervention -
Participants will come in for a face to face initial clinical screening assessment at the start of the study at the Clinical Research Centre of the University of Auckland which is in an urban centre. If considered suitable to participate, they will be provided with the smartdevices which they will have with them for a period of 1 month of data collection. The 1 month of data collection will be in the participants' own environment e.g. home, workplace, gym, etc. as they will be carrying these smartdevices with them. Refer to the Procedures section for details of the data captured.
Adherence -
Participants will be individually contacted weekly into the study after they are recruited to check whether they are able to use the smartdevices confidently and troubleshoot should they be encountering any technical challenges.
Study duration -
Total of 1 year. Data from individual participants will be gathered over a period of 1 month.
Query!
Intervention code [1]
320966
0
Early detection / Screening
Query!
Comparator / control treatment
Smartdevice data will also be collected daily for 1 month from a group of healthy control participants who do not have mild-moderate depression, The details provided in the Description of intervention(s)/exposure are also relevant to this section. All participants will receive identical materials/procedures/other aspects of the study.
Query!
Control group
Active
Query!
Outcomes
Primary outcome [1]
327243
0
Change in heart-rate variability using the smartwatch.
(Heart-rate variability is reported as the root mean square of successive differences between heartbeats)
Query!
Assessment method [1]
327243
0
Query!
Timepoint [1]
327243
0
Using the smartwatch to passively capture heart physiological data on a daily basis for a period of 1 month.
Query!
Primary outcome [2]
327327
0
Change in subjective mood ratings using ecological momentary assessment (EMAs) which measure subjective mood on a 10-point Likert scale.
Query!
Assessment method [2]
327327
0
Query!
Timepoint [2]
327327
0
EMAs will be completed several times daily (up to 5 times daily) to capture mood variation over 1 month.
Query!
Primary outcome [3]
327329
0
Change in the acoustic features of speech - the main features examined are prosody and jitter. Using the smartphone to capture the acoustic features of speech (spoken audio diaries of 2-5 minutes duration).
Query!
Assessment method [3]
327329
0
Query!
Timepoint [3]
327329
0
Speech data will be captured once daily over a period of 1 month.
Query!
Secondary outcome [1]
394345
0
Change in breathing rate as measured by the smartwatch.
Query!
Assessment method [1]
394345
0
Query!
Timepoint [1]
394345
0
Breathing rate will be measured on a daily basis for a period of 1 month. Breathing rate is measured as breaths per minute.
Query!
Secondary outcome [2]
394629
0
Change in sleep quality as measured by the smartwatch. Sleep quality is reported by the Fitbit Health App as a score from 0-100.
Query!
Assessment method [2]
394629
0
Query!
Timepoint [2]
394629
0
Using the smartwatch to passively capture sleep data on a daily basis for a period of 1 month.
Query!
Secondary outcome [3]
394630
0
Change in step activity. Step activity is reported as total steps taken daily.
Query!
Assessment method [3]
394630
0
Query!
Timepoint [3]
394630
0
Daily step activity will be acquired for a period of 1 month.
Query!
Secondary outcome [4]
397324
0
Change in oxygen saturation which is measured as a percentage.
Query!
Assessment method [4]
397324
0
Query!
Timepoint [4]
397324
0
Oxygen saturation will be measured passively through the Fitbit smartwatches over the period of one month whereby daily average oxygen saturations are reported.
Query!
Eligibility
Key inclusion criteria
Inclusion criteria for participants with depression -
• Participant is willing and able to give informed consent for participation in the study
• Male or female, aged 18 years or above and less than 60 years
• Able and willing to comply with all study requirements as assessed by the research team
• Following a referral from their GP, diagnostic confirmation of major depressive disorder for at least two weeks will be undertaken by the research team. Participants will be assessed using the Mini-International Neuropsychiatric Interview (MINI) which is a structured diagnostic clinical interview using DSM V criteria (American Psychiatric Association, 2013; Sheehan et al., 1998) and a Montgomery-Asberg Depression Rating Scale (MADRS) score 7-19 inclusive for mild depression and 20-34 inclusive for those with moderate depression (Williams & Kobak, 2008)
Inclusion criteria for healthy controls -
• Participant is willing and able to give informed consent for participation in the study
• Male or female, aged 18 years or above and less than 60 years
• As assessed by the research team, to be able and willing to comply with all study requirements
• Participants will be assessed using the Mini-International Neuropsychiatric Interview (MINI) which is a structured diagnostic clinical interview using DSM V criteria (American Psychiatric Association, 2013; Sheehan et al., 1998) and Montgomery-Asberg Depression Rating Scale (MADRS) score of 6 or less for self-referrals (Williams & Kobak, 2008). Absence of major depressive disorder will be necessary for at least three months.
Query!
Minimum age
18
Years
Query!
Query!
Maximum age
60
Years
Query!
Query!
Sex
Both males and females
Query!
Can healthy volunteers participate?
Yes
Query!
Key exclusion criteria
Exclusion criteria for participants with depression -
• History of psychosis or personality disorder
• Any unstable medical or neurological condition
• Substance abuse or dependence in the last six months
• Planned major changes to psychotropic medication
• Imminent risk of suicide as determined by the Columbia-Suicide Severity Rating Scale (CSSRS) (Posner et al., 2011)
• Any other condition judged by the treating clinician as likely to impact on the ability of the participant to complete the study
• Inability to speak or read English to a level that enables informed consent and/or participation in the study
• Those who are unable or disinterested in using the technology involved in the study
Exclusion criteria for healthy participants (controls) -
• Prior history of any physical health or mental health diagnosis
Query!
Study design
Purpose of the study
Prevention
Query!
Allocation to intervention
Non-randomised trial
Query!
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Allocation is not concealed
Query!
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Not applicable
Query!
Masking / blinding
Open (masking not used)
Query!
Who is / are masked / blinded?
Query!
Query!
Query!
Query!
Intervention assignment
Other
Query!
Other design features
There will be 2 groups in this study but both groups will receive the same intervention.
The first group is the participants with mild-moderate depression while the second group are participants who are healthy controls.
Query!
Phase
Not Applicable
Query!
Type of endpoint/s
Safety
Query!
Statistical methods / analysis
This study will adopt a case-control study design, recruiting people with depression and healthy controls. This will ensure that detailed individual data will be acquired for both groups, and their data will be used to help develop machine learning approaches e.g. deep neural networks. This study is a feasibility study which would allow the benefits and challenges of developing an electronic architecture/infrastructure that would permit the objective assessment of people with depression and enable future pilot and randomised controlled trials to be undertaken (Eldridge et al., 2016).
As this study is not focused on testing the efficacy of an intervention but rather a study comparing those who are depressed versus healthy controls and whether there are possible difference in digital biomarkers, this study has similar participant numbers as prior feasibility studies e.g. Mahadevan et al (2020).
Based on the physiological and behavioural data captured, data will be developed into a machine learning model. This will allow inferencing in the future at an individual level whether a person was depressed or potentially provide early warning indicators that a person's depression might be relapsing.
Reference -
Eldridge, S. M., Lancaster, G. A., Campbell, M. J., Thabane, L., Hopewell, S., Coleman, C. L., & Bond, C. M. (2016). Defining Feasibility and Pilot Studies in Preparation for Randomised Controlled Trials: Development of a Conceptual Framework. PLoS One, 11(3), e0150205. doi:10.1371/journal.pone.0150205
Mahadevan, N., Demanuele, C., Zhang, H. et al. Development of digital biomarkers for resting tremor and bradykinesia using a wrist-worn wearable device. npj Digit. Med. 3, 5 (2020). https://doi.org/10.1038/s41746-019-0217-7
Query!
Recruitment
Recruitment status
Recruiting
Query!
Date of first participant enrolment
Anticipated
1/07/2021
Query!
Actual
1/11/2021
Query!
Date of last participant enrolment
Anticipated
30/09/2024
Query!
Actual
Query!
Date of last data collection
Anticipated
30/09/2024
Query!
Actual
Query!
Sample size
Target
40
Query!
Accrual to date
15
Query!
Final
Query!
Recruitment outside Australia
Country [1]
23626
0
New Zealand
Query!
State/province [1]
23626
0
Query!
Funding & Sponsors
Funding source category [1]
308394
0
Government body
Query!
Name [1]
308394
0
Health Research Council of New Zealand
Query!
Address [1]
308394
0
Level 3 - ProCARE Building, Grafton Mews, at 110 Stanley Street, Grafton, Auckland 1010
Query!
Country [1]
308394
0
New Zealand
Query!
Primary sponsor type
University
Query!
Name
The University of Auckland
Query!
Address
20 Symonds Street
Auckland 1010
New Zealand
Query!
Country
New Zealand
Query!
Secondary sponsor category [1]
309272
0
None
Query!
Name [1]
309272
0
Query!
Address [1]
309272
0
Query!
Country [1]
309272
0
Query!
Ethics approval
Ethics application status
Approved
Query!
Ethics committee name [1]
308357
0
Auckland Health Research Ethics Committee (AHREC)
Query!
Ethics committee address [1]
308357
0
Auckland Health Research Ethics Committee, The University of Auckland, Private Bag 92019, Auckland 1142
Query!
Ethics committee country [1]
308357
0
New Zealand
Query!
Date submitted for ethics approval [1]
308357
0
16/04/2021
Query!
Approval date [1]
308357
0
03/06/2021
Query!
Ethics approval number [1]
308357
0
AH22436
Query!
Summary
Brief summary
Depression is the most prevalent mental health disorder in New Zealand (Wells et al., 2006) and is the second leading cause of disability in the world (Ferrari et al., 2013). However, despite the availability of effective treatments for depression, less than 10% of individuals with depression in many countries receive treatment in a timely way (Reddy, 2010). There are several barriers to early diagnosis and treatment including, limited access to mental health services and a lack of objective assessment techniques based on behavioural or physiological parameters which taken together, result in delayed presentations and poorer outcomes. Therefore, this study aims to acquire, in a pilot clinical population, physiological and behavioural data through the application of inbuilt sensors in smartphones and smartwatches and develop a machine-learning algorithm (moodAI) that will help in the earlier detection of depression and also provide a relapse signature on an individual level.
Query!
Trial website
Query!
Trial related presentations / publications
Query!
Public notes
Query!
Contacts
Principal investigator
Name
110434
0
A/Prof Frederick Sundram
Query!
Address
110434
0
Dept of Psychological Medicine, School of Medicine
University of Auckland
Building 507
22-30 Park Avenue, Grafton
Auckland 1023
Query!
Country
110434
0
New Zealand
Query!
Phone
110434
0
+64 9 923 7521
Query!
Fax
110434
0
Query!
Email
110434
0
[email protected]
Query!
Contact person for public queries
Name
110435
0
Frederick Sundram
Query!
Address
110435
0
Dept of Psychological Medicine, School of Medicine
University of Auckland
Building 507
22-30 Park Avenue, Grafton
Auckland 1023
Query!
Country
110435
0
New Zealand
Query!
Phone
110435
0
+64 9 923 7521
Query!
Fax
110435
0
Query!
Email
110435
0
[email protected]
Query!
Contact person for scientific queries
Name
110436
0
Frederick Sundram
Query!
Address
110436
0
Dept of Psychological Medicine, School of Medicine
University of Auckland
Building 507
22-30 Park Avenue, Grafton
Auckland 1023
Query!
Country
110436
0
New Zealand
Query!
Phone
110436
0
+64 9 923 7521
Query!
Fax
110436
0
Query!
Email
110436
0
[email protected]
Query!
Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
Query!
No/undecided IPD sharing reason/comment
Though individual participant data is de-identified, it is not expected to be made publicly available as this is a feasibility trial with potential for the acquired data to inform further trials and data modelling/algorithm development which needs to be kept confidential for now.
Query!
What supporting documents are/will be available?
No Supporting Document Provided
Results publications and other study-related documents
Documents added manually
No documents have been uploaded by study researchers.
Documents added automatically
No additional documents have been identified.
Download to PDF