Trial Review

Technical difficulties have been reported by some users of the search function and is being investigated by technical staff. Thank you for your patience and apologies for any inconvenience caused.

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
Trial registered on ANZCTR


Registration number
ACTRN12619000838112
Ethics application status
Approved
Date submitted
27/05/2019
Date registered
11/06/2019
Date last updated
18/06/2019
Date data sharing statement initially provided
11/06/2019
Type of registration
Retrospectively registered

Titles & IDs
Public title
The Actionable Intime Insights (AI2) Study: Implementing a digital model for timely and needs-based interventions in mental health services by applying algorithms to health care data
Scientific title
Employing a just-in-time adaptive care early intervention approach for a transformational change in the way mental illness is observed, managed and followed-up: The Actionable Intime Insights (AI2) Study
Secondary ID [1] 298145 0
Nil known
Universal Trial Number (UTN)
Trial acronym
AI2
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Medication error 312685 0
Schizophrenia 312686 0
Bipolar Disorder 312687 0
Serious mental illness 312688 0
Relapse 312689 0
Hospitalisation 312690 0
Medication non-adherence 312691 0
Condition category
Condition code
Mental Health 311185 311185 0 0
Addiction
Mental Health 311186 311186 0 0
Anxiety
Mental Health 311187 311187 0 0
Depression
Mental Health 311188 311188 0 0
Other mental health disorders
Mental Health 311189 311189 0 0
Psychosis and personality disorders
Mental Health 311190 311190 0 0
Schizophrenia
Public Health 311191 311191 0 0
Health service research

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
This is a pilot intervention study that will aim to gauge the feasibility and potential efficacy of using an innovative digital data analytics application (The Actionable Intime Insights [AI2] Application). to support healthcare professionals provide more effective and undemanding ways of monitoring, managing, and treating patients with a chronic mental illness. It will run for 12 months.

Essentially, AI2 is a digital cloud based application service for healthcare professionals and patients that is centralised around the use of MyHealthRecord data. This digital health system contains information such as: medicines (prescription and dispense records, PBS), and Medicare Benefit Schedule (MBS) claims. The methodological premise behind the AI2 study intervention is to use this data as a way to monitor and manage patients, providing real-time visualisation algorithms that identify patients at-risk of relapse and re-hospitalisation. The AI2application is designed so that each MBS and PBS claim made by the patient is visually displayed as an event in a vertical axis, and placed against a time scale (with the day/month and year) on a horizontal axis. In addition to the event (e.g. GP visit), an accompanying simple notes entry box is also included which allows for clinicians to annotate certain insights or predicted outcomes. The additional benefit of adding the notes initiative into the AI2 application is that it adds a contextual backdrop to the documented events, which, in turn, could facilitate the clinicians to identify and develop effective strategies and post-treatment plans.


When participants (people with serious mental illness) log into the AI2 system they will see at first glance their individual profile which will include their personal details (i.e. date of birth, phone number, email address, Medicare number, My Health Record account access, and when they joined). Patients will also have access to their own individual historic timeline of MBS and PBS events on a horizontal platform, and a separate tab that will allow them to connect and disconnect with various healthcare professionals. Patients are not expected to interact with AI2 directly beyond creating an account, but are welcome to view their information. After creating an account, participants will be randomly allocated to either the intervention (50% of participants) or control (50% of participants) group. If an alert is triggered by the AI2 system for a participant in the intervention group (a missed prescription, a missed appointment), the patient will be send an SMS explaining that they have missed this event and are encouraged to contact their clinician. If an alert is triggered for the control group, no SMS will be sent.




After consenting to participate, the only tasks required of participants are to sign up to the AI2 system, have their My Health Record data transferred to the AI2 system, and agree to fill in a post study questionnaire. Our in-house psychiatrists acting as study ‘Monitors’ are trained on how to use the AI2 system, how to correctly interpret the algorithms, and how to specify appropriate intervention pathways when participants are identified at risk of relapse and hospitalisation. Once the trial commences, the clinician Monitors will spend dedicated time engaging with the AI2 system to identify patterns within the data for individual participants that may indicate potential relapse or risk of hospitalisation. These patterns are displayed in dashboard view in a traffic light colour coded reference (Red = people at high risk, urgent action required, Yellow = people at moderate risk, action required, Green = people not at risk, no action required).
Intervention code [1] 314367 0
Behaviour
Intervention code [2] 314368 0
Prevention
Intervention code [3] 314369 0
Treatment: Other
Comparator / control treatment
50% will act as a control, receiving care as usual.
Care as usual refers to whatever protocol is defined individually with their GP- whether it be regular appointment visits to get prescriptions, or regular psychiatrist appointments. There is no guideline protocol for how care as usual is defined, they are still able to view their AI2 account information, but our psychiatrists will not act on any alerts generated by the Control group.

Pre-intervention Medicare (MBS) and PBS data records may be utilised to come to the MBS and PBS data after the completion of the study intervention
Control group
Active

Outcomes
Primary outcome [1] 319949 0
Evaluate the responsiveness of participants to SMS alerts (composite outcome)

We will assess feasibility of patient-signup alerts using the following parameters:

a) Participant compliance: Evidence of the patient responding to the reminder via picking up a script (PBS) or seeing their GP (MBS) within 2 weeks of reminder.
b) Contentment: Patient participants will complete the Medical Interview Satisfaction Scale to assess their level of satisfaction with their healthcare provide in relation to distress relief, communication, rapport, and compliance intent.
c) Preference: Post- study questionnaires/focus groups will be administered to evaluate participant-preferences for alert types, content, and benefit.
Timepoint [1] 319949 0
a) 6 months after intervention commencement
b) end of intervention (12 months)
c) Rolling review (e.g., checked monthly as new participants sign up)
Primary outcome [2] 320188 0
Composite outcome: Evaluate the usefulness, usability and acceptability of the AI2 application for people with SMI

A short qualitative structured interview, in the way of predetermined questions, will be administered to participants as a way to provide an avenue for further discussion relating to their experience with the AI2 application. These questions will assess participants experience of using the application (efficacy, simplicity, usefulness). These questions will be designed specifically for the study

Patient participants will complete the Medical Interview Satisfaction Scale to assess their level of satisfaction with their healthcare provide in relation to distress relief, communication, rapport, and compliance intent.

Through passive data collection methodology, we will also obtain a basic measurement of usability and feasibility of the AI2 application and web dashboard through uptake and usage parameters, which are being collected automatically by the AI2 system.
Timepoint [2] 320188 0
end of intervention (12 months)
Primary outcome [3] 320190 0
To validate the AI2 algorithms.

Aim 3: To validate the AI2 algorithms.
The one-year pre-intervention MBS and PBS data will be used for 10-fold cross validation of algorithms to produce actionable indicators that reflect valid changes in functioning and deterioration. These metrics will be compared with real-world patient outcomes, as follows:
Sensitivity: Measures the proportion of patient relapse and hospitalisation that are correctly identified as people at high or moderate risk,
Specificity: Measures the proportion of patients that are correctly identified as not at risk.
Timepoint [3] 320190 0
End of intervention (12 months)
Secondary outcome [1] 369964 0
To evaluate the efficacy of the AI2 application in reducing relapse

Multivariable Cox proportional hazards regression analysis will be used to evaluate the efficacy of AI2 in reducing patient relapse. 12-Months pre-intervention and post-intervention MBS and PBS data records will be compared as a way to identify the level of usefulness in reducing people relapse (6 months prospective, 6 months retrospective).
Timepoint [1] 369964 0
End of study (12 months)
Secondary outcome [2] 371041 0
To evaluate the efficacy of the AI2 application in reducing hospitalisation

Multivariable Cox proportional hazards regression analysis will be used to evaluate the efficacy of AI2 in reducing hospitalisation. 12-Months pre-intervention and post-intervention MBS and PBS data records will be compared as a way to identify the level of usefulness in reducing hospitalisation (6 months prospective, 6 months retrospective).
Timepoint [2] 371041 0
Baseline, 3, 6, 9, and 12 month intervention periods with equivalent pre-intervention historical periods.

Eligibility
Key inclusion criteria

1. Men and women over the age of 18.
2. Have been diagnosed by a mental health professional with a chronic mental disorder as defined by the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), used by clinicians and researchers to diagnose and classify mental disorders.
3. Have sufficient command of the English language to be able to understand the instructions.
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria

1. Have not been diagnosed with a critical mental illness as per defined by the DSM-5.
2. Deemed by the clinician to be unwilling, unlikely or unable to comprehend or comply with the study protocol.

Study design
Purpose of the study
Prevention
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Central randomisation by computer
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Simple randomisation using a randomisation table created by computer software (In the Ai2 application)
Masking / blinding
Who is / are masked / blinded?



Intervention assignment
Other design features
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
Actual
1/09/2018
Date of last participant enrolment
Anticipated
1/09/2019
Actual
Date of last data collection
Anticipated
1/09/2020
Actual
Sample size
Target
100
Accrual to date
25
Final
Recruitment in Australia
Recruitment state(s)
SA

Funding & Sponsors
Funding source category [1] 302670 0
Government body
Name [1] 302670 0
NHMRC Medical Research Future Fund
Country [1] 302670 0
Australia
Primary sponsor type
University
Name
Flinders University
Address
Digital Psychiatry & Personal Health Informatics,
College of Medicine and Public Health, Flinders University,
Tonsley, GPO Box 2100, Adelaide, SA 5001, Australia.
Country
Australia
Secondary sponsor category [1] 302601 0
None
Name [1] 302601 0
Address [1] 302601 0
Country [1] 302601 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 303293 0
The Southern Adelaide Clinical Human Research Ethics Committee
Ethics committee address [1] 303293 0
Flinders Medical Centre
L6 / 6C room 219
8204 7433
Flinders Drive
Bedford Park
SA
5042
Ethics committee country [1] 303293 0
Australia
Date submitted for ethics approval [1] 303293 0
13/11/2017
Approval date [1] 303293 0
22/11/2017
Ethics approval number [1] 303293 0
AK03478

Summary
Brief summary
We are recruiting participants aged over 18 years old to participate in a 2-year internet based study, called the Actionable Intime Insights (AI2) Study . The study aims to explore whether the use of patients Medicare Benefit Scheme (MBS) and Pharmaceutical Benefit Scheme (PBS) claims data held in My Health Record, can unveil more sufficient ways for clinicians and other healthcare professionals to provide optimal health care to patients with a chronic mental illness. Specifically, when people go to visit their doctors, they typically lodge a MBS or PBS claim to subsidise some of the payment costs. However, to date, there has not been a successful way of monitoring and managing the MBS and PBS data. We hope that we can be the first to provide a long-term sustainable solution to this problem, with the implementation of our novel digital application called the Actionable Intime Insights (AI2) application. We believe the AI2 application will help transform the way clinicians and patients interact with each other and ultimately improve patient’s well-being and outcomes.
Trial website
www.aisquared.co
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 93162 0
A/Prof Niranjan Bidargaddi
Address 93162 0
Personal Health Informatics, College of Medicine and Public Health, Flinders University, Tonsley (Level 2), GPO Box 2100, Adelaide, SA 5001
Country 93162 0
Australia
Phone 93162 0
+61 8 7221 8840
Fax 93162 0
Email 93162 0
niranjan.bidargaddi@flinders.edu.au
Contact person for public queries
Name 93163 0
Miss Lydia Oakey-Neate
Address 93163 0
Personal Health Informatics, College of Medicine and Public Health
Flinders University

1284 South Road, Tonsley SA 5042
GPO Box 2100 Adelaide SA 5001
Country 93163 0
Australia
Phone 93163 0
+61 8 7221 8264
Fax 93163 0
Email 93163 0
lydia.oakeyneate@flinders.edu.au
Contact person for scientific queries
Name 93164 0
A/Prof Niranjan Bidargaddi
Address 93164 0
Personal Health Informatics, College of Medicine and Public Health, Flinders University, Tonsley (Level 2), GPO Box 2100, Adelaide, SA 5001
Country 93164 0
Australia
Phone 93164 0
+61 8 7221 8840
Fax 93164 0
Email 93164 0
niranjan.bidargaddi@flinders.edu.au

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
No/undecided IPD sharing reason/comment
IPD is sensitive health information, and as per ethics, IPD will not be shared with third parties.


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.