Prospective Real World Study on Therapy Prediction Algorithm Training

Prospective Real World Study on Therapy Prediction Algorithm Training Using Data From the Mobio Mental Health Platform AmDTx

This study examines the impact of using an algorithm to select therapy content for patients engaged with the mobile mental health platform AmDTx (Mobio Interactive). The algorithm is to be trained with three separate sources of data. Two sources of data come from self-reports by the patients themselves, provided before and after engaging with therapy content. The third source of data comes from an objective measurement of psychological stress, made possible through artificial analysis of computer vision data captured from the mobile device camera as the patient completes a 30 second selfie video before and after engaging with therapy content.

Study Overview

• Status: Completed
• Conditions: Stress; Emotional Wellbeing
• Intervention / Treatment: Device: AmDTx

Detailed Description

From 2,786 unique individuals engaging between March 2015 and December 2022 in English language psychotherapy sessions and providing pre- and post-session self-report and facial biometric data via the AmDTx mental health platform (Mobio Interactive Pte Ltd, Singapore), analysis was conducted on 67 "super users" that completed at least 28 sessions with all pre- and post-session measures. AmDTx is a clinically validated mental health platform that provides patients with audio recordings supporting mental wellbeing (asynchronous and on-demand psychotherapy). AmDTx also contains easy to use tools that rapidly assess mental wellbeing, including an objective measure of psychological stress derived from AI analysis of facial biomarkers (Objective Stress Level; ∆OSL), and ecological momentary assessments (EMAs). Two commonly used EMAs within AmDTx are self-reported stress (∆SRS) and self-reported mood (∆SRM). These three data sources were used to independently train an algorithm designed to predict what future therapy sessions would prove most efficacious for each individual. Algorithm predictions were compared against the efficacy of the individual's self-selected sessions.

• Study Type: Observational
• Enrollment (Actual): 67

Contacts and Locations

Study Locations

• Singapore
  • Singapore, Singapore, 389637
    • Mobio Interactive Pte Ltd

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

AmDTx users at least 18 years old, of any gender, and from any geography and socioeconomic status.

Description

Inclusion Criteria:

• Completion of at least 28 English-language psychotherapy sessions that contained the required session payloads for algorithm inclusion, and only when the objective and two subjective measures were all completed both before and after each session.

Exclusion Criteria:

• Under 18 years old

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

AmDTx engaged; Data were collected between March 2015 and December 2022 on 36,160 unique users in a manner compliant with the Health Insurance Portability and Accountability Act (HIPAA), Personal Health Information Protection Act (PHIPA), and General Data Protection Regulation (GDPR). Of these, 2,786 unique individuals engaged in biometric and self-report data collection. To protect the real-world applicability of the results, users were not given any special instruction or information about the nature or possibility of the current analyses. As consequence, user data varied greatly in terms of engagement and app-use characteristics. To create a single, unified, and consistent dataset that could be leveraged across all intended analyses, data were filtered to only include English-language psychotherapy sessions that contained the required session payloads for algorithm inclusion (see below), and only when all the objective and two subjective measures were completed both before and after each session.

Device: AmDTx; AmDTx (Mobio Interactive Pte Ltd, Singapore), is an advanced mobile health platform equipped with computer vision and AI to objectively quantify psychological stress and benchmarked ecological momentary assessments to subjectively measure stress, valence, and arousal. Asynchronous and on-demand psychotherapy available as audio files within AmDTx has been clinically validated across the mental illness severity spectrum. Psychotherapy within AmDTx primarily leverages meditation/mindfulness techniques to enhance relaxation, build stress resilience, improve focus and decision making, and influence behaviour and affect bias.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Objective Stress Level (OSL)	Objective stress level (∆OSL). Objective stress within AmDTx was obtained via a 30-second "selfie" video captured with the front-facing camera of a mobile device (smartphone or table). The computer vision data extracted from the videos in real time through study completion, an average of 27.1 measures per person per year, were then passed through a deep neural network (DNN) to compute the objective stress level (∆OSL) at that moment in time. ∆OSL is represented with a value between 0 to 1, with greater values representing more stress.	Continuous
Self-Reported Stress (SRS)	Subjective, self-reported stress (∆SRS). Subjective stress within AmDTx was quantified via an animated digital "slider". Users reported their current level of stress either by dragging a marker on the slider to a position of their choosing between "none" (0) and "extreme" (10), or by tapping on one of four faces positioned above the slider, with each face visually depicting stress levels at the mid-points of four quadrants (i.e., values of 1.25, 3.75, 6.25, 8.75). Users were instructed input the stress that represents how they feel "right here, right now". Data collected in real time through study completion, an average of 27.1 measures per person per year.	Continuous
Self-Reported Mood (SRM)	Subjective, self-reported mood (∆SRM). Subjective mood within AmDTx was quantified via a "mood board", which asks users to select from 32 different words representing various emotions (e.g., "delighted", "content", "gloomy", "tense"). The mood board consists of two axes, one spanning from "unpleasant" to "pleasant" and the other from "mild" to "intense". Each quadrant contains 8 mood words. Users were instructed to tap on the words that represent how they feel "right here, right now". Data collected in real time through study completion, an average of 27.1 measures per person per year.	Continuous

Collaborators and Investigators

• Sponsor: Mobio Interactive PTE LTD
• Investigators: Principal Investigator: Bechara J Saab, PhD, Mobio Interactive Pte Ltd

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2015
• Primary Completion (Actual): December 31, 2022
• Study Completion (Actual): December 31, 2022

Study Registration Dates

• First Submitted: January 10, 2024
• First Submitted That Met QC Criteria: February 11, 2024
• First Posted (Actual): February 20, 2024

Study Record Updates

• Last Update Posted (Actual): February 20, 2024
• Last Update Submitted That Met QC Criteria: February 11, 2024
• Last Verified: February 1, 2024

More Information

Terms related to this study

• Keywords: Remote monitoring; Psychological stress; Remote therapy; Precision psychiatry; Recommendation algorithm
• Other Study ID Numbers: PRW001

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

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