Active Mental Health Psychology & Behaviour

Project PHONOTYPE: Validation of smartphone-based digital phenotyping markers for detecting amotivation symptoms in young people with depression

In plain English

AI plain-English summary

A smartphone’s sensors—microphone, GPS, accelerometer, screen logs—could reveal whether a depressed teenager is losing motivation before they say a word. This matters because young people with depression who suffer from amotivation—loss of interest and drive—often do not respond to standard treatments. New therapies exist, but clinicians lack reliable ways to identify who needs them. Project PHONOTYPE tests whether digital signals from phones can serve as objective markers of amotivation, using AI to analyse patterns in movement, location, and phone use across more than 7,500 adolescents and young adults. If the digital markers prove reliable, clinicians could match young people to motivation-targeted therapies like Positive Affect Therapy earlier, improving treatment outcomes. The team will also run two new trials and build a Digital Phenotyping Databank to make the tools widely usable. This is applied clinical research with a direct practical goal: better targeting of existing treatments. Success would not change daily life for most people, but it could quietly improve how mental health services triage and treat one of the hardest-to-reach symptoms in adolescent depression.

View original technical description
Young people with depression who experience loss of interest and motivational drive (amotivation symptoms) respond poorly to first-line depression treatments. New treatments for amotivation symptoms have emerged (e.g., Positive Affect Therapy), and if delivered to the right young people at the right time, could improve treatment outcomes. In project PHONOTYPE, will investigate whether digital signals collected from smartphones are useful for identifying young people with amotivation symptoms. The key goals are to determine whether digital markers converge with self-reported amotivation symptoms in cross-sectional and longitudinal datasets, whether they predict a more severe depressive illness course, and whether they are useful for identifying young people who respond favourably to motivation-targeted treatment. We will use artificial intelligence (AI) to identify digital signals, using our custom-built AI-enhanced digital phenotyping and clinical trial platform. Our team of international mental health leaders, lived experience research specialists, and AI experts, will leverage existing richly-phenotyped longitudinal studies of adolescents and clinical trials of young adults with depression (N>7,500). To establish generalisability and clinical utility, we will conduct two new trials and establish a Digital Phenotyping Databank. Throughout, we will implement a capacity-building program to ensure lived experience advisors engage as peers across leadership, governance, design, and translation.

View the original record at the funder ↗

Researchers

Alexis Whitton (EPMC Awardee)Artur Shvetcov (EPMC Awardee)Bridianne O'Dea (EPMC Awardee)Elizabeth Elder (EPMC Awardee)Helen Christensen (EPMC Awardee)Jill Newby (EPMC Awardee)Rajesh Vasa (EPMC Awardee)Thin Nguyen (EPMC Awardee)

Related Research

Grants with similar aims, by meaning.

The Computational Psychiatry of Major Depressive Disorder
Cognitive and behavioural biomarkers for the diagnosis and treatment of mental health conditions
Intelligent DEPression Tracking (I-DEPT) - A Novel, Longitudinal and Multi-Modal Machine Learning Framework for Quantifying Depression Symptoms
ANTONA-MH: Accelerating New Therapies with Objective Neurophysiological Assessment for Mental Health
NEurobehavioural predictiVE and peRsonalised Modelling of depressIve symptoms duriNg primary somatic Diseases with ICT-enabled self-management procedures

Original classification

Finding the right treatment, for the right people, at the right time for anxiety

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.