Psych · Public and community psychiatry
Digital psychiatry, apps and AI in mental health care
Also known as Digital mental health · e-mental health · mHealth in psychiatry · Mental health apps · Internet-delivered CBT · Blended care · Digital phenotyping · Passive sensing · Digital therapeutics · AI in psychiatry · LLM chatbots in mental health
Exam-exhaustive fellowship topic on digital psychiatry and AI — telepsychiatry versus in-person evidence, mental health apps and how to prescribe one, internet-delivered CBT and blended care, digital phenotyping and passive sensing, machine learning for diagnosis, triage and risk (including the suicide prediction paradox), LLM chatbots and their documented harms, privacy and data governance, the digital divide, and regulation as principles. FRANZCP-primary, globally tagged.
Practise this topic
On this page
Study tools
Your progress
Saved on this device.
Target exams
Red flags
- Accepting an algorithmic risk score in place of a clinical risk formulation — good discrimination does not mean a useful positive predictive value
- Recommending an app without checking where its data goes — privacy policies routinely do not match privacy behaviour
- Running a remote consultation with no location, no escalation pathway and no plan for the call dropping
- Missing catatonia, delirium, intoxication or physical deterioration because the assessment stayed on video
- A patient relying on an LLM chatbot for crisis support — chatbots have documented failures to escalate
- Passive monitoring introduced at family or service request without the patient's informed, revocable consent
- Digital-only service redesign that quietly excludes the people with the most severe illness and the least access
- Quoting an app store effectiveness claim as if it were evidence
Meet the patient
A 29-year-old man with recurrent depression arrives ten minutes late to a video appointment, from his car, outside work. He has been "doing therapy" for six weeks — an app he found by searching, plus long nightly conversations with a general-purpose chatbot that he says "listens better than my GP".[1][18]
He also brings a printout: your service's new risk-stratification dashboard has flagged him amber. Nobody has told him why. He wants to know whether the computer thinks he is going to kill himself.[14][16]
Three technologies, three different evidence bases, three different ways to get this wrong. The examiner's question is always the same: what changes about your clinical duty? Nothing. That is the whole topic.[1][13]
References20ShowHide
- [1]Torous J, et al. The evolving field of digital mental health: current evidence and implementation issues for smartphone apps, generative artificial intelligence, and virtual reality World Psychiatry, 2025.PMID 40371757
- [2]Fernandez E, et al. Live psychotherapy by video versus in-person: A meta-analysis of efficacy and its relationship to types and targets of treatment Clin Psychol Psychother, 2021.PMID 33826190
- [3]Andersson G, et al. Guided Internet-based vs. face-to-face cognitive behavior therapy for psychiatric and somatic disorders: a systematic review and meta-analysis World Psychiatry, 2014.PMID 25273302
- [4]Karyotaki E, et al. Internet-Based Cognitive Behavioral Therapy for Depression: A Systematic Review and Individual Patient Data Network Meta-analysis JAMA Psychiatry, 2021.PMID 33471111
- [5]Erbe D, et al. Blending Face-to-Face and Internet-Based Interventions for the Treatment of Mental Disorders in Adults: Systematic Review J Med Internet Res, 2017.PMID 28916506
- [6]Linardon J, et al. The efficacy of app-supported smartphone interventions for mental health problems: a meta-analysis of randomized controlled trials World Psychiatry, 2019.PMID 31496095
- [7]Baumel A, et al. Objective User Engagement With Mental Health Apps: Systematic Search and Panel-Based Usage Analysis J Med Internet Res, 2019.PMID 31573916
- [8]Lagan S, et al. Mental Health App Evaluation: Updating the American Psychiatric Association's Framework Through a Stakeholder-Engaged Workshop Psychiatr Serv, 2021.PMID 33882716
- [9]Larsen ME, et al. Using science to sell apps: Evaluation of mental health app store quality claims NPJ Digit Med, 2019.PMID 31304366
- [10]Huckvale K, et al. Assessment of the Data Sharing and Privacy Practices of Smartphone Apps for Depression and Smoking Cessation JAMA Netw Open, 2019.PMID 31002321
- [11]Insel TR Digital Phenotyping: Technology for a New Science of Behavior JAMA, 2017.PMID 28973224
- [12]Adler DA, et al. Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks JMIR Mhealth Uhealth, 2020.PMID 32865506
- [13]Chekroud AM, et al. The promise of machine learning in predicting treatment outcomes in psychiatry World Psychiatry, 2021.PMID 34002503
- [14]Belsher BE, et al. Prediction Models for Suicide Attempts and Deaths: A Systematic Review and Simulation JAMA Psychiatry, 2019.PMID 30865249
- [15]Large M, et al. Meta-Analysis of Longitudinal Cohort Studies of Suicide Risk Assessment among Psychiatric Patients: Heterogeneity in Results and Lack of Improvement over Time PLoS One, 2016.PMID 27285387
- [16]Obermeyer Z, et al. Dissecting racial bias in an algorithm used to manage the health of populations Science, 2019.PMID 31649194
- [17]Zhang Q, et al. Generative AI Mental Health Chatbots as Therapeutic Tools: Systematic Review and Meta-Analysis of Their Role in Reducing Mental Health Issues J Med Internet Res, 2025.PMID 41401240
- [18]Blease C, et al. ChatGPT and mental healthcare: balancing benefits with risks of harms BMJ Ment Health, 2023.PMID 37949485
- [19]Spanakis P, et al. The digital divide in people with severe mental illness: lessons learned and challenges lying ahead Br J Psychiatry, 2025.PMID 40114499
- [20]Parker L, et al. The "Hot Potato" of Mental Health App Regulation: A Critical Case Study of the Australian Policy Arena Int J Health Policy Manag, 2019.PMID 30980633