133 Mobile phone mental health applications: a novel pathway for overdiagnosis of depression
Bibliographic record
Abstract
Mobile phone mental health applications (apps) are widely used, and usage has only been accelerated by the global COVID-19 pandemic. These apps often offer a suggested diagnosis as well as treatment guidance. Despite the extensive use of these apps, there is no evidence on the effect they may have on overdiagnosis of mental health conditions, specifically depression. Given the nature of mental health, overdiagnosis can be particularly difficult to quantify and attempts to study overdiagnosis in mental health have often focused on misdiagnosis. Overdiagnosis is separate from misdiagnosis and occurs when overdetection or overdefinition occur. Overdefinition is of relevance in mental health as the DSM-V criteria have been critiqued as being overinclusive such that normal aspects of life are medicalized. Overdiagnosis of depression can have significant effects on the user in the forms of treatment side effects, stigma and labelling harms as well as direct and indirect costs. From a systems level, overdiagnosis results in inefficient use of resources and potential diversion of resources away from those most in need. Objectives To understand if mobile phone mental health apps have the potential to contribute to the overdiagnosis of depression in users with milder and self-limited depressive symptoms or grief reactions. Methods A review of the relevant literature was conducted using PubMed. The top 25 apps using the search term ‘depression’ on the Apple App Store and Google Play App Store were reviewed. Results Numerous apps (8/25 on each app store) inappropriately used a general screening and treatment response tracking tool, the PHQ-9 questionnaire, as a diagnostic tool. These apps and others provided users with a suggested diagnosis of depression in the context of short term mild depressive symptoms that do not meet DSM-V criteria for Major Depressive Disorder (MDD). This may reflect misdiagnosis, however beyond this phenomenon, these apps appear to be susceptible to overdiagnosis as well. Users may meet diagnostic criteria for MDD however symptoms may be sufficiently transient or mild that clinicians using their clinical judgement would not make a diagnosis of depression. Mental health apps lack this fine-tuned clinical judgment and have the potential to indiscriminately make the diagnosis in those experiencing non-pathologic aspects of everyday experiences. The top 12 apps in each store represent greater than 90% of the monthly active users of all depression apps. Among the top 12 apps, 4/12 after making a suggested diagnosis of depression then offered links to for profit web-based therapy services that in some cases have funded the app itself or reimbursed the app for successful referrals. Conclusion Physicians need to be aware of this potential for overdiagnosis of depression and should clarify how a patient’s previous history of depression was diagnosed. Additionally, patients presenting with depressive symptoms may have already used these apps to reach a premature diagnostic conclusion and expect a certain level of treatment based on the recommendations of these apps. This can strain the therapeutic relationship and care must be taken to explain the nuances of diagnosis and treatment that these apps often overlook.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.016 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".