Related Experiment Video
Updated: Apr 4, 2026
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
Published on: May 10, 2022
Automatically detecting trends and open questions from mental health publications: a Wellcome-funded GALENOS project
Janna Hastings1,2, Marie Wosny3, Jaycee Kennett4,5
1Human-Centered Health AI, Idiap Research Institute, Martigny, Switzerland janna.hastings@idiap.ch.
Background:
More effective and better tolerated treatments are urgently needed for people with mental health disorders, such as anxiety, depression and psychosis. However, the rate of translation of positive results from early phase studies into clinically validated treatments remains painstakingly slow. The scientific literature on mental health preclinical and early interventions is burgeoning at pace, making it difficult for researchers, practitioners and policymakers to identify and track new developments.
Objective:
As part of the Wellcome-funded Global Alliance of Living Evidence for aNxiety, depressiOn and pSychosis project, we aimed to develop and evaluate an automated approach to track the evolution of mental health research over time, detect emerging trends and suggest open questions.
Methods:
Our approach used topic modelling, large language models and time-series forecasting in combination. We applied our approach to a corpus of 182 747 titles and abstracts extracted from the OpenAlex database for 2015-2025. Using topic modelling to identify topics and then tracking topic mentions over time, we built a time series predictive model and predicted 'trendiness' based on sustained increased mentions above baseline expected from model predictions. We evaluated our approach retrospectively using a blinded expert study of a randomly selected sample of trending and not trending topics. Finally, we developed a novel topic-augmented generation approach to suggest open questions in trendy topics and evaluated the approach by comparison to baseline-generated questions without topic augmentation.
Findings:
Our approach detected 973 topics and predicted 165 (17%) of those as trending. Key topics that the model predicted as trending included 'ketamine for treatment-resistant depression', 'student mental health in academia' and 'COVID-19 psychosis'. We found that domain experts largely agreed with the model's predictions of trendiness. Topic-augmented generated questions were more specific than baseline generated questions.
Conclusions:
Our approach enables identification of new developments and open questions. Future work will improve temporal pattern tracking and use full texts.
Clinical Implications:
Our approach can support all stakeholders to gain an overview of the published literature, assess temporal patterns, identify trends and rank open questions.
Insights
An automated approach using AI identifies emerging trends in mental health research, such as ketamine for depression and student mental health. This tool helps track developments and suggests open research questions for better treatments.
Area of Science:
- Mental Health Research
- Computational Linguistics
- Data Science
Background:
- Urgent need for improved mental health treatments (anxiety, depression, psychosis).
- Slow translation of early research findings into clinical practice.
- Rapid growth in scientific literature hinders tracking of new developments.
Purpose of the Study:
- Develop and evaluate an automated method to track mental health research evolution.
- Identify emerging trends and suggest open research questions.
- Support researchers, practitioners, and policymakers in navigating the literature.
Main Methods:
- Combined topic modeling, large language models, and time-series forecasting.
- Analyzed 182,747 titles and abstracts (2015-2025) from OpenAlex.
- Predicted 'trendiness' based on topic mention frequency over time.
Main Results:
- Identified 973 topics, predicting 165 (17%) as trending.
- Trending topics included 'ketamine for treatment-resistant depression' and 'student mental health'.
- Domain experts validated the model's trend predictions; topic-augmented questions were more specific.
Conclusions:
- The automated approach effectively identifies new developments and open questions in mental health research.
- Supports stakeholders in understanding literature trends and prioritizing research areas.
- Future work aims to enhance temporal tracking and incorporate full-text analysis.
More Related Videos
Related Concept Videos
01:30Current Trends in Nursing II
01:27Diagnostic and Statistical Manual of Mental Disorders (DSM)
01:29Introspection
02:40The Scientific Method
01:52Regression Toward the Mean
01:28Self-Help Support Groups
Accessibility and Cost-Effectiveness
One of the primary strengths of self-help...