Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Functional Outcome Prediction in Young Adults With Mental Health Symptoms Using Machine Learning and Large Language

Pavol Mikolas1,2, Fabian Huth1, Kyra Bröckel-Bundt1

  • 1Department of Psychiatry and Psychotherapy, Carl Gustav Carus University Hospital, TUD Dresden University of Technology, Dresden, Germany.

JMIR Mental Health
|June 22, 2026
PubMed

Related Concept Videos

Longitudinal Research02:20

Longitudinal Research

Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...
Longitudinal Studies01:26

Longitudinal Studies

Longitudinal studies are also widely used in other medical and social science fields. For instance, in cardiovascular research, they can monitor patients' health over decades to identify risk factors for heart disease, such as high cholesterol or smoking, and evaluate the long-term effectiveness of preventive measures. Similarly, in mental health studies, researchers might follow individuals from adolescence into adulthood to understand the development and progression of conditions like...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

AI-based selection of tumor regions for genomic profiling in neuropathology.

Neuro-oncology advances·2026
Same author

Clinical decision support in hematological malignancies using a case-grounded AI agent.

Nature medicine·2026
Same author

A deep learning framework for efficient pathology image analysis.

Nature communications·2026
Same author

Precision medicine in mental health: applications, challenges, and recommendations - CORRIGENDUM.

European psychiatry : the journal of the Association of European Psychiatrists·2026
Same author

Decomposing neuroanatomical heterogeneity in depression: insights from an ENIGMA major depressive disorder working group study in 5146 individuals.

Translational psychiatry·2026
Same author

Counterfactual Diffusion Models Provide Interpretable Explanations of Artificial Intelligence Models in Pathology.

Cancer research·2026
Same journal

From Alliance to Nexus: Rethinking Digital Therapeutic Relationships.

JMIR mental health·2026
Same journal

Governing Ethical Tensions in Youth Digital Mental Health Research.

JMIR mental health·2026
Same journal

Use of a Conversational Agent for Training Mental Health Professionals in Suicide Safety Planning: Pilot Feasibility and Acceptability Study.

JMIR mental health·2026
Same journal

Coproduction Without Youth? Closing the Participation Gap in Digital Mental Health Research.

JMIR mental health·2026
Same journal

Using AI to Detect Psychosis Relapse: Scoping Review.

JMIR mental health·2026
Same journal

Prevalence and Predictors of Self-Reported Adverse Experiences in Digital Meditation Training: 2 Randomized Controlled Trials.

JMIR mental health·2026
See all related articles
Summary
This summary is machine-generated.

Predicting functional outcomes in young adults with mental health conditions is crucial. Machine learning models, including large language models (LLMs), show promise in forecasting global functioning using clinical data.

Area of Science:

  • Neuroscience
  • Psychiatry
  • Machine Learning

Background:

  • Rising rates of functional impairments in mental health conditions necessitate improved prognostic tools.
  • Current prognostic models often focus on psychosis, but a transdiagnostic approach is needed for early recognition services.
  • Predicting functional outcomes can enhance the targeting of preventive interventions for mental health disorders.

Purpose of the Study:

  • To predict global functioning in young, help-seeking individuals over a 2-year follow-up period.
  • To utilize baseline clinical and structural magnetic resonance imaging (MRI) data for prediction.
  • To explore a transdiagnostic approach for predicting functional outcomes in affective, anxiety, and attention-deficit hyperactivity disorder (ADHD) presentations.

Main Methods:

Keywords:
longitudinal studiesmachine learningmagnetic resonance imagingmental disordersnatural language processingneuroimagingprognosisyoung adult

Related Experiment Videos

  • Classified 357 individuals (aged 18-35) as impaired (Global Assessment of Functioning [GAF] ≤60) or non-impaired (GAF>60) at 1- or 2-year follow-up.
  • Employed linear support vector machine (SVM), decision tree, and large language model (LLM) Llama-3 to predict GAF status using clinical data and/or structural MRI.
  • Utilized leave-one-site-out (SVM) or external sample (LLM) for validation.

Main Results:

  • SVM achieved 69.2% balanced accuracy using clinical features, with occupational functioning, interpersonal relationships, cognitive function, and symptom severity being most predictive.
  • Decision tree analysis identified 5 key predictive items, reaching 76.6% balanced accuracy.
  • Structural MRI data (amygdala, hippocampus) did not enhance prediction (57.1% balanced accuracy), while Llama-3 showed comparable performance to SVM (72.6% balanced accuracy).

Conclusions:

  • Machine learning models demonstrate significant potential for predicting global functioning in individuals with mental health conditions.
  • An out-of-the-box LLM achieved comparable predictive performance without specific training, highlighting the utility of free-text data for mental health prognosis.
  • These findings support the use of machine learning and LLMs in developing transdiagnostic tools for mental health outcome prediction.