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 Concept Videos

Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Modeling in Therapy01:26

Modeling in Therapy

Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Treatment Strategies for Psychological Disorders01:24

Treatment Strategies for Psychological Disorders

Treatment approaches for psychological disorders fall into three main categories: psychological, biological, and sociocultural. Each approach targets different aspects of mental health, requiring varying levels of education and training.
Psychological therapies focus on modifying emotions, thoughts, and behaviors through talking, interpreting, listening, rewarding, challenging, and modeling. Clinical psychologists, counselors, and social workers commonly practice psychotherapy. Clinical...
Language and Cognition01:27

Language and Cognition

Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.

You might also read

Related Articles

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

Sort by
Same author

Changes in resting-state functional connectivity linked to affective symptoms: insights from a population-based study of adolescents and young adults.

Translational psychiatry·2026
Same author

The neuroanatomy of depression: weak but replicable effects in 4021 individuals from three clinical cohorts.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

How to benchmark medical AI agents.

PLoS medicine·2026
Same author

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

Neuro-oncology advances·2026
Same author

Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction.

Brain informatics·2026
Same author

Mutation enrichment in targeted panels flags immunotherapy-responsive POLE-driven hypermutated microsatellite-stable colorectal cancers.

NPJ precision oncology·2026

Related Experiment Video

Updated: Jun 27, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

clickBrick prompt engineering: optimizing large language model performance in clinical psychiatry.

Falk Gerrik Verhees1, Fabian Huth2, Vincent Meyer2

  • 1Department of Psychiatry and Psychotherapy, University Hospital Dresden, TUD Dresden University of Technology, Dresden, Germany. falkgerrik.verhees@ukdd.de.

Npj Mental Health Research
|June 25, 2026
PubMed
Summary

The clickBrick framework significantly improves large language models' (LLMs) accuracy in extracting psychopathological criteria from clinical notes. This structured prompt engineering enhances AI

Related Experiment Videos

Last Updated: Jun 27, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Natural Language Processing
  • Psychiatric Informatics

Background:

  • Large language models (LLMs) show promise in clinical research, achieving expert-level performance on tasks like pathology classification and suicidality identification.
  • Effective prompt engineering is crucial for optimizing LLM performance, particularly in complex domains like clinical data analysis.
  • The clickBrick framework is introduced as a modular approach to enhance LLM capabilities through structured prompt design.

Purpose of the Study:

  • To evaluate the effectiveness of the clickBrick prompt engineering framework for comprehensive psychopathological assessment using LLMs.
  • To compare the performance of two locally-run LLMs in extracting 12 transdiagnostic psychopathological criteria from electronic health records.
  • To assess the clinical utility of clickBrick-enhanced LLM outputs in predicting psychiatric diagnoses.

Main Methods:

  • Employed the clickBrick framework to progressively structure prompts for LLM-based extraction of 12 psychopathological criteria from 100 psychiatric patient records.
  • Compared LLM performance against expert-labeled ground truth across various prompt structures.
  • Trained linear support vector machines on LLM outputs to predict discharge diagnoses for 1692 patients, assessing clinical value.

Main Results:

  • Reliable extraction of information across 12 psychopathological classification tasks achieved balanced accuracies from 71% to 94%.
  • The clickBrick framework substantially improved extraction accuracy by 19% to 36% for the most responsive LLM.
  • A reasoning prompt within clickBrick demonstrated superior performance in 7 out of 12 extraction domains.

Conclusions:

  • Iterative, expert-led prompt engineering with clickBrick is critical for realizing the clinical potential of LLMs in mental health.
  • The clickBrick framework provides a reproducible and explainable method for deploying trustworthy AI in clinical settings.
  • clickBrick enhanced LLM performance improved overall classification accuracy for psychiatric diagnoses from 71% to 76%.