Article

clickBrick Prompt Engineering: Optimizing Large Language Model Performance in Clinical Psychiatry

2025-06-30

Abstract excerpt

<h4>Background: </h4> Prompt engineering has the potential to enhance large language models (LLM) ability to solve tasks through improved in-context learning. In clinical research, the use of LLMs has shown expert-level performance for a variety of tasks ranging from pathology slide classification to identifying suicidality. We introduce clickBrick, a modular prompt-engineering framework, and rigorously test its e...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 23a9b902-b6cf-53d6-935c-548422bc7301
DOI: 10.1101/2025.06.28.25330267

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

clickBrick Prompt Engineering: Optimizing Large Language Model Performance in Clinical PsychiatryDOI 10.1101/2025.06.28.25330267Read

Automated Insomnia Phenotyping from Electronic Health Records: Leveraging Large Language Models to Decode Clinical NarrativesSemantic proximity Read

Large-Scale Psychiatric Concept Extraction from Electronic Health Records: A Comparative Study of Encoder-Based Language ModelsSemantic proximity Read

A Systematic Exploration of LLM Behavior for EHR PhenotypingSemantic proximity Read

Explainable Suicide Phenotyping from Initial Psychiatric Evaluation Notes Using Reasoning Large Language ModelsSemantic proximity Read

Explainable Suicide Phenotyping from Initial Psychiatric Evaluation Notes Using Reasoning Large Language Models.Semantic proximity Read

Evaluation of large language model chatbot responses to psychotic promptsSemantic proximity Read

Zero-shot extraction of seizure outcomes from clinical notes using generative pretrained transformersSemantic proximity Read

Evaluating and Enhancing an AI Mental Health Guide in High-Risk Mental Health ContextsSemantic proximity Read

Disentangling Symptom Heterogeneity in Large-Scale Psychiatric Text: Domain-Adapted vs. Instruction-Tuned TransformersSemantic proximity Read

A retrieval-augmented generation large language model framework for accurate dementia identification from electronic health recordsSemantic proximity Read

First the Rules, Then the Summary: Piloting a Design for Accurate LLM-Generated Clinical SummariesSemantic proximity Read

Fine-Tuning PubMedBERT for Hierarchical Condition Category Classification from Clinical NotesSemantic proximity Read