Changing the Paradigm from Dynamic Queries to LLM-generated SQL Queries with Human Intervention

2025-09-11

AI Summary

Traditional dynamic query interfaces (e.g., sliders, checkboxes) impose high cognitive load, cause visual clutter, and lack filtering transparency when applied to high-dimensional, heterogeneous, and encoded medical data in health visualization. Method: This paper proposes a novel paradigm leveraging large language models (LLMs) as the interaction layer: medical experts’ natural language analysis intents are automatically parsed into editable, executable SQL queries—replacing static control-based interfaces. The approach integrates NL2SQL techniques, an editable query editor, and an EventFlow-inspired visualization framework, while retaining lightweight dynamic controls on-demand to ensure filter interpretability. Contribution/Results: Deployed within France’s national health data platform and evaluated in ParcoursVis, the system significantly reduces memorization burden for field names and encodings, improves query construction efficiency and exploratory fluidity, and—uniquely—enables natural-language-driven, transparent, controllable, and clinician-oriented interactive analysis of high-dimensional health data.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Question Answering
• Humans and AI: Intelligent User Interfaces

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

We propose leveraging Large Language Models (LLMs) as an interaction layer for medical visualization systems. In domains like healthcare, where users must navigate high-dimensional, coded, and heterogeneous datasets, LLM-generated queries enable expert medical users to express complex analytical intents in natural language. These intents are then translated into editable and executable queries, replacing the dynamic query interfaces used by traditional visualization systems built around sliders, check boxes, and drop-downs. This interaction model reduces visual clutter and eliminates the need for users to memorize field names or system codes, supporting fluid exploration, with the drawback of not exposing all the filtering criteria. We also reintroduce dynamic queries on demand to better support interactive exploration. We posit that medical users are trained to know the possible filtering options but challenged to remember the details of the attribute names and code values. We demonstrate this paradigm in ParcoursVis, our scalable EventFlow-inspired patient care pathway visualization system powered by the French National Health Data System, one of the largest health data repositories in the world.

Problem

• Translating natural language medical queries into SQL
• Replacing dynamic query interfaces with LLM-generated queries
• Supporting expert users in navigating complex healthcare datasets

Innovation

• LLM-generated SQL queries with human intervention
• Replacing dynamic queries with natural language interface
• Combining LLM queries with on-demand dynamic queries