CTG-Insight: A Multi-Agent Interpretable LLM Framework for Cardiotocography Analysis and Classification

TL;DR

CTG-Insight is an interpretable multi-agent LLM framework that analyzes and classifies cardiotocography signals, providing structured medical insights and natural language explanations, achieving state-of-the-art accuracy.

Contribution

This work introduces a novel multi-agent LLM system for CTG analysis that offers interpretability and extensibility, outperforming existing models in accuracy and transparency.

Findings

Achieves 96.4% accuracy on NeuroFetalNet Dataset

Provides structured interpretation of CTG signals based on medical guidelines

Outperforms deep learning models and single-agent LLM baseline

Abstract

Remote fetal monitoring technologies are becoming increasingly common. Yet, most current systems offer limited interpretability, leaving expectant parents with raw cardiotocography (CTG) data that is difficult to understand. In this work, we present CTG-Insight, a multi-agent LLM system that provides structured interpretations of fetal heart rate (FHR) and uterine contraction (UC) signals. Drawing from established medical guidelines, CTG-Insight decomposes each CTG trace into five medically defined features: baseline, variability, accelerations, decelerations, and sinusoidal pattern, each analyzed by a dedicated agent. A final aggregation agent synthesizes the outputs to deliver a holistic classification of fetal health, accompanied by a natural language explanation. We evaluate CTG-Insight on the NeuroFetalNet Dataset and compare it against deep learning models and the single-agent LLM baseline. Results show that CTG-Insight achieves state-of-the-art accuracy (96.4%) and F1-score (97.8%) while producing transparent and interpretable outputs. This work contributes an interpretable and extensible CTG analysis framework.