Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign

TL;DR

Peak-Detector employs instruction-tuned large language models with a novel signal representation to achieve accurate, explainable peak detection across multiple physiological signal modalities, enhancing transparency and robustness.

Contribution

It introduces a cross-modal, explainable peak detection framework using instruction-tuned LLMs and a new signal representation technique, improving generalizability and interpretability over traditional methods.

Findings

Achieves state-of-the-art or tied-best detection accuracy across four physiological modalities.

Provides self-explanations that help identify failure modes and support verification.

Demonstrates robustness across seven diverse datasets, including real-world data.

Abstract

Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiogram (BCG), and Bodyseismography (BSG), is fundamental for cardiovascular monitoring but is often hindered by artifacts and signal variability. Conventional algorithms are typically engineered with expert knowledge for a single signal modality, limiting their generalizability. Conversely, deep learning-based methods often lack interpretability, limiting transparency for expert verification and hindering expert-computer interaction. To address these limitations, we introduce Peak-Detector, a novel framework that leverages instruction-tuned Large Language Models (LLMs) for robust, cross-modal, and explainable peak detection. A core innovation of our framework is a "peak-representation" technique that transforms time-series data into a condensed format, preserving critical event information while significantly reducing signal length. This representation provides a crucial inductive bias, guiding the LLM to reason over physiologically meaningful events rather than raw, noisy data. The model is optimized through a two-stage process: supervised fine-tuning (SFT) followed by reinforcement learning (RL) with a multi-objective reward function. The model's self-explanation capabilities are cultivated by fine-tuning on a custom-built Peak-Explanation dataset. Across four modalities-ECG, PPG, BCG, and BSG-spanning seven datasets (six public benchmarks plus one real-world cohort), Peak-Detector demonstrates strong cross-modal performance, achieving best or tied-best detection under clinically relevant temporal tolerance. Beyond accuracy, the generated rationales surface failure modes and support verification and error analysis.