Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors

2025-05-16

AI Summary

Psychiatric diagnosis suffers from subjectivity and limited accessibility, often delaying timely intervention. To address this, we propose a human-centered, contestable AI-assisted diagnostic system. It acquires R-R interval (RRI) and heart rate variability (HRV) time-series data via Polar H9/H10 wearable ECG devices and employs a Multi-Scale Time-Frequency Transformer (MSTFT) to jointly model autonomic nervous system dysfunction across temporal and spectral domains. Crucially, we introduce a novel diagnostic interface integrating Self-Adversarial Explanation (SAE) with a Contestable Large Language Model (Contestable LLM), enabling clinicians to transparently verify and actively challenge AI-generated decisions. Evaluated on the HRV-ACC dataset using leave-one-out cross-validation, our system achieves 91.7% accuracy—significantly outperforming state-of-the-art methods—while SAE effectively detects explanation inconsistencies. The system is open-source and supports real-time clinical interaction and validation.

Technology Category

• Humans and AI: AI for Accessibility
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Psychiatric disorders affect millions globally, yet their diagnosis faces significant challenges in clinical practice due to subjective assessments and accessibility concerns, leading to potential delays in treatment. To help address this issue, we present Heart2Mind, a human-centered contestable psychiatric disorder diagnosis system using wearable electrocardiogram (ECG) monitors. Our approach leverages cardiac biomarkers, particularly heart rate variability (HRV) and R-R intervals (RRI) time series, as objective indicators of autonomic dysfunction in psychiatric conditions. The system comprises three key components: (1) a Cardiac Monitoring Interface (CMI) for real-time data acquisition from Polar H9/H10 devices; (2) a Multi-Scale Temporal-Frequency Transformer (MSTFT) that processes RRI time series through integrated time-frequency domain analysis; (3) a Contestable Diagnosis Interface (CDI) combining Self-Adversarial Explanations (SAEs) with contestable Large Language Models (LLMs). Our MSTFT achieves 91.7% accuracy on the HRV-ACC dataset using leave-one-out cross-validation, outperforming state-of-the-art methods. SAEs successfully detect inconsistencies in model predictions by comparing attention-based and gradient-based explanations, while LLMs enable clinicians to validate correct predictions and contest erroneous ones. This work demonstrates the feasibility of combining wearable technology with Explainable Artificial Intelligence (XAI) and contestable LLMs to create a transparent, contestable system for psychiatric diagnosis that maintains clinical oversight while leveraging advanced AI capabilities. Our implementation is publicly available at: https://github.com/Analytics-Everywhere-Lab/heart2mind.

Problem

• Diagnosing psychiatric disorders objectively using wearable ECG data
• Addressing subjectivity in mental health assessments with AI biomarkers
• Enabling clinician contestability in AI-driven psychiatric diagnosis systems

Innovation

• Wearable ECG monitors for real-time cardiac data
• Multi-Scale Temporal-Frequency Transformer for analysis
• Contestable AI with explainable and adversarial components