Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for Biometrics

TL;DR

This paper explores ethical front-end design considerations for sensor-fused health conversational agents, emphasizing biometric translation, risk mitigation, and user autonomy in AI health support systems.

Contribution

It introduces a novel ethical design space with five dimensions for biometric translation in health agents and proposes adaptive disclosure as a safety mechanism.

Findings

Identifies five key dimensions of ethical front-end design for biometric translation.

Analyzes interaction of design dimensions with context and biofeedback risks.

Proposes adaptive disclosure as a safety guardrail for health conversational agents.

Abstract

The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of "Sensor-Fused LLM agents" for personal health and well-being support. While recent breakthroughs have demonstrated the technical feasibility of this fusion (e.g., Time-LLM, SensorLLM), research primarily focuses on "Ethical Back-End Design for Generative AI", concerns such as sensing accuracy, bias mitigation in training data, and multimodal fusion. This leaves a critical gap at the front end, where invisible biometrics are translated into language directly experienced by users. We argue that the "illusion of objectivity" provided by sensor data amplifies the risks of AI hallucinations, potentially turning errors into harmful medical mandates. This paper shifts the focus to "Ethical Front-End Design for AI", specifically, the ethics of biometric translation. We propose a design space comprising five dimensions: Biometric Disclosure, Monitoring Temporality, Interpretation Framing, AI Stance, and Contestability. We examine how these dimensions interact with context (user- vs. system-initiated) and identify the risk of biofeedback loops. Finally, we propose "Adaptive Disclosure" as a safety guardrail and offer design guidelines to help developers manage fallibility, ensuring that these cutting-edge health agents support, rather than destabilize, user autonomy.