A Voice-based Triage for Type 2 Diabetes using a Conversational Virtual Assistant in the Home Environment

2024-11-28

arXiv.org

AI Summary

This study addresses the challenge of early, at-home screening for type 2 diabetes (T2D) in elderly populations. We propose a non-intrusive initial screening method based on voice pathology analysis: natural conversational speech is captured via off-the-shelf virtual assistants, from which seven non-identifying acoustic features are extracted; a lightweight classification model is deployed on edge devices to enable real-time, low-resource, privacy-preserving risk assessment. Our key innovation lies in deeply embedding acoustic machine learning–based triage into consumer-grade voice assistants, establishing an Internet-of-Medical-Things (IoMT) cloud-edge collaborative architecture. In a pilot study with 24 older adults, the system achieved detection sensitivities of 70% for males and 60% for females—constituting the first empirical validation of voice-driven T2D risk screening feasibility in real-world home settings.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Speech

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Incorporating cloud technology with Internet of Medical Things for ubiquitous healthcare has seen many successful applications in the last decade with the advent of machine learning and deep learning techniques. One of these applications, namely voice-based pathology, has yet to receive notable attention from academia and industry. Applying voice analysis to early detection of fatal diseases holds much promise to improve health outcomes and quality of life of patients. In this paper, we propose a novel application of acoustic machine learning based triaging into commoditised conversational virtual assistant systems to pre-screen for onset of diabetes. Specifically, we developed a triaging system which extracts acoustic features from the voices of n=24 older adults when they converse with a virtual assistant and predict the incidence of Diabetes Mellitus (Type 2) or not. Our triaging system achieved hit-rates of 70% and 60% for male and female older adult subjects, respectively. Our proposed triaging uses 7 non-identifiable voice-based features and can operate within resource-constrained embedded systems running voice-based virtual assistants. This application demonstrates the feasibility of applying voice-based pathology analysis to improve health outcomes of older adults within the home environment by early detection of life-changing chronic conditions like diabetes.

Problem

• Develop voice-based diabetes triage using virtual assistants
• Detect Type 2 Diabetes via acoustic analysis of older adults
• Enable early screening with non-identifiable voice features

Innovation

• Voice-based triage using conversational virtual assistant
• Acoustic machine learning for diabetes pre-screening
• Cloud and IoT for home healthcare monitoring