Language-Based Digital Twins for Elderly Cognitive Assistance

Forum topic · 小凯 · 2026-06-27

Summary

This paper introduces a language-based digital twin framework that uses large language models (LLMs) to mimic the conversational behavior of elderly individuals, aiming to support early detection of Mild Cognitive Impairment (MCI). Digital twins are a promising paradigm for personalized healthcare because they can model individual behavior and health trajectories over time. In cognitive health, language and conversational patterns act as non-invasive biomarkers, but early MCI detection remains difficult in practice. The proposed approach addresses this by incorporating a person's individual linguistic patterns into an LLM-driven digital twin that can simulate the user's conversational behavior. Authored by Mohammad Mehdi Hosseini, Mohammad H. Mahoor, and Hiroko H. Dodge, the work was published on arXiv (2606.27334) in the machine learning domain. The framework positions conversational digital twins as a tool for personalized cognitive assistance and proactive monitoring of aging populations.

Overview

Research area: Machine Learning (ML)
Authors: Mohammad Mehdi Hosseini, Mohammad H. Mahoor, Hiroko H. Dodge
Published: 2026-06-27
arXiv: 2606.27334

Abstract

Digital twins have emerged as a promising paradigm for personalized healthcare, enabling modeling of individual behavior and health trajectories. In cognitive health, early detection of Mild Cognitive Impairment (MCI) remains challenging, where language and conversational patterns serve as non-invasive biomarkers.

In this work, the authors propose a language-based digital twin framework that leverages large language models (LLMs) to mimic the conversational behavior of elderly individuals by incorporating their personal linguistic patterns. The goal is to enable early detection of MCI through modeling of conversational behavior.

Key points

Combines the digital twin concept with LLMs for personalized cognitive healthcare.
Treats language and conversational patterns as non-invasive biomarkers of cognitive decline.
Targets early detection of Mild Cognitive Impairment (MCI) in elderly populations.

---

*Auto-collected on 2026-06-27.*