Towards Human-AI-Robot Collaboration and AI-Agent based Digital Twins for Parkinson's Disease Management: Review and Outlook

TL;DR

This paper addresses the fragmentation between PD sensing/monitoring and robotic rehabilitation by proposing a unified, AI-driven closed-loop framework that fuses multimodal sensing, agentic AI, and robotic interventions into a Parkinson's patient digital twin. It surveys two major pillars—wearable/IoT sensing modalities and robotic technologies (RARS, SARs, AR/VR platforms)—and articulates how advances in LLMs, foundation models, and agentic AI can bridge these domains. The authors introduce a concrete vision for a PD digital twin (PPDT) that integrates real-time multimodal data, AI reasoning, and robotics to deliver personalized, explainable care, with RLHF, RAG, and continual learning enabling adaptive decision support. They also discuss significant challenges—data labeling, privacy, rare-event handling, and clinical translation—while outlining actionable priorities such as data/evaluation standards, privacy-by-design, and human-in-the-loop frameworks to move from prototypes to scalable, patient-centered PD care.

Abstract

The current body of research on Parkinson's disease (PD) screening, monitoring, and management has evolved along two largely independent trajectories. The first research community focuses on multimodal sensing of PD-related biomarkers using noninvasive technologies such as inertial measurement units (IMUs), force/pressure insoles, electromyography (EMG), electroencephalography (EEG), speech and acoustic analysis, and RGB/RGB-D motion capture systems. These studies emphasize data acquisition, feature extraction, and machine learning-based classification for PD screening, diagnosis, and disease progression modeling. In parallel, a second research community has concentrated on robotic intervention and rehabilitation, employing socially assistive robots (SARs), robot-assisted rehabilitation (RAR) systems, and virtual reality (VR)-integrated robotic platforms for improving motor and cognitive function, enhancing social engagement, and supporting caregivers. Despite the complementary goals of these two domains, their methodological and technological integration remains limited, with minimal data-level or decision-level coupling between the two. With the advent of advanced artificial intelligence (AI), including large language models (LLMs), agentic AI systems, a unique opportunity now exists to unify these research streams. We envision a closed-loop sensor-AI-robot framework in which multimodal sensing continuously guides the interaction between the patient, caregiver, humanoid robot (and physician) through AI agents that are powered by a multitude of AI models such as robotic and wearables foundation models, LLM-based reasoning, reinforcement learning, and continual learning. Such closed-loop system enables personalized, explainable, and context-aware intervention, forming the basis for digital twin of the PD patient that can adapt over time to deliver intelligent, patient-centered PD care.

Figures (5)

• Figure 1: PD in a nutshell: prevalence, economic burden, vulnerable populations, risk factors, signs and symptoms (motor and non-motor), impact on quality of life of patient and that of family members and caregivers, pathology (based on molecular biology), biomarkers and clinical diagnosis (UPDRS and more), prognosis, intervention methods, non-invasive monitoring via wearables for measuring on/off states for measurement of effectiveness of medical intervention.
• Figure 2: Outline of this survey paper: Section II reviews selected literature that utilizes various sensors for PD research. Section III discusses the state-of-the-art on robots-based PD research. Section IV highlights the potential of closed-loop integration of sensor and robots via advanced AI tools such AI agents, LLMs, reinforcement learning to realize the concept of PD digital twin.
• Figure 3: Wearables, IoT and IoMT sensors used for continuous monitoring of motor and non-motor symptoms of PD patients.
• Figure 4: RARS, SARs and AR/VR-empowered robotic systems hold the promise for rehabilitation of IwPD under various different scenarios.
• Figure 5: Authors' vision: continuous monitoring and personalized care for Parkinson’s disease via agentic AI-powered robotic digital twins.