AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom Tracking

2025-03-05

AI Summary

Traditional Parkinson’s disease (PD) diaries lack interactivity and clinical guidance, resulting in incomplete and inaccurate symptom and medication reporting. To address this, we propose PATRIKA—the first AI-driven conversational diary system integrating cooperative dialogue principles with structured clinical interview paradigms. PATRIKA employs clinical-knowledge-guided natural language generation (NLG), dynamic user modeling, and iterative human–AI co-design to enable personalized, progressive data collection via simulated clinician–patient dialogues. A user study demonstrated that targeted probing questions increased log information yield by 62%; 94% of participants indicated willingness for long-term adoption; and neurologists confirmed the clinical relevance and direct utility of the collected data. This work marks a paradigm shift in chronic disease self-reporting—from unidirectional logging to bidirectional clinical collaboration—substantially enhancing patient engagement and the clinical validity of patient-reported outcomes.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Journaling plays a crucial role in managing chronic conditions by allowing patients to document symptoms and medication intake, providing essential data for long-term care. While valuable, traditional journaling methods often rely on static, self-directed entries, lacking interactive feedback and real-time guidance. This gap can result in incomplete or imprecise information, limiting its usefulness for effective treatment. To address this gap, we introduce PATRIKA, an AI-enabled prototype designed specifically for people with Parkinson's disease (PwPD). The system incorporates cooperative conversation principles, clinical interview simulations, and personalization to create a more effective and user-friendly journaling experience. Through two user studies with PwPD and iterative refinement of PATRIKA, we demonstrate conversational journaling's significant potential in patient engagement and collecting clinically valuable information. Our results showed that generating probing questions PATRIKA turned journaling into a bi-directional interaction. Additionally, we offer insights for designing journaling systems for healthcare and future directions for promoting sustained journaling.

Problem

• Enhances Parkinson's disease symptom tracking with AI.
• Improves journaling accuracy through interactive feedback.
• Facilitates patient engagement and clinical data collection.

Innovation

• AI-enabled conversational journaling for Parkinson's disease
• Cooperative conversation principles and clinical simulations
• Personalized, bi-directional interaction for symptom tracking