RECOVER: Designing a Large Language Model-based Remote Patient Monitoring System for Postoperative Gastrointestinal Cancer Care

2025-02-09

AI Summary

Postoperative complications in gastrointestinal cancer are unpredictable, life-threatening, and poorly addressed by conventional remote patient monitoring (RPM) due to limited clinical integration. Method: We propose RECOVER—the first clinically co-designed LLM-enhanced RPM framework, developed via participatory design, clinical guideline knowledge structuring, and multi-stakeholder interface development to enable natural-language patient self-reporting and real-time, visual clinician oversight. Contributions/Results: (1) Six clinical integration strategies were distilled; (2) a dual-track information modeling mechanism—guideline-driven yet personalized—was established; (3) a responsible AI implementation pathway for postoperative oncology monitoring was articulated. Real-world dual-track evaluation demonstrated significantly improved early complication detection and response efficiency, high usability acceptance from both clinicians and patients, and yielded reusable design principles and implementation paradigms for LLM-augmented clinical monitoring systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Cancer surgery is a key treatment for gastrointestinal (GI) cancers, a group of cancers that account for more than 35% of cancer-related deaths worldwide, but postoperative complications are unpredictable and can be life-threatening. In this paper, we investigate how recent advancements in large language models (LLMs) can benefit remote patient monitoring (RPM) systems through clinical integration by designing RECOVER, an LLM-powered RPM system for postoperative GI cancer care. To closely engage stakeholders in the design process, we first conducted seven participatory design sessions with five clinical staff and interviewed five cancer patients to derive six major design strategies for integrating clinical guidelines and information needs into LLM-based RPM systems. We then designed and implemented RECOVER, which features an LLM-powered conversational agent for cancer patients and an interactive dashboard for clinical staff to enable efficient postoperative RPM. Finally, we used RECOVER as a pilot system to assess the implementation of our design strategies with four clinical staff and five patients, providing design implications by identifying crucial design elements, offering insights on responsible AI, and outlining opportunities for future LLM-powered RPM systems.

Problem

• Designing LLM-based RPM system
• Postoperative GI cancer care
• Integrating clinical guidelines

Innovation

• LLM-powered RPM system
• Conversational agent for patients
• Interactive dashboard for staff