CALYPSO: Forecasting and Analyzing MRSA Infection Patterns with Community and Healthcare Transmission Dynamics

2025-08-19

AI Summary

This study addresses the challenges of cross-scale (community-to-healthcare) MRSA transmission prediction and interpretable intervention evaluation. We propose the first hybrid framework integrating deep neural networks with a mechanistic metapopulation model. Methodologically, we jointly model human mobility (via insurance claims, commuting flows, and referral data), spatiotemporal transmission dynamics, and intervention responses—enabling interpretable, multi-scale (state/county/institution) forecasting and counterfactual policy assessment. Our key contribution lies in the organic unification of data-driven learning and mechanistic modeling, balancing predictive accuracy with public health interpretability and operational feasibility. Experiments demonstrate that our approach reduces statewide prediction error by over 4.5% compared to pure machine learning baselines, accurately identifies high-risk regions, and generates cost-optimal resource allocation strategies for infection control.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Methicillin-resistant Staphylococcus aureus (MRSA) is a critical public health threat within hospitals as well as long-term care facilities. Better understanding of MRSA risks, evaluation of interventions and forecasting MRSA rates are important public health problems. Existing forecasting models rely on statistical or neural network approaches, which lack epidemiological interpretability, and have limited performance. Mechanistic epidemic models are difficult to calibrate and limited in incorporating diverse datasets. We present CALYPSO, a hybrid framework that integrates neural networks with mechanistic metapopulation models to capture the spread dynamics of infectious diseases (i.e., MRSA) across healthcare and community settings. Our model leverages patient-level insurance claims, commuting data, and healthcare transfer patterns to learn region- and time-specific parameters governing MRSA spread. This enables accurate, interpretable forecasts at multiple spatial resolutions (county, healthcare facility, region, state) and supports counterfactual analyses of infection control policies and outbreak risks. We also show that CALYPSO improves statewide forecasting performance by over 4.5% compared to machine learning baselines, while also identifying high-risk regions and cost-effective strategies for allocating infection prevention resources.

Problem

• Forecasting MRSA infection rates across healthcare and community settings
• Evaluating infection control policies and outbreak risk counterfactuals
• Integrating mechanistic models with neural networks for interpretable predictions

Innovation

• Hybrid neural-mechanistic metapopulation model
• Leverages multi-source patient mobility data
• Enables multi-resolution interpretable forecasting