Online Transfer Learning for RSV Case Detection

TL;DR

This paper tackles the challenge of learning from sequential biomedical data with limited labeled target data by introducing Multi-Source Adaptive Weighting (MSAW), an online ensemble that dynamically weights pre-trained source models and a growing target model. By treating each season as a domain and updating weights in real time as new target data arrive, MSAW effectively blends historical knowledge with evolving evidence. Applied to RSV case detection in multi-year EHR data from UPMC, the approach outperforms static- and online-baseline methods, demonstrating the practical potential of online transfer learning for adaptable, data-efficient healthcare analytics. The study also highlights the method's ability to respond to domain shifts and seasonality, supporting more responsive public health planning and resource allocation.

Abstract

Transfer learning has become a pivotal technique in machine learning and has proven to be effective in various real-world applications. However, utilizing this technique for classification tasks with sequential data often faces challenges, primarily attributed to the scarcity of class labels. To address this challenge, we introduce Multi-Source Adaptive Weighting (MSAW), an online multi-source transfer learning method. MSAW integrates a dynamic weighting mechanism into an ensemble framework, enabling automatic adjustment of weights based on the relevance and contribution of each source (representing historical knowledge) and target model (learning from newly acquired data). We demonstrate the effectiveness of MSAW by applying it to detect Respiratory Syncytial Virus cases within Emergency Department visits, utilizing multiple years of electronic health records from the University of Pittsburgh Medical Center. Our method demonstrates performance improvements over many baselines, including refining pre-trained models with online learning as well as three static weighting approaches, showing MSAW's capacity to integrate historical knowledge with progressively accumulated new data. This study indicates the potential of online transfer learning in healthcare, particularly for developing machine learning models that dynamically adapt to evolving situations where new data is incrementally accumulated.

Figures (2)

• Figure 1: Architecture of the proposed ensemble model.
• Figure 2: (a) Probability of a feature present given RSV (b) $Log_{10} LR$ of features present.