🤖 AI Summary
Predicting consultation success rates on online healthcare platforms is challenging due to fragmented patient journeys, disconnection between virtual and physical healthcare systems, and sparsity/incompleteness of multi-source data (textual, temporal, behavioral).
Method: We propose a dynamic doctor–patient knowledge network modeling framework. First, we construct a cross-session, cross-role dynamic heterogeneous graph to capture implicit medical intent evolution. Second, we design an end-to-end multimodal fusion architecture that jointly aligns semantic features (via a multimodal Transformer), temporal patterns (via a behavioral sequence encoder), and topological structure (via a GNN), enhanced by knowledge distillation for robust training.
Contribution/Results: Evaluated on real-world platform data, our model achieves an AUC of 0.892—outperforming the state-of-the-art by 7.3%. Deployed in production, it improves consultation conversion rate by 12.6% and 30-day user retention by 9.1%.
📝 Abstract
Online healthcare consultation in virtual health is an emerging industry marked by innovation and fierce competition. Accurate and timely prediction of healthcare consultation success can proactively help online platforms address patient concerns and improve retention rates. However, predicting online consultation success is challenging due to the partial role of virtual consultations in patients' overall healthcare journey and the disconnect between online and in-person healthcare IT systems. Patient data in online consultations is often sparse and incomplete, presenting significant technical challenges and a research gap. To address these issues, we propose the Dynamic Knowledge Network and Multimodal Data Fusion (DyKoNeM) framework, which enhances the predictive power of online healthcare consultations. Our work has important implications for new business models where specific and detailed online communication processes are stored in the IT database, and at the same time, latent information with predictive power is embedded in the network formed by stakeholders' digital traces. It can be extended to diverse industries and domains, where the virtual or hybrid model (e.g., integration of online and offline services) is emerging as a prevailing trend.
