Knowledge Graph Representations to enhance Intensive Care Time-Series Predictions
This work addresses the challenge of enhancing clinical outcome predictions in Intensive Care Units for healthcare professionals, but it is incremental as it builds on existing fusion models by adding knowledge graphs.
The paper tackled the problem of integrating established medical knowledge into ICU predictive models by proposing a method that combines knowledge graph representations with patient time-series data and clinical reports, resulting in improved performance, particularly in handling missing data, and includes an interpretability component.
Intensive Care Units (ICU) require comprehensive patient data integration for enhanced clinical outcome predictions, crucial for assessing patient conditions. Recent deep learning advances have utilized patient time series data, and fusion models have incorporated unstructured clinical reports, improving predictive performance. However, integrating established medical knowledge into these models has not yet been explored. The medical domain's data, rich in structural relationships, can be harnessed through knowledge graphs derived from clinical ontologies like the Unified Medical Language System (UMLS) for better predictions. Our proposed methodology integrates this knowledge with ICU data, improving clinical decision modeling. It combines graph representations with vital signs and clinical reports, enhancing performance, especially when data is missing. Additionally, our model includes an interpretability component to understand how knowledge graph nodes affect predictions.