Background: Intensive Care Unit readmissions represent both a health riskfor patients and a financial burden for healthcare facilities. As healthcare became more data-driven with the introduction of Electronic Health Records, machine learning methods have been applied to predict Intensive Care Unit (ICU) readmission risk. However, these methods disregard the meaningand relationships of data objects and work blindly over clinical data without taking into account scientific knowledge and context. Ontologies and Knowledge Graphs can help bridge this gap between data and scientific context, as they are computational artefacts that represent the entities of adomain and their relationships to each other in a formalized way.
Methods and Results: We have developed an approach that enriches Electronic Health Records data with semantic annotations to ontologies, and then generates Knowledge Graph embeddings to represent a patient’s stay in the ICU in a contextualized manner. These are used by machine learning models to predict the 30-day ICU readmission risk. This approach is based on several contributions: (1) an enrichment of the MIMIC-III dataset with patient-oriented annotations to various biomedical ontologies; (2) a predictive model of ICU readmission risk that uses Knowledge Graph embeddings to represent patient data using semantic annotations; (3) a variant of the predictive model that targets different time points during an ICU stay. Our predictive approaches outperformed both a baseline and state-of-the-art works achieving a mean Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.827 and an Area Under the Precision-Recall Curve (AUPRC) of 0.691. The application of this novel approach to help clinicians decide whether a patient can be discharged has the potential to prevent the readmission of 40% of Intensive Care Unit patients, without unnecessarily prolonging the stay of those who would not require it.
Conclusion: The coupling of semantic annotation and Knowledge Graph embeddings affords two clear advantages: they consider scientific context and they are able to build representations of Electronic Health Records (EHR) information of different types in a common format. This work demonstrates the potential for impact that integrating ontologies and Knowledge Graphs into clinical machine learning applications can have.