Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
This addresses the challenge of modeling disease dynamics in clinical settings where data is limited, offering a hybrid approach that combines domain knowledge with machine learning for improved predictions in pharmacology and healthcare.
The paper tackled the problem of predicting disease progression under medications by integrating expert-designed ODEs from pharmacology with Neural ODEs to handle small sample regimes and unobservable variables, resulting in consistent outperformance of previous works, especially with few training samples.
Modeling a system's temporal behaviour in reaction to external stimuli is a fundamental problem in many areas. Pure Machine Learning (ML) approaches often fail in the small sample regime and cannot provide actionable insights beyond predictions. A promising modification has been to incorporate expert domain knowledge into ML models. The application we consider is predicting the progression of disease under medications, where a plethora of domain knowledge is available from pharmacology. Pharmacological models describe the dynamics of carefully-chosen medically meaningful variables in terms of systems of Ordinary Differential Equations (ODEs). However, these models only describe a limited collection of variables, and these variables are often not observable in clinical environments. To close this gap, we propose the latent hybridisation model (LHM) that integrates a system of expert-designed ODEs with machine-learned Neural ODEs to fully describe the dynamics of the system and to link the expert and latent variables to observable quantities. We evaluated LHM on synthetic data as well as real-world intensive care data of COVID-19 patients. LHM consistently outperforms previous works, especially when few training samples are available such as at the beginning of the pandemic.