Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks
This work addresses the need for reliable data extraction in clinical decision support systems, but it is incremental as it builds on existing multi-modal fusion techniques with a focus on calibration and consistency.
The paper tackles the problem of extracting structured patient-level information from electronic health records by integrating both tabular data and unstructured text, using a Bayesian network with a consistency node to improve prediction calibration and handle contradictions. The result is a method that enhances interpretability and performance on the SimSUM dataset, though specific numerical gains are not detailed.
Electronic health records (EHRs) form an invaluable resource for training clinical decision support systems. To leverage the potential of such systems in high-risk applications, we need large, structured tabular datasets on which we can build transparent feature-based models. While part of the EHR already contains structured information (e.g. diagnosis codes, medications, and lab results), much of the information is contained within unstructured text (e.g. discharge summaries and nursing notes). In this work, we propose a method for multi-modal patient-level information extraction that leverages both the tabular features available in the patient's EHR (using an expert-informed Bayesian network) as well as clinical notes describing the patient's symptoms (using neural text classifiers). We propose the use of virtual evidence augmented with a consistency node to provide an interpretable, probabilistic fusion of the models' predictions. The consistency node improves the calibration of the final predictions compared to virtual evidence alone, allowing the Bayesian network to better adjust the neural classifier's output to handle missing information and resolve contradictions between the tabular and text data. We show the potential of our method on the SimSUM dataset, a simulated benchmark linking tabular EHRs with clinical notes through expert knowledge.