# Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks

arXiv: https://arxiv.org/abs/2511.17056 · HTML: https://mlsanity.com/paper/2511.17056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health](https://mlsanity.com/paper/2306.10070/) (2023)
- [Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer](https://mlsanity.com/paper/1906.04716/) (2019)
- [MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare](https://mlsanity.com/paper/1810.09593/) (2018)
- [Causal Machine Learning for Healthcare and Precision Medicine](https://mlsanity.com/paper/2205.11402/) (2022)
- [Multimodal Machine Learning for Automated ICD Coding](https://mlsanity.com/paper/1810.13348/) (2018)
- [Bayesian Networks in Healthcare: Distribution by Medical Condition](https://mlsanity.com/paper/2002.00224/) (2020)
- [A Comprehensive Scoping Review of Bayesian Networks in Healthcare: Past, Present and Future](https://mlsanity.com/paper/2002.08627/) (2020)
- [RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records](https://mlsanity.com/paper/2403.00815/) (2024)
- [The Three Ghosts of Medical AI: Can the Black-Box Present Deliver?](https://mlsanity.com/paper/2012.06000/) (2020)
- [Multimodal data matters: language model pre-training over structured and unstructured electronic health records](https://mlsanity.com/paper/2201.10113/) (2022)
- [Hierarchical Pretraining on Multimodal Electronic Health Records](https://mlsanity.com/paper/2310.07871/) (2023)
- [Graph-Text Multi-Modal Pre-training for Medical Representation Learning](https://mlsanity.com/paper/2203.09994/) (2022)
- [SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records](https://mlsanity.com/paper/2409.08936/) (2024)
- [Clinical Reasoning over Tabular Data and Text with Bayesian Networks](https://mlsanity.com/paper/2403.09481/) (2024)
- [Investigating potential causes of Sepsis with Bayesian network structure learning](https://mlsanity.com/paper/2406.09207/) (2024)

## Abstract (arXiv)

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.