# RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction

arXiv: https://arxiv.org/abs/2308.05046 · HTML: https://mlsanity.com/paper/2308.05046/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://mlsanity.com/paper/1906.05474/) (2019)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [Knowledge Matters: Radiology Report Generation with General and Specific Knowledge](https://mlsanity.com/paper/2112.15009/) (2021)
- [Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labels](https://mlsanity.com/paper/2005.12734/) (2020)
- [Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation](https://mlsanity.com/paper/2303.17579/) (2023)
- [Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learning](https://mlsanity.com/paper/1802.05800/) (2018)
- [CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases](https://mlsanity.com/paper/1610.08763/) (2016)
- [VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels](https://mlsanity.com/paper/2102.11467/) (2021)
- [Gradual Fine-Tuning for Low-Resource Domain Adaptation](https://mlsanity.com/paper/2103.02205/) (2021)
- [Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation](https://mlsanity.com/paper/2206.01988/) (2022)
- [CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output](https://mlsanity.com/paper/2006.15229/) (2020)
- [Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss](https://mlsanity.com/paper/1803.03378/) (2018)
- [Understanding Spatial Language in Radiology: Representation Framework, Annotation, and Spatial Relation Extraction from Chest X-ray Reports using Deep Learning](https://mlsanity.com/paper/1908.04485/) (2019)

## Built on by (most cited first, 11 of 11)

- [LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation](https://mlsanity.com/paper/2404.00998/) (2024)
- [Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges](https://mlsanity.com/paper/2309.04550/) (2023)
- [Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation](https://mlsanity.com/paper/2505.21190/) (2025)
- [Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs](https://mlsanity.com/paper/2408.14397/) (2024)
- [CLEAR: A Clinically-Grounded Tabular Framework for Radiology Report Evaluation](https://mlsanity.com/paper/2505.16325/) (2025)
- [MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data](https://mlsanity.com/paper/2601.06847/) (2026)
- [Modeling Clinical Uncertainty in Radiology Reports: from Explicit Uncertainty Markers to Implicit Reasoning Pathways](https://mlsanity.com/paper/2511.04506/) (2025)
- [RadTimeline: Timeline Summarization for Longitudinal Radiological Lung Findings](https://mlsanity.com/paper/2603.22820/) (2026)
- [A Dual-View Approach to Classifying Radiology Reports by Co-Training](https://mlsanity.com/paper/2406.05995/) (2024)
- [MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting](https://mlsanity.com/paper/2412.02971/) (2024)
- [RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI](https://mlsanity.com/paper/2605.00421/) (2026)

## Abstract (arXiv)

We present RadGraph2, a novel dataset for extracting information from radiology reports that focuses on capturing changes in disease state and device placement over time. We introduce a hierarchical schema that organizes entities based on their relationships and show that using this hierarchy during training improves the performance of an information extraction model. Specifically, we propose a modification to the DyGIE++ framework, resulting in our model HGIE, which outperforms previous models in entity and relation extraction tasks. We demonstrate that RadGraph2 enables models to capture a wider variety of findings and perform better at relation extraction compared to those trained on the original RadGraph dataset. Our work provides the foundation for developing automated systems that can track disease progression over time and develop information extraction models that leverage the natural hierarchy of labels in the medical domain.