# Hierarchical Section Matching Prediction (HSMP) BERT for Fine-Grained Extraction of Structured Data from Hebrew Free-Text Radiology Reports in Crohn's Disease

arXiv: https://arxiv.org/abs/2509.04519 · HTML: https://mlsanity.com/paper/2509.04519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [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)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4](https://mlsanity.com/paper/2310.12321/) (2023)
- [PromptBERT: Improving BERT Sentence Embeddings with Prompts](https://mlsanity.com/paper/2201.04337/) (2022)
- [HeRo: RoBERTa and Longformer Hebrew Language Models](https://mlsanity.com/paper/2304.11077/) (2023)
- [RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering](https://mlsanity.com/paper/2407.15621/) (2024)
- [Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language](https://mlsanity.com/paper/2405.01682/) (2024)

## Abstract (arXiv)

Extracting structured clinical information from radiology reports is challenging, especially in low-resource languages. This is pronounced in Crohn's disease, with sparsely represented multi-organ findings. We developed Hierarchical Structured Matching Prediction BERT (HSMP-BERT), a prompt-based model for extraction from Hebrew radiology text. In an administrative database study, we analyzed 9,683 reports from Crohn's patients imaged 2010-2023 across Israeli providers. A subset of 512 reports was radiologist-annotated for findings across six gastrointestinal organs and 15 pathologies, yielding 90 structured labels per subject. Multilabel-stratified split (66% train+validation; 33% test), preserving label prevalence. Performance was evaluated with accuracy, F1, Cohen's kappa, AUC, PPV, NPV, and recall. On 24 organ-finding combinations with >15 positives, HSMP-BERT achieved mean F1 0.83±0.08 and kappa 0.65±0.17, outperforming the SMP zero-shot baseline (F1 0.49±0.07, kappa 0.06±0.07) and standard fine-tuning (F1 0.30±0.27, kappa 0.27±0.34; paired t-test p < 10-7). Hierarchical inference cuts runtime 5.1× vs. traditional inference. Applied to all reports, it revealed associations among ileal wall thickening, stenosis, and pre-stenotic dilatation, plus age- and sex-specific trends in inflammatory findings. HSMP-BERT offers a scalable solution for structured extraction in radiology, enabling population-level analysis of Crohn's disease and demonstrating AI's potential in low-resource settings.