# Modeling Clinical Uncertainty in Radiology Reports: from Explicit Uncertainty Markers to Implicit Reasoning Pathways

arXiv: https://arxiv.org/abs/2511.04506 · HTML: https://mlsanity.com/paper/2511.04506/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 42 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction](https://mlsanity.com/paper/2308.05046/) (2023)
- [Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation](https://mlsanity.com/paper/2505.21190/) (2025)
- [BioLORD-2023: Semantic Textual Representations Fusing LLM and Clinical Knowledge Graph Insights](https://mlsanity.com/paper/2311.16075/) (2023)

## Built on by (most cited first, 4 of 4)

- [The Slop Paradox: How Synthetic Standardization Erodes Clinical Uncertainty and Cross-Modal Alignment in AI-Rewritten Radiology Reports](https://mlsanity.com/paper/2606.17791/) (2026)
- [Bayesian uncertainty estimation improves clinical decision making in medical AI agents](https://mlsanity.com/paper/2607.20582/) (2026)
- [Clinically-Grounded Hierarchical Classification for Consistent Chest X-ray Interpretation](https://mlsanity.com/paper/2608.03016/) (2026)
- [UR2-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report Generation](https://mlsanity.com/paper/2608.22217/) (2026)

## Abstract (arXiv)

Radiology reports are invaluable for clinical decision-making and hold great potential for automated analysis when structured into machine-readable formats. These reports often contain uncertainty, which we categorize into two distinct types: (i) Explicit uncertainty reflects doubt about the presence or absence of findings, conveyed through hedging phrases. These vary in meaning depending on the context, making rule-based systems insufficient to quantify the level of uncertainty for specific findings; (ii) Implicit uncertainty arises when radiologists omit parts of their reasoning, recording only key findings or diagnoses. Here, it is often unclear whether omitted findings are truly absent or simply unmentioned for brevity. We address these challenges with a two-part framework. We quantify explicit uncertainty by creating an expert-validated, LLM-based reference ranking of common hedging phrases, and mapping each finding to a probability value based on this reference. In addition, we model implicit uncertainty through an expansion framework that systematically adds characteristic sub-findings derived from expert-defined diagnostic pathways for 14 common diagnoses. Using these methods, we release Lunguage++, an expanded, uncertainty-aware version of the Lunguage benchmark of fine-grained structured radiology reports. This enriched resource enables uncertainty-aware image classification, faithful diagnostic reasoning, and new investigations into the clinical impact of diagnostic uncertainty.