# Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation

arXiv: https://arxiv.org/abs/2605.07785 · HTML: https://mlsanity.com/paper/2605.07785/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 18 of 18)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models](https://mlsanity.com/paper/2310.03182/) (2023)
- [VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels](https://mlsanity.com/paper/2102.11467/) (2021)
- [CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output](https://mlsanity.com/paper/2006.15229/) (2020)
- [A Structural Causal Model for MR Images of Multiple Sclerosis](https://mlsanity.com/paper/2103.03158/) (2021)
- [Causally Reliable Concept Bottleneck Models](https://mlsanity.com/paper/2503.04363/) (2025)
- [Cross-Modal Conceptualization in Bottleneck Models](https://mlsanity.com/paper/2310.14805/) (2023)
- [Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment](https://mlsanity.com/paper/2104.05261/) (2021)
- [Structural Causal Bottleneck Models](https://mlsanity.com/paper/2603.08682/) (2026)
- [Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays](https://mlsanity.com/paper/2403.19444/) (2024)
- [Explainability Through Human-Centric Design for XAI in Lung Cancer Detection](https://mlsanity.com/paper/2505.09755/) (2025)

## Built on by (most cited first, 1 of 1)

- [Matryoshka Concept Bottleneck Models](https://mlsanity.com/paper/2605.20612/) (2026)

## Abstract (arXiv)

Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final diagnoses. However, most existing CBMs treat concepts as discriminative predictors of pathology labels, without explicitly modelling the underlying clinical generative process where diseases produce observable radiographic findings. We propose XpertCausal, a radiologist-guided causal CBM for chest X-ray interpretation which models pathology-to-concept relationships using a probabilistic noisy-OR framework. This generative model is then inverted via Bayesian inference to estimate pathology probabilities from predicted concepts. Radiologist-curated concept-pathology associations are used to constrain model structure to radiologist-defined clinically plausible reasoning pathways. We evaluate XpertCausal on MIMIC-CXR across pathology classification performance, calibration, explanation quality, and alignment with radiologist-defined reasoning pathways. Compared with both a non-causal CBM baseline and a causal ablation with unconstrained learned associations, XpertCausal achieves improved AUROC, calibration, and clinically relevant explanation quality, while learning concept-pathology relationships that more closely align with expert knowledge. These results demonstrate that incorporating clinically motivated causal structure and expert domain knowledge into CBMs can lead to more accurate, interpretable, and clinically aligned models for CXR interpretation.