# CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output

arXiv: https://arxiv.org/abs/2006.15229 · HTML: https://mlsanity.com/paper/2006.15229/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 23 of 23)

- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images](https://mlsanity.com/paper/2302.14042/) (2023)
- [Improving the Fairness of Chest X-ray Classifiers](https://mlsanity.com/paper/2203.12609/) (2022)
- [VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels](https://mlsanity.com/paper/2102.11467/) (2021)
- [Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.17004/) (2023)
- [CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes](https://mlsanity.com/paper/2106.02524/) (2021)
- [Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research](https://mlsanity.com/paper/2311.09402/) (2023)
- [UniBrain: Universal Brain MRI Diagnosis with Hierarchical Knowledge-enhanced Pre-training](https://mlsanity.com/paper/2309.06828/) (2023)
- [RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction](https://mlsanity.com/paper/2308.05046/) (2023)
- [Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs](https://mlsanity.com/paper/2408.14397/) (2024)
- [Learning to diagnose common thorax diseases on chest radiographs from radiology reports in Vietnamese](https://mlsanity.com/paper/2209.04794/) (2022)
- [Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality](https://mlsanity.com/paper/2105.01009/) (2021)
- [CoRPA: Adversarial Image Generation for Chest X-rays Using Concept Vector Perturbations and Generative Models](https://mlsanity.com/paper/2502.05214/) (2025)
- [Making Document-Level Information Extraction Right for the Right Reasons](https://mlsanity.com/paper/2110.07686/) (2021)
- [Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays](https://mlsanity.com/paper/2403.19444/) (2024)
- [A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?](https://mlsanity.com/paper/2504.05227/) (2025)
- [Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges](https://mlsanity.com/paper/2509.15107/) (2025)
- [Improving Chest X-Ray Classification by RNN-based Patient Monitoring](https://mlsanity.com/paper/2210.16074/) (2022)
- [Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation](https://mlsanity.com/paper/2605.07785/) (2026)
- [A Disease Labeler for Chinese Chest X-Ray Report Generation](https://mlsanity.com/paper/2404.16852/) (2024)
- [Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset](https://mlsanity.com/paper/2505.23030/) (2025)
- [Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models](https://mlsanity.com/paper/2603.15525/) (2026)

## Abstract (arXiv)

It is often infeasible or impossible to obtain ground truth labels for medical data. To circumvent this, one may build rule-based or other expert-knowledge driven labelers to ingest data and yield silver labels absent any ground-truth training data. One popular such labeler is CheXpert, a labeler that produces diagnostic labels for chest X-ray radiology reports. CheXpert is very useful, but is relatively computationally slow, especially when integrated with end-to-end neural pipelines, is non-differentiable so can't be used in any applications that require gradients to flow through the labeler, and does not yield probabilistic outputs, which limits our ability to improve the quality of the silver labeler through techniques such as active learning. In this work, we solve all three of these problems with textttCheXpert++, a BERT-based, high-fidelity approximation to CheXpert. textttCheXpert++ achieves 99.81% parity with CheXpert, which means it can be reliably used as a drop-in replacement for CheXpert, all while being significantly faster, fully differentiable, and probabilistic in output. Error analysis of textttCheXpert++ also demonstrates that textttCheXpert++ has a tendency to actually correct errors in the CheXpert labels, with textttCheXpert++ labels being more often preferred by a clinician over CheXpert labels (when they disagree) on all but one disease task. To further demonstrate the utility of these advantages in this model, we conduct a proof-of-concept active learning study, demonstrating we can improve accuracy on an expert labeled random subset of report sentences by approximately 8% over raw, unaltered CheXpert by using one-iteration of active-learning inspired re-training. These findings suggest that simple techniques in co-learning and active learning can yield high-quality labelers under minimal, and controllable human labeling demands.