Fine-Tuned LLMs Boost Error Detection in Radiology Reports

A type of artificial intelligence (AI) called fine-tuned large language models (LLMs) greatly enhances error detection in radiology reports, according to a new study published in Radiology, a journal of the Radiological Society of North America (RSNA). Researchers said the findings point to an important role for this technology in medical proofreading.

Radiology reports are crucial for optimal patient care. Their accuracy can be compromised by factors like errors in speech recognition software, variability in perceptual and interpretive processes and cognitive biases. These errors can lead to incorrect diagnoses or delayed treatments, making the need for accurate reports urgent.

LLMs like ChatGPT are advanced generative AI models that are trained on vast amounts of text to generate human language. While they offer great potential in proofreading, their application in the medical field, particularly in detecting errors within radiology reports, remains underexplored.

To bridge this gap in knowledge, researchers evaluated fine-tuned LLMs for detecting errors in radiology reports during medical proofreading. A fine-tuned LLM is a pre-trained language model that is further trained on domain-specific data.

"Initially, LLMs are trained on large-scale public data to learn general language patterns and knowledge," said study senior author Yifan Peng, Ph.D., from the Department of Population Health Sciences at Weill Cornell Medicine in New York City. "Fine-tuning occurs as the next step, where the model undergoes additional training using smaller, targeted datasets relevant to particular tasks."

To test the model, Dr. Peng and colleagues built a dataset with two parts. The first consisted of 1,656 synthetic reports, including 828 error-free reports and 828 reports with errors. The second part comprised 614 reports, including 307 error-free reports from MIMIC-CXR, a large, publicly available database of chest X-rays, and 307 synthetic reports with errors.

The researchers used the synthetic reports to boost the amount of training data and fulfill the data-hungry needs of LLM fine-tuning.

"Synthetic reports can also increase the coverage and diversity, balance out the cases and reduce the annotation costs," said the study's first author, Cong Sun, Ph.D., from Dr. Peng's lab. "In radiology, or more broadly, the clinical domain, synthetic reports allow safe data-sharing without compromising patient privacy."

The researchers found that the fine-tuned model outperformed both GPT-4 and BiomedBERT, a natural language processing tool for biomedical research.

"The LLM that was fine-tuned on both MIMIC-CXR and synthetic reports demonstrated strong performance in the error detection tasks," Dr. Sun said. "It meets our expectations and highlights the potential for developing lightweight, fine-tuned LLM specifically for medical proofreading applications."

The study provided evidence that LLMs can assist in detecting various types of errors, including transcription errors and left/right errors, which refer to misidentification or misinterpretation of directions or sides in text or images.

The use of synthetic data in AI model building has raised concerns of bias in the data. Dr. Peng and colleagues took steps to minimize this by using diverse and representative samples of real-world data to generate the synthetic data. However, they acknowledged that synthetic errors may not fully capture the complexity of real-world errors in radiology reports. Future work could include a systematic evaluation of how bias introduced by synthetic errors affects model performance.

The researchers hope to study fine-tuning's ability to reduce radiologists' cognitive load and enhance patient care and find out if fine-tuning would degrade the model's ability to generate reasoning explanations.

"We are excited to keep exploring innovative strategies to enhance the reasoning capabilities of fine-tuned LLMs in medical proofreading tasks," Dr. Peng said. "Our goal is to develop transparent and understandable models that radiologists can confidently trust and fully embrace."

Sun C, Teichman K, Zhou Y, Critelli B, Nauheim D, Keir G, Wang X, Zhong J, Flanders AE, Shih G, Peng Y.
Generative Large Language Models Trained for Detecting Errors in Radiology Reports.
Radiology. 2025 May;315(2):e242575. doi: 10.1148/radiol.242575

Most Popular Now

Open Medical Works with Moray's Dig…

Open Medical is working with the Digital Health & Care Innovation Centre’s Rural Centre of Excellence on a referral management plan, as part of a research and development scheme to...

Generative AI on Track to Shape the Futu…

Using advanced artificial intelligence (AI), researchers have developed a novel method to make drug development faster and more efficient. In a new paper, Xia Ning, lead author of the study and...

Reorganisation, Consolidation, and Cuts:…

NHS England has been downsized and abolished. Integrated care boards have been told to change function, consolidate, and deliver savings. Trusts are planning big cuts. The Highland Marketing advisory board...

AI-Human Task-Sharing could Cut Mammogra…

The most effective way to harness the power of artificial intelligence (AI) when screening for breast cancer may be through collaboration with human radiologists - not by wholesale replacing them...

AI Tool Uses Face Photos to Estimate Bio…

Eyes may be the window to the soul, but a person's biological age could be reflected in their facial characteristics. Investigators from Mass General Brigham developed a deep learning algorithm...

Philips Future Health Index 2025 Report …

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today unveiled its 2025 Future Health Index U.S. report, "Building trust in healthcare AI," spotlighting the state of...

AI Model Improves Delirium Prediction, L…

An artificial intelligence (AI) model improved outcomes in hospitalized patients by quadrupling the rate of detection and treatment of delirium. The model identifies patients at high risk for delirium and...

AI-Powered Precision: Unlocking the Futu…

A team of researchers from the Department of Diagnostic and Therapeutic Ultrasonography at the Tianjin Medical University Cancer Institute & Hospital, have published a review in Cancer Biology & Medicine...

Call for Papers: AI Applications in Biom…

JMIR Biomedical Engineering is inviting submissions for a new section titled "AI Applications in Biomedical Engineering." This themed section explores the integration of biomedical engineering and artificial intelligence (AI), focusing...

DeepSeek-R1 Offers Promising Potential t…

A joint research team from The Hong Kong University of Science and Technology and The Hong Kong University of Science and Technology (Guangzhou) has published a perspective article in MedComm...

Deep Learning can Predict Lung Cancer Ri…

A deep learning model was able to predict future lung cancer risk from a single low-dose chest CT scan, according to new research published at the ATS 2025 International Conference...

A Machine Learning Tool for Diagnosing, …

Scientists aiming to advance cancer diagnostics have developed a machine learning tool that is able to identify metabolism-related molecular profile differences between patients with colorectal cancer and healthy people. The analysis...