Everything has to be in its place. Not only on the operating table or in the office, but also with data. Structured reports, for example, are helpful for doctors as well as for further use in research in databases. Later, such structured data can also be used to train other AI models for image-based diagnosis. In practice, however, reports are usually written in free text form, which complicates further use. This is exactly where the application of AI, more precisely LLMs, comes in.
LLMs can be divided into two categories: The closed-weights models are the commercial, well-known AI variants that are also used in chatbots such as Chat-GPT. Open-weights models, such as Meta's Llama models, are an option that can be run on internal clinic servers and can even be trained further. When applying these models, all data remain stored locally, which makes the use of open LLMs advantageous in terms of data security. "The problem with commercial, closed models is that in order to use them, you have to transfer the data to external servers, which are often located outside the EU. This is not recommended for patient data," emphasizes Prof. Julian Luetkens, comm. Director of the Clinic for Diagnostic and Interventional Radiology at the UKB.
"But are all LLMs equally suitable for understanding and structuring the medical content of radiological reports? To find out which LLM is suitable for a clinic, we tested various open and closed models," explains Dr. Sebastian Nowak, first and corresponding author of the study and postdoc at the University of Bonn's Clinic for Diagnostic and Interventional Radiology at the UKB. "We were also interested in whether open LLMs can be developed effectively on site in the clinic with just a few already structured reports."
Therefore, the research team carried out an analysis of 17 open and four closed LLMs. All of them analyzed thousands of radiology reports in free text form. Public radiology reports in English, without data protection, were used for the analysis as well as data-protected reports from the UKB in German.
The results show that in the case of the reports without data protection, the closed models have no advantage over some of the open LLMs. When applied directly without training, larger, open LLMs were better than smaller, open LLMs. The use of already structured reports as training data for open LLMs led to an effective improvement in the quality of information processing, even with just a few manually prepared reports. The training also reduced the difference in accuracy between large and small LLMs.
"In a training session with over 3,500 structured reports, there was no longer any relevant difference between the largest open LLM and a language model that was 1,200 times smaller," says Nowak. "Overall, it can be concluded that open LLMs can keep up with closed ones and have the advantage of being able to be developed locally in a data protection-safe manner."
This discovery has the potential to unlock clinical databases for comprehensive epidemiological studies and research into diagnostic AI. "Ultimately, this will benefit the patient, all while strictly observing data protection," explains Nowak. "We want to enable other clinics to use our research directly and have therefore published the code and methods for LLM use and training under an open license.
For further information, please visit:
https://github.com/ukb-rad-cfqiai/LLM_based_report_info_extraction/
Nowak S, Wulff B, Layer YC, Theis M, Isaak A, Salam B, Block W, Kuetting D, Pieper CC, Luetkens JA, Attenberger U, Sprinkart AM.
Privacy-ensuring Open-weights Large Language Models Are Competitive with Closed-weights GPT-4o in Extracting Chest Radiography Findings from Free-Text Reports.
Radiology. 2025 Jan;314(1):e240895. doi: 10.1148/radiol.240895