Large language models for structured reporting in radiology: past, present, and future

Felix Busch, Lena Hoffmann, Daniel Pinto dos Santos, Marcus R. Makowski, Luca Saba, Philipp Prucker, Martin Hadamitzky, Nassir Navab et al.

European Radiology 2024 article cited by 129

Source Open-access PDF More in Medicine & Health

importance 5/10 partially solved Artificial Intelligence in Healthcare and Education radiology reporting stage: research mixed

Problem

Structured reporting in radiology would standardize and improve report quality, but widespread adoption has remained limited.

Why it matters

Standardized radiology reports reduce errors, improve comprehensiveness, and increase guideline adherence in patient care.

What the AI did

A narrative review surveying LLMs as a way to automate and facilitate structured reporting, covering ten studies of GPT-3.5/GPT-4 and other models.

Results

Ten studies identified; all reported promising results; six of ten demonstrated multilingual feasibility

Impact

Evidence that LLM-based structured reporting is feasible, but the literature is still limited and adoption unsolved.

Record

Venue	European Radiology
Published	2024
Work type	article
Authors	Felix Busch, Lena Hoffmann, Daniel Pinto dos Santos, Marcus R. Makowski, Luca Saba, Philipp Prucker, Martin Hadamitzky, Nassir Navab et al.
Citations	129 (OpenAlex, at import time)
References	72
Model or method	GPT-3.5, GPT-4, Perplexity, Bing Chat, IT5
Organization	not stated in source
Primary source	https://doi.org/10.1007/s00330-024-11107-6
Open access	hybrid
Keywords	large language models, structured reporting, radiology, GPT-4, clinical documentation

Importance rating

5 / 10

real but narrower advance

Report standardization affects radiology practice broadly, but abstract gives no scale; evidence is a sparse ten-study review with adoption still unsolved.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Medicine & Health

#	Paper	Year	Citations	Importance
1	Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction Yeong Chan Lee, Jiho Cha, Injeong Shim, Woong‐Yang Park, Se Woong Kang...	2023	107	10
2	Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization Tawsifur Rahman, Amith Abdullah Khandakar, Muhammad Abdul Kadir, Khand...	2020	651	10
3	A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach Nitish Biswas, Khandaker Mohammad Mohi Uddin, Sarreha Tasmin Rikta, Sa...	2022	116	10
4	Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning Hamada R. H. Al-Absi, Mohammad Tariqul Islam, Mahmoud Ahmed Refaee, Mu...	2022	89	10
5	Proteomics and Machine Learning Approaches Reveal a Set of Prognostic Markers for COVID-19 Severity With Drug Repurposing Potential Kruthi Suvarna, Deeptarup Biswas, Medha Gayathri J. Pai, Arup Acharjee...	2021	76	10