Impact of Documentation Aids on the Inclusion of Salient Left-Ventricular Late Gadolinium Enhancement Characteristics in Cardiac Magnetic Resonance Imaging Impressions
Open Access
- 29 October 2026
- journal article
- research article
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-12
Abstract
Late gadolinium enhancement (LGE) on cardiac magnetic resonance (CMR) imaging is a key diagnostic and prognostic biomarker in ischemic cardiomyopathy (ICM) and nonischemic cardiomyopathy (NICM). However, the completeness of LGE reporting in routine CMR impressions remains incompletely characterized. We aimed to evaluate the impact of large language model (LLM)-assisted reporting on the consistency of LGE pattern, distribution, and severity documentation in CMR impressions for ICM and NICM. We analyzed 828 unstructured (1990–2023) and 400 structured (2024–2025) CMR reports to identify documentation of LGE pattern, distribution, and severity. A Llama 3 language model fine-tuned on 27,000 structured CMR reports was used to generate 9650 CMR impressions; LGE attributes were extracted using an LLM judge. LLM reporting behavior was further assessed using quantized low-rank adaptation adapters trained on structured and unstructured impressions. Structured reporting captured LGE pattern more frequently than unstructured reporting overall (85.5% vs. 61.0%, p = 9.60 × 10 −7 ) and for ICM (90.0% vs. 69.4%, p = 0.005). LLM-generated impressions demonstrated more frequent reporting of LGE distribution (75.3%) and severity (70.9%) versus structured and unstructured reports ( p < 0.001). Fine-tuning with an adapter trained on unstructured impressions significantly improved reporting of all three LGE attributes. Structured reporting improved LGE pattern documentation, but gaps in LGE distribution and severity documentation persisted across human report formats. LLM-generated impressions achieved broader attribute coverage for LGE distribution and severity. Fine-tuning on unstructured data improved model performance, suggesting that passive augmentation with data capturing the documentation styles of multiple providers may help to address reporting gaps.Keywords
Funding Information
- National Heart, Lung, and Blood Institute (1R01HL180504-01)
This publication has 35 references indexed in Scilit:
- Discrepancies between preliminary and final radiology reports: Impact of training level, imaging modality, and clinical risk factorsEuropean Journal of Radiology, 2026
- Late-gadolinium enhancement predicts appropriate device therapies in nonischemic recipients of primary prevention implantable cardioverter-defibrillatorsHeart Rhythm, 2025
- Risk Stratification in Nonischemic Dilated Cardiomyopathy Using CMR ImagingJAMA, 2024
- Late gadolinium enhancement on cardiac MRI: A systematic review and meta-analysis of prognosis across cardiomyopathiesInternational Journal of Cardiology, 2024
- Investigating the impact of cognitive biases in radiologists’ image interpretation: A scoping reviewEuropean Journal of Radiology, 2023
- What Influences the Way Radiologists Express Themselves in Their Reports? A Quantitative Assessment Using Natural Language ProcessingJournal of Digital Imaging, 2022
- Prognostic Value of Late Gadolinium Enhancement in Predicting Life‐Threatening Arrhythmias in Heart Failure Patients With Implantable Cardioverter‐Defibrillators: A Systematic Review and Meta‐AnalysisJournal of Magnetic Resonance Imaging, 2019
- Role of Cardiac Magnetic Resonance Imaging in Valvular Heart Disease: Diagnosis, Assessment, and ManagementCurrent Cardiology Reports, 2018
- Structured report compliance: effect on audio dictation time, report length, and total radiologist study timeEmergency Radiology, 2016
- The radiology report — Are we getting the message across?Clinical Radiology, 2011