Value of Clinical Information on Radiology Reports in Oncological Imaging

Experience Matters: Impact on Technical Success and Complication Rate in Percutaneous Transhepatic Biliary Drainage

RATIONALE AND OBJECTIVES

To investigate factors influencing the success and complication rate of percutaneous transhepatic biliary drainage (PTBD).

MATERIALS AND METHODS

PTBD procedures between 2017 and 2022 were enrolled retrospectively. Success rate, complications, and technical considerations were compared using Mann-Whitney U-, X2-, and Fishers exact tests. The influence of the study center's experience (training-effect) on success and complication rates was assessed by linear regression categorized by year.

RESULTS

In 398 patients, 499 PTBD procedures (337 men; mean age 66.2 +/- 12.5 years) were carried out, with a success rate of 83.2% (415/499). PTBD in dilated bile ducts was more successful than in non-dilated bile ducts (90.0%; 316/340 vs. 68.6%; 109/159; p < 0.001), with e.g. lower radiation doses (2787.52 +/- 4012.72 cGy*cm2 vs. 4679.25 +/- 4663.55 cGy*cm2; p < 0.001), and shorter total procedure time (33.42 +/- 24.03 min vs. 41.09 +/- 27.21 min; p < 0.001). Complications occurred in 34/499 (6.8%) procedures (major complications n = 25/34) with no significant difference in bile duct width. Right-sided PTBD revealed more complications (9.0%; 30/332 vs. 2.4%; 4/166; p = 0.006) and higher radiation doses (3679.47 +/- 4571.71 cGy*cm2 vs. 2819.01 +/- 3724.92 cGy*cm2; p = 0.001) than left-sided approaches. Linear regression showed a significant continuous increase in the technical success rate of 3.0% per year (2017-2022; 72.5%; 78.5%; 82.2%; 85.0%; 89.0%; 87.5%; p = 0.005), while the overall complication rate remained unaffected (p = 0.364).

CONCLUSION

Medical centers adopting PTBD procedures can potentially increase their success rate significantly within a short period of time. PTBD is a safe procedure, with left-sided approaches showing lower complication rates and radiation exposure, underscoring their often-underestimated advantages in clinical practice.

Leveraging Large Language Models to Generate Clinical Histories for Oncologic Imaging Requisitions

Background Clinical information improves imaging interpretation, but physician-provided histories on requisitions for oncologic imaging often lack key details. Purpose To evaluate large language models (LLMs) for automatically generating clinical histories for oncologic imaging requisitions from clinical notes and compare them with original requisition histories. Materials and Methods In total, 207 patients with CT performed at a cancer center from January to November 2023 and with an electronic health record clinical note coinciding with ordering date were randomly selected. A multidisciplinary team informed selection of 10 parameters important for oncologic imaging history, including primary oncologic diagnosis, treatment history, and acute symptoms. Clinical notes were independently reviewed to establish the reference standard regarding presence of each parameter. After prompt engineering with seven patients, GPT-4 (version 0613; OpenAI) was prompted on April 9, 2024, to automatically generate structured clinical histories for the 200 remaining patients. Using the reference standard, LLM extraction performance was calculated (recall, precision, F1 score). LLM-generated and original requisition histories were compared for completeness (proportion including each parameter), and 10 radiologists performed pairwise comparison for quality, preference, and subjective likelihood of harm. Results For the 200 LLM-generated histories, GPT-4 performed well, extracting oncologic parameters from clinical notes (F1 = 0.983). Compared with original requisition histories, LLM-generated histories more frequently included parameters critical for radiologist interpretation, including primary oncologic diagnosis (99.5% vs 89% [199 and 178 of 200 histories, respectively]; P < .001), acute or worsening symptoms (15% vs 4% [29 and seven of 200]; P < .001), and relevant surgery (61% vs 12% [122 and 23 of 200]; P < .001). Radiologists preferred LLM-generated histories for imaging interpretation (89% vs 5%, 7% equal; P < .001), indicating they would enable more complete interpretation (86% vs 0%, 15% equal; P < .001) and have a lower likelihood of harm (3% vs 55%, 42% neither; P < .001). Conclusion An LLM enabled accurate automated clinical histories for oncologic imaging from clinical notes. Compared with original requisition histories, LLM-generated histories were more complete and were preferred by radiologists for imaging interpretation and perceived safety. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Tavakoli and Kim in this issue.

Diagnostic accuracy in axial spondyloarthritis: a systematic evaluation of the role of clinical information in the interpretation of sacroiliac joint imaging

OBJECTIVES

Radiography and MRI of the sacroiliac joints (SIJ) are relevant for the diagnosis and classification of patients with axial spondyloarthritis (axSpA). This study aimed to evaluate the impact of clinical information (CI) on the accuracy of imaging interpretation.

METHODS

Out of 109 patients referred because of suspicion of axSpA with complete imaging sets (radiographs and MRI of SIJ), 61 were diagnosed with axSpA (56%). Images were independently evaluated by three radiologists in four consecutive reading campaigns: radiographs and radiographs+MRI without and with CI including demographic data, SpA features, physical activity and pregnancy. Radiographs were scored according to the modified New York criteria, and MRIs for inflammatory and structural changes compatible with axSpA (yes/no). The clinical diagnosis was taken as reference standard. The compatibility of imaging findings with a diagnosis of axSpA (precision) before and after the provision of CI and radiologists' confidence with their findings (0-10) were evaluated.

RESULTS

The precision of radiographs evaluation without versus with CI increased from 70% to 78% (p=0.008), and for radiographs+MRI from 81% to 82% (p=1.0), respectively. For CR alone, the sensitivity and specificity of radiologic findings were 51% and 94% without and 60% and 100% with CI, while, for radiographs+MRI, they were 74% and 90% vs 71% and 98%, respectively. The diagnostic confidence of radiologists increased from 5.2±1.9 to 6.0±1.7 with CI for radiographs, and from 6.7±1.6 to 7.2±1.6 for radiographs+MRI, respectively.

CONCLUSION

The precision, specificity and diagnostic confidence of radiologic evaluation increased when CI was provided.