Evaluating growth patterns and rupture risk to determine the repair threshold for saccular abdominal aortic aneurysms.

Abstract

Saccular abdominal aortic aneurysms (sAAA) lack a specific ICD code, and data on clinical outcomes and size criteria for repair remains sparse. We performed a large language model (LLM) assisted term-search to identify all consecutive patients with saccular abdominal aortic aneurysm (sAAA) at a large multi system hospital between April 1999 to August 2025. Patients with sAAA (Group I) were compared with patients with fusiform AAA (fAAA; Group II) using de-identified LLM data in the entire cohort. Clinical data including demographics, mode of detection, aneurysm size, and outcomes were retrospectively reviewed from a single center. The primary outcome was rupture risk and aneurysm growth rate. The LLM accessed 1.3billion clinical notes in 8million patients over the study period, and identified 298 patients (233male, mean age 75 + 8 year) with sAAA and 42,971 with fAAA (Table 1A). The mean fAAA diameter was 4 + 1cm; No sAAA ruptures were observed at presentation or during long term follow up, regardless of aneurysm size. Clinical data validation was performed in 50 sAAA patients (33 males; mean age, 81 ± 9 years, median initial maximum diameter 4.1 cm) [range 3-6.2cm]. Majority were detected incidentally (Table 1B). Thirty-two patients (64%) did not undergo repair. In this group, the initial mean sAAA diameter was 3.6 ± 1.0 cm. At a mean imaging follow up of 57 months (Average 3.5 scan/patient), the mean sAAA diameter increased to 4 ± 1.3cm. The rate of aneurysm growth increased with increasing sAAA size (p=0.03).Eighteen patients underwent repair (mean sAAA diameter 5.4 ± 1.0 cm). Repair was performed as sAAA were symptomatic in 3 patients, meeting traditional size criteria (5cm in females, 5.5cm in men) at the initial scan in 2 patients or on surveillance (mean 32 months) in 12 patients. Repair was based on morphology alone in 1 asymptomatic patient. Procedures included open repair in 4 and endovascular repair in 14; operative mortality was 2%. At a clinical follow-up of 80 months (mean, median 64 months) there was no additional aneurysm related mortality. Rupture of AAA due to saccular morphology seems rare. Most sAAAs present incidentally and demonstrate slow growth rates when less than 5 cm in diameter. Intervention is safe and effective for saccular abdominal aortic aneurysms that meet the traditional criteria for repair for AAA. LLMs demonstrate potential utility in identification of rare vascular pathology which do not have defined ICD codes.