Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2103
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-21T10:42:47.179144Z
status: published
lens: g_space
sector: health
headline: Deep Learning-Based 3D CT Body Composition Is Associated With Mortality in Patients Undergoing Transcatheter Aortic Valve Replacement
dek: BACKGROUND: Recent advances in artificial intelligence enable fully automated 3-dimensional computed tomography (CT)-based body composition quantification. We investigated whether automated CT-derived thoraco-abdominopelvic body composition measures are associated with mortality after transcatheter aortic valve replacement. METHODS: In this retrospective multicenter study, consecutive patients undergoing transcatheter aortic valve replacement with preprocedural CT imaging were included between 2014 and 2023. A d…
gain_title: Adding AI-derived 3D CT body composition measures to demographic and cardiometabolic factors raised mortality discrimination (Harrell C from 0.66 to 0.71) in TAVR patients.
problem_title: (none)
trace_subject: (none)
gain_reading: Adding AI-derived 3D CT body composition measures to demographic and cardiometabolic factors raised mortality discrimination (Harrell C from 0.66 to 0.71) in TAVR patients.
gain_evidence: Addition of body composition measures provided incremental discriminatory value beyond demographics and cardiometabolic risk factors (Harrell C, 0.66 versus 0.71; P <0.001)
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers applied a deep learning pipeline that automatically segmented preprocedural noncontrast CT scans in 915 patients who underwent transcatheter aortic valve replacement between 2014 and 2023. It measured the volume and attenuation of fat and muscle compartments, then tested these against death during follow-up, with 160 deaths observed.

The findings suggest that scans already acquired before the procedure could yield extra prognostic information without added imaging. The work is retrospective, so it shows association and improved discrimination rather than proof that acting on these measures changes patient outcomes.
limitation: 
tag: Evidence-backed gain
key_points: The cohort had 915 patients with a median age of 84 years, and 58% were men. | 160 patients (17.5%) died over a median follow-up of 22 months. | Lower subcutaneous adipose tissue volume and higher adipose tissue attenuation were linked to higher mortality. | Higher skeletal muscle volume and attenuation were linked to better survival. | The Harrell C statistic rose from 0.66 to 0.71 when body composition was added to the model.
rundown: The study was retrospective and multicenter and included consecutive TAVR patients who had preprocedural CT imaging between 2014 and 2023. The AI pipeline segmented thoraco-abdominopelvic noncontrast scans in three dimensions.

It quantified subcutaneous, visceral, and muscular adipose tissue and lean skeletal muscle, with volumes indexed to body surface area. Associations with mortality were assessed with Cox models and restricted cubic splines.

Models were adjusted for age, sex, body mass index, hypertension, diabetes, and chronic renal failure. Body composition added independent prognostic information beyond these factors.
sources:
- peer_reviewed | Circulation: Cardiovascular Imaging | https://doi.org/10.1161/circimaging.126.020106 | 2026-10-20
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

6466d94ace79600c269c98b69c555b19cfb2af3eea2b3b802ed98f8e8193bc30

previous

0000000000000000000000000000000000000000000000000000000000000000