Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0948
version: 2
kind: revised
reason: Direction audit: filed as a problem but describes a gain.
timestamp: 2026-10-26T06:38:51.415270Z
status: published
lens: g_space
sector: health
headline: A machine learning-derived sarcopenia index is associated with survival and nonrelapse mortality in DLBCL
dek: Abstract Body composition analysis (BCA) provides an objective assessment of metabolic states, but its prognostic value in diffuse large B-cell lymphoma (DLBCL) remains unclear. We applied machine learning-supported BCA to computed tomography imaging from patients with newly diagnosed DLBCL enrolled in the prospective phase 3 PETAL trial to quantify radiologic sarcopenia. We assessed BCA results in relation to survival after first-line immunochemotherapy, treatment-related hematologic toxicities, and molecular d…
gain_title: Machine learning-supported body composition analysis applied to CT imaging quantifies radiologic sarcopenia and enables risk stratification for survival after first-line immunochemotherapy in newly diagnosed DLBCL.
problem_title: (none)
trace_subject: (none)
gain_reading: Machine learning-supported body composition analysis applied to CT imaging quantifies radiologic sarcopenia and enables risk stratification for survival after first-line immunochemotherapy in newly diagnosed DLBCL.
gain_evidence: We applied machine learning-supported BCA to computed tomography imaging from patients with newly diagnosed DLBCL enrolled in the prospective phase 3 PETAL trial to quantify radiologic sarcopenia. | supporting the evaluation of BCA for risk stratification in personalized lymphoma therapy.
problem_reading: (none)
problem_evidence: (none)
quick_read: In patients with newly diagnosed diffuse large B-cell lymphoma from the PETAL trial, investigators used machine learning-supported body composition analysis of CT imaging to measure skeletal muscle mass. Those in the lowest tertile had inferior survival after adjustment for established risk factors, with cause-specific analyses pointing to nonrelapse mortality rather than lymphoma-specific death.

The findings matter because they position an automated imaging biomarker as a host-vulnerability indicator that predicts both nonrelapse mortality and hematologic toxicity, and identifies early muscle loss during therapy as a separate risk factor. It remains uncertain how much variability is driven by factors beyond age and disease burden, and whether BCA-guided interventions can improve outcomes.
limitation: 
tag: Evidence-backed gain
key_points: Study used machine learning-supported BCA on CT imaging from newly diagnosed DLBCL patients enrolled in prospective phase 3 PETAL trial. | Patients in lowest tertile of normalized skeletal muscle mass had inferior survival after adjustment for established risk factors. | Cause-specific analysis showed sarcopenia predicted nonrelapse mortality, not lymphoma-specific death, and was only independent risk factor for higher-grade hematotoxicity. | Longitudinal BCA showed early muscle loss during therapy also linked to inferior survival, distinct from baseline sarcopenia.
rundown: Researchers applied machine learning-supported body composition analysis to CT scans from the prospective PETAL phase 3 trial of newly diagnosed DLBCL to quantify normalized skeletal muscle mass and define radiologic sarcopenia.

Baseline sarcopenia and early treatment-emergent muscle loss were found to be uncorrelated and independent of molecular clusters, with only a small fraction of muscle mass variability explained by age and lymphoma burden, and no recurrently mutated gene linked to lower muscle mass.
sources:
- peer_reviewed | Blood Advances | https://doi.org/10.1182/bloodadvances.2026020504 | 2026-09-01
prev: fe62a1111fccc0489fdc3290973a32665dcfaa27692b78671a2827d44e3ce9f9

sha256

33fe9178c0745af4450dacea822f2df58fe443f6c8b251a04bd1787da93a0ec1

previous

fe62a1111fccc0489fdc3290973a32665dcfaa27692b78671a2827d44e3ce9f9