ArticleFrontiers in oncology2026
Predicting survival of patients treated with antibody-drug conjugates in early-phase clinical trials using AI-quantified 3D body composition on CT scans.
Article in Frontiers in oncology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
27 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: Body composition has a significant impact on the prognosis of cancer patients. However, little is known about its impact on the efficacy and safety of antibody-drug conjugates (ADCs), despite the need for accurate patient profiling to ensure reliable safety data and early signals of activity. Methods: All patients treated with ADCs in early-phase clinical trials between March 2015 and March 2023 in our institution were retrospectively included in the analysis. Pre-treatment injected CT scans were acquired for all patients. A deep learning software, Anthropometer3DNet, automatically quantified anthropometric parameters in three dimensions (3D) on the acquired CT scans: skeletal muscle mass (SMM), total adipose tissue (TAT), subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and lean body mass (LBM). The effect of these anthropometric parameters on progression-free survival (PFS), overall survival (OS), and time in protocol (TIP) was analyzed. Results: A total of 136 patients were included. The median age, Eastern Cooperative Oncology Group Performance Status (ECOG PS), albumin, and number of previous lines of treatment were respectively 60.8 years (30 to 85), 1 (0-2), 42 g/L [interquartile range (IQR): 39-44], and 3 (IQR: 0-2). The median PFS and OS were 2.6 and 7.9 months, respectively; 90 (66%) patients had experienced toxicity (of which 46 were grade 3-5). Univariate analyses showed that higher SAT [hazard ratio (HR) = 0.67, p = 0.03] and TAT (HR = 0.60, p = 0.01) were significantly associated with longer PFS [median PFS (mPFS) = 2.76 vs. 2.3 and 2.76 vs. 1.9, respectively]. Higher SAT (HR = 0.66, p = 0.04) and higher VAT (HR = 0.65, p = 0.04) were significantly associated with longer OS [median OS (mOS) = 9.34 vs. 7.43 months and 9.27 vs. 6.08 months, respectively]. Higher TAT was associated with longer TIP in both univariate and multivariate analyses (HR = 0.56, p = 0.006). A Royal Marsden Hospital (RMH) prognostic score of 2 or more was associated with PFS, OS, and TIP in both univariate and multivariate analyses (HR = 1.78, 1.89, and 1.74, respectively). All anthropometric parameters were significantly associated with all-grade toxicity in the univariate analysis but not in the multivariate analysis. Conclusions: Automatic extraction of body composition parameters using artificial intelligence (AI) may help in anticipating the benefits of ADCs in patients included in early-phase clinical trials. Combining anthropomorphic data with clinical and biological data may lead to more refined patient selection.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.