Skip to main content

Advertisement

Advertisement

Advertisement

Advertisement

ADVERTISEMENT

Abstracts P-143


Using artificial intelligence CT-based methods to evaluate body composition for predicting survival outcomes in patients with colorectal cancer receiving PD-1 treatment

Liu X. Yang Y.

West China Hospital, Sichuan University, Chengdu, China

Background

As for PFS, SMI [hazard ratio (HR) (95% CI): 1.041 ((1.003-1.081))], SMD [HR (95% CI): 1.113 (1.035-1.197)], and pre-therapeutic alkaline phosphatase (ALP) [HR (95% CI): 1.003 (1.001-1.005)], and ΔSMD [HR (95% CI): 1.113 (1.035-1.197)] were considered as prognostic predictors with statistical significance (p<0.05). Our results showed patients with lower SMD had prognostic value for prediction of poorer OS compared with patients with higher SMD with HR of 1.113 (95%CI: 1.035-1.197, p=0.004).

Methods

The body composition of 116 patients with colorectal cancer at the third lumbar vertebra level was analyzed using an AI-based software (Visage Imaging). All patients received PD-1 treatment with available abdominal CTs before treatment. The body composition-associated indicators were evaluated, including skeletal muscle index (SMI), skeletal muscle density (SMD), subcutaneous (SATI), and visceral adipose tissue index (VATI). Demographic characteristics and the indicators from blood and biochemical tests were obtained before treatment. The prognostic values of body composition-associated indicators were evaluated with survival outcomes, including progression-free survival (PFS) and overall survival (OS) in univariate and multivariate analysis.

Results

As for PFS, SMI [hazard ratio (HR) (95% CI): 1.041 ((1.003-1.081))], SMD [HR (95% CI): 1.113 (1.035-1.197)], and pre-therapeutic alkaline phosphatase (ALP) [HR (95% CI): 1.003 (1.001-1.005)], and ΔSMD [HR (95% CI): 1.113 (1.035-1.197)] were considered as prognostic predictors with statistical significance (p<0.05). Our results showed patients with lower SMD had prognostic value for prediction of poorer OS compared with patients with higher SMD with HR of 1.113 (95%CI: 1.035-1.197, p=0.004).

Conclusions

As for PFS, SMI [hazard ratio (HR) (95% CI): 1.041 ((1.003-1.081))], SMD [HR (95% CI): 1.113 (1.035-1.197)], and pre-therapeutic alkaline phosphatase (ALP) [HR (95% CI): 1.003 (1.001-1.005)], and ΔSMD [HR (95% CI): 1.113 (1.035-1.197)] were considered as prognostic predictors with statistical significance (p<0.05). Our results showed patients with lower SMD had prognostic value for prediction of poorer OS compared with patients with higher SMD with HR of 1.113 (95%CI: 1.035-1.197, p=0.004).

Legal entity responsible for the study

The authors.

Funding

Has not received any funding.

Disclosures

All authors have declared no conflicts of interest.

Publisher
Elsevier Ltd
Source Journal
Annals of Oncology
E ISSN 1569-8041 ISSN 0923-7534

Advertisement

Advertisement

Advertisement

Advertisement