Combination of radiomic and clinical characteristics to predict mortality in patients with colorectal perforation DOI Creative Commons

J R Lin,

Zheng Li, Wei Jiang

et al.

International Journal of Colorectal Disease, Journal Year: 2025, Volume and Issue: 40(1)

Published: March 31, 2025

We aim to construct and verify a model combining radiomic clinical data predict early mortality in patients with colorectal perforation two-center study. Data from 147 at Xiaogan Central Hospital (2014-2024) 52 Southern of Medical University (2021-2023) were collected for training validation. Univariate multivariate analyses performed identify risk factors associated mortality. Radiomic characteristics CT scans extracted via least absolute shrinkage selection operator (LASSO) regression an imaging score. A nomogram was developed by integrating the findings analysis. Predictive performance evaluated area under receiver operating characteristic curve (AUC), utility assessed decision analysis (DCA). highlighted age, ASA classification, shock index, rad-score, white blood cell (WBC) count, neutrophil (N) lymphocyte (L) counts, sodium (Na+), creatinine (Cr), procalcitonin (PCT) as significant prognostic indicators (p < 0.05). Multivariate confirmed PCT, rad-score independent factors. The combined (RCCCN) includes four variables: patient's PCT level, rad-score. RCCCN demonstrated excellent predictive validation cohort (AUC: 0.92, 95% CI: 0.84-0.99) good calibration. features effectively predicts perforation, providing valuable tool decision-making patient management.

Language: Английский

Combination of radiomic and clinical characteristics to predict mortality in patients with colorectal perforation DOI Creative Commons

J R Lin,

Zheng Li, Wei Jiang

et al.

International Journal of Colorectal Disease, Journal Year: 2025, Volume and Issue: 40(1)

Published: March 31, 2025

We aim to construct and verify a model combining radiomic clinical data predict early mortality in patients with colorectal perforation two-center study. Data from 147 at Xiaogan Central Hospital (2014-2024) 52 Southern of Medical University (2021-2023) were collected for training validation. Univariate multivariate analyses performed identify risk factors associated mortality. Radiomic characteristics CT scans extracted via least absolute shrinkage selection operator (LASSO) regression an imaging score. A nomogram was developed by integrating the findings analysis. Predictive performance evaluated area under receiver operating characteristic curve (AUC), utility assessed decision analysis (DCA). highlighted age, ASA classification, shock index, rad-score, white blood cell (WBC) count, neutrophil (N) lymphocyte (L) counts, sodium (Na+), creatinine (Cr), procalcitonin (PCT) as significant prognostic indicators (p < 0.05). Multivariate confirmed PCT, rad-score independent factors. The combined (RCCCN) includes four variables: patient's PCT level, rad-score. RCCCN demonstrated excellent predictive validation cohort (AUC: 0.92, 95% CI: 0.84-0.99) good calibration. features effectively predicts perforation, providing valuable tool decision-making patient management.

Language: Английский

Citations

0