Predicting Distant Metastases in Gastric Cancer Using a CT Radiomics-Clinical Model
Author Information
Author(s): Xue Hui-Bin, Liang Mei-Li, Xu Huang-Zhen, Wang Chen-Yu, Xu Tian-Wen, Zhao Ai-Yue
Primary Institution: The Second Affiliated Hospital of Fujian Medical University
Hypothesis
Radiomics could be a valuable asset in forecasting the risk of distant metastases in gastric cancer.
Conclusion
The nomogram of the joint model, integrating radiomic features and clinically independent predictors, exhibits robust predictive capability for early identification of high-risk patients with a propensity for distant metastases of gastric cancer.
Supporting Evidence
- The predictive performance of the joint model 1 was superior to that of the clinical model and radiomics model.
- The joint model 1 exhibited a higher clinical net benefit than other models.
- Age, histological grade, and N stage were identified as independent predictors of distant metastases.
Takeaway
This study created a tool to help doctors predict if gastric cancer will spread to other parts of the body using CT scans and patient information.
Methodology
The study used retrospective data from 301 gastric cancer patients, applying logistic regression and machine learning algorithms to develop predictive models based on clinical and radiomic features.
Limitations
The study is retrospective and requires external validation; it also only used venous phase CT images for feature extraction.
Participant Demographics
Patients diagnosed with gastric cancer at the Second Affiliated Hospital of Fujian Medical University from January 2018 to December 2022.
Statistical Information
P-Value
p<0.001
Confidence Interval
95% CI 0.811-0.949
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website