We can’t show the full text here under this license. Use the link below to read it at the source.
Metabolism score and machine learning models for the prediction of esophageal squamous cell carcinoma progression
Using metabolism measures and machine learning to predict progression of esophageal squamous cell cancer
AI simplified
Abstract
A based on five blood indicators achieved an area under the curve (AUC) of 0.89 for predicting outcomes in esophageal squamous cell carcinoma patients.
- Five independent prognostic indicators for overall survival in esophageal squamous cell carcinoma were identified: alkaline phosphatase, free fatty acids, homocysteine, lactate dehydrogenase, and triglycerides.
- A metabolism score was developed from these five indicators, serving as an independent prognostic factor.
- The nomogram created using the metabolism score and clinical features provided a robust method for predicting patient prognosis.
- The random forest model demonstrated superior predictive ability with an AUC of 0.90 and accuracy of 86%.
- An online predictive tool was established utilizing the random forest model for practical application in clinical settings.
AI simplified
Key numbers
0.90
AUC of Random Forest Model
Performance metric for the random forest model in predicting overall survival.
491
Patient Cohort Size
Total number of ESCC patients included in the study.
0 to 11.62
Range
Distribution of metabolism scores calculated from blood metabolic indicators.