Cancer scienceJul 12, 2024

Using metabolism measures and machine learning to predict progression of esophageal squamous cell cancer

Circadian Biology Weekly Brief ↗PubMed ↗DOI ↗OA ↗

Updated Mar 29, 2026

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.

Simplified

The incomplete prediction of prognosis in esophageal squamous cell carcinoma (ESCC) patients is attributed to various therapeutic interventions and complex prognostic factors. Consequently, there is a pressing demand for enhanced predictive biomarkers that can facilitate clinical management and treatment decisions. This study recruited 491 ESCC patients who underwent surgical treatment at Huashan Hospital, Fudan University. We incorporated 14 blood metabolic indicators and identified independent prognostic indicators for overall survival through univariate and multivariate analyses. Subsequently, a formula was established based on the biochemical markers. We constructed a nomogram and machine learning models utilizing the metabolism score and clinically significant prognostic features, followed by an evaluation of their predictive accuracy and performance. We identified alkaline phosphatase, free fatty acids, homocysteine, lactate dehydrogenase, and triglycerides as independent prognostic indicators for ESCC. Subsequently, based on these five indicators, we established a metabolism score that serves as an independent prognostic factor in ESCC patients. By utilizing this metabolism score in conjunction with clinical features, a nomogram can precisely predict the prognosis of ESCC patients, achieving an area under the curve (AUC) of 0.89. The random forest (RF) model showed superior predictive ability (AUC = 0.90, accuracy = 86%, Matthews correlation coefficient = 0.55). Finally, we used an RF model with optimal performance to establish an online predictive tool. The metabolism score developed in this study serves as an independent prognostic indicator for ESCC patients.

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.

Full Text

We can’t show the full text here under this license.

View Full Text ↗

Funding

Competing interests

The authors declare no conflict of interest.

PubMed

Using metabolism measures and machine learning to predict progression of esophageal squamous cell cancer

Abstract

Key numbers

Full Text

Funding

Competing interests

You found one interesting study. We’ll send the next 7.

What Lands in Your Inbox Each Week:

Recent issues from the circadian biology brief

Abstract

Key numbers

Full Text

Funding

Competing interests

Related papers

You found one interesting study. We’ll send the next 7.

What Lands in Your Inbox Each Week:

Recent issues from the circadian biology brief