The gap before real clinical application of imaging-based machine-learning and radiomic models for chemoradiation outcome prediction in esophageal cancer: a systematic review and meta-analysis

Abstract

Background: Due to tumoral heterogeneity and the lack of robust biomarkers, the prediction of chemoradiotherapy response and prognosis in patients with esophageal cancer (EC) is challenging. The goal of this study was to assess the study quality and clinical value of machine learning and radiomic-based quantitative imaging studies for predicting the outcomes of EC patients after chemoradiotherapy.

Materials and methods: PubMed, Embase, and Cochrane were searched for eligible articles. The methodological quality and risk of bias were evaluated using the Radiomics Quality Score (RQS), Image Biomarkers Standardization Initiative (IBSI) Guideline, and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement, as well as the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. A meta-analysis of the evidence focusing on predicting chemoradiotherapy response and outcome in EC patients was implemented.

Results: Forty-six studies were eligible for qualitative synthesis. The mean RQS score was 9.07, with an adherence rate of 42.52%. The adherence rates of the TRIPOD and IBSI were 61.70 and 43.17%, respectively. Ultimately, 24 studies were included in the meta-analysis, of which 16 studies had a pooled sensitivity, specificity, and area under the curve (AUC) of 0.83 (0.76-0.89), 0.83 (0.79-0.86), and 0.84 (0.81-0.87) in neoadjuvant chemoradiotherapy datasets, as well as 0.84 (0.75-0.93), 0.89 (0.83-0.93), and 0.93 (0.90-0.95) in definitive chemoradiotherapy datasets, respectively. Moreover, radiomics could distinguish patients from the low-risk and high-risk groups with different disease-free survival (DFS) (pooled hazard ratio: 3.43, 95% CI 2.39-4.92) and overall survival (pooled hazard ratio: 2.49, 95% CI 1.91-3.25). The results of subgroup and regression analyses showed that some of the heterogeneity was explained by the combination with clinical factors, sample size, and usage of the deep learning (DL) signature.

Conclusions: Noninvasive radiomics offers promising potential for optimizing treatment decision-making in EC patients. However, it is necessary to make scientific advancements in EC radiomics regarding reproducibility, clinical usefulness analysis, and open science categories. Improved model reporting of study objectives, blind assessment, and image processing steps are required to help promote real clinical applications of radiomics in EC research.

Figure 1

Flow diagram of study inclusion. DFS, disease-free survival; HR, hazard ratio; OS, overall survival.

Figure 2

Quality assessment of the included studies. (A) Ideal percentage of Radiomics Quality Score. (B) Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis adherence rate. (C) Adherence rate of Image Biomarkers Standardization Initiative preprocessing steps. (D) Quality Assessment of Diagnostic Accuracy Studies-2 assessment result.

Figure 3

Forest plots of pooled sensitivity and specificity of imaging-based radiomics in predicting esophageal cancer concurrent chemoradiotherapy response. (A) Sensitivity in neoadjuvant chemoradiotherapy. (B) Specificity in neoadjuvant chemoradiotherapy. (C) Sensitivity in definitive chemoradiotherapy. (D) Specificity in definitive chemoradiotherapy. The numbers are pooled estimates with 95% CIs in parentheses; horizontal lines indicate 95% CIs; pooled result for all studies is presented as a black diamond. DCRT, definitive chemoradiotherapy; NCRT, neoadjuvant chemoradiotherapy.

Figure 4

Summary receiver operating characteristic (SROC) curve of the model performance for radiomics in chemoradiotherapy response prediction. (A) SROC curve of the model performance in neoadjuvant chemoradiotherapy datasets; (B) SROC curve of the model performance in definitive chemoradiotherapy datasets. SROC, summary receiver operating characteristic.

Figure 5

Forest plots of the predictive performance of radiomics in (A) disease-free survival and (B) overall survival of patients treated with concurrent chemoradiotherapy. Hazard ratio for each dataset is presented as a black dot, with the horizontal line indicating the 95% CI. The pooled result for all studies is presented as a black diamond. DFS, disease-free survival; HR, hazard ratio; OS, overall survival.