Machine learning in predicting pathological complete response to neoadjuvant chemoradiotherapy in rectal cancer using MRI: A systematic review and meta-analysis.

Abstract

To evaluate the performance of machine learning models in predicting treatment response to neoadjuvant chemoradiotherapy (nCRT) in rectal cancer using computed tomography (CT) and magnetic resonance imaging (MRI). We searched PubMed, Embase, Cochrane Library, and Web of Science for studies published before January 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) was used to assess the methodological quality of the included studies, random-effects models were used to calculate sensitivity and specificity, I2 values were used for heterogeneity measurements, and subgroup analyses were carried out to detect potential sources of heterogeneity. A total of 1690 patients from 24 studies were included. The meta-analysis calculated a pooled area under the curve (AUC) of 0.92 (95%CI-0.89-0.94), pooled sensitivity of 0.81 (95%CI-0.73-0.88), and pooled specificity of 0.88 (95%CI-0.82-0.92). We investigated 4 studies that mainly contributed to heterogeneity. After performing meta-analysis again excluding these 4 studies, the heterogeneity was significantly reduced. In subgroup analysis, the pooled AUC of the deep learning model was 0.95 and was 0.88 for the traditional statistical model; the pooled AUC of studies that used diffusion-weighted imaging (DWI) was 0.90, and was 0.92 in studies that did not use DWI; the pooled AUC of studies conducted in China was 0.94, and was 0.83 in studies conducted in other countries. Machine learning has promising potential in predicting tumor response to nCRT in patients with locally advanced rectal cancer. Together with clinical information, machine-learning based models may bring us closer toward precision medicine. Compared to traditional machine learning models, deep learning-based studies are able to obtain higher AUC, although they are less predominant and more heterogeneous. Together with clinical information, machine-learning based models may bring us closer toward precision medicine.