Predicting multi-class responses to preoperative chemoradiotherapy in rectal cancer patients

Abstract

Background: Preoperative chemoradiotherapy (CRT) has become a widely used treatment for improving local control of disease and increasing survival rates of rectal cancer patients. We aimed to identify a set of genes that can be used to predict responses to CRT in patients with rectal cancer.

Methods: Gene expression profiles of pre-therapeutic biopsy specimens obtained from 77 rectal cancer patients were analyzed using DNA microarrays. The response to CRT was determined using the Dworak tumor regression grade: grade 1 (minimal, MI), grade 2 (moderate, MO), grade 3 (near total, NT), or grade 4 (total, TO).

Results: Top ranked genes for three different feature scores such as a p-value (pval), a rank product (rank), and a normalized product (norm) were selected to distinguish pre-defined groups such as complete responders (TO) from the MI, MO, and NT groups. Among five different classification algorithms, supporting vector machine (SVM) with the top 65 norm features performed at the highest accuracy for predicting MI using a 5-fold cross validation strategy. On the other hand, 98 pval features were selected for predicting TO by elastic net (EN). Finally we combined TO- and MI-finder models to build a three-class classification model and validated it using an independent dataset of rectal cancer mRNA expression.

Conclusions: We identified MI- and TO-finders for predicting preoperative CRT responses, and validated these data using an independent public dataset. This stepwise prediction model requires further evaluation in clinical studies in order to develop personalized preoperative CRT in patients with rectal cancer.

Keywords: Chemoradiotherapy; Dworak classification; Microarray; Prediction model; Rectal cancer.

Fig. 1

Characteristics of features selected by three different scores. All genes are represented in volcano plot. Gene with top 100 highest feature score are depicted with different color and shape while others with grey color. P-value based feature score (‘pval’, left), normalized product based (‘norm’, middle) and rank product based feature scores (‘rank’, right) are shown

Fig. 2

Binary-class prediction accuracy for MI and TO. Column and row of whole figure represent prediction class (MI or TO) and feature score used (pval, norm, or rank), respectively. For each panel, different color denotes different classification algorithm. Maximum accuracy among the algorithms and the number of feature used for the maximum value are also depicted in each panel

Fig. 3

Sequential multi-class prediction. To predict the preoperative CRT response of a patient, TO predictor is performed and answers whether the patient is total response group or not. If yes, CRT is conducted, or MI predictor is performed and predicts whether the patient will show minimal response. According to the result of this step, clinician can decide a proper treatment of the patient