PET-based radiomic feature based on the cross-combination method for predicting the mid-term efficacy and prognosis in high-risk diffuse large B‑cell lymphoma patients

Abstract

Abstract Objectives This study aims to develop machine-learning cross-combinatorial methods for predicting the mid-term efficacy and prognosis in high-risk patients with diffuse large B-cell lymphoma (DLBCL). Methods Retrospectively, we recruited 177 high-risk DLBCL patients from two medical centers between October 2012 and September 2022 and divided them into a training cohort (n = 123) and a validation cohort (n = 52). We extracted 111 radiomic features along with SUVmax, MTV, and TLG from the baseline PET. 49 feature selection-classification pairs were using to obtain the Radiomics Score (RadScore). Logistic regression was employed to identify independent clinical and PET factors. The models were evaluated using receiver operating characteristic (ROC) curves and calibration curves. Decision curve analysis (DCA) was conducted to assess the predictive power of the models. The prognostic power of RadScore was assessed using Kaplan–Meier plots (KM). Results 177 patients (mean age,63 ± 13 years,129 men) were evaluated. Multivariate analyses showed that gender (OR,2.760;95%CI:1.196,6.368);p = 0.017), B symptoms (OR,4.065;95%CI:1.837,8.955; p = 0.001), SUVmax (OR,2.619;95%CI:1.107,6.194; p = 0.028), and RadScore (OR,7.167;95%CI:2.815,18.248; p<0.001) independently contributed to the risk factors for predicting mid-term outcome. The AUC values of the combined models in the training and validation groups were 0.846 (95%CI:0.775,0.917; p < 0.05) and 0.724 (95%CI:0.591,0.858; p < 0.05) respectively. DCA showed that the combined model incorporating RadScore, clinical risk factors, and metabolic metrics has optimal net clinical benefit. The low RadScore group outperformed progression-free survival (PFS)(HR,0.4601;95%CI:0.2748,0.7702) and overall survival (OS)(HR,0.4683,95%CI: 0.2754,0.7961) compared to the high RadScore group. Conclusion The combined model incorporating RadScore demonstrates a significant enhancement in predicting medium-term efficacy and prognosis in high-risk DLBCL patients. RadScore using selection-classification methods holds promise as a potential method for evaluating medium-term treatment outcome and prognosis in high-risk DLBCL patients.