F-FDG PET radiomics score construction by automatic machine learning for treatment response prediction in elderly patients with diffuse large B-cell lymphoma: a multicenter study.

in Journal of cancer research and clinical oncology by Jincheng Zhao, Wenzhuo Zhao, Man Chen, Jian Rong, Yue Teng, Jianxin Chen, Jingyan Xu

TLDR

  • The study developed and validated an AutoML model using PET imaging-based radiomics features to predict treatment response in elderly DLBCL patients, with high accuracy compared to metabolic parameters and clinical-pathological models.

Abstract

To explore the development and validation of automated machine learning (AutoML) models forF-FDG PET imaging-based radiomics signatures to predict treatment response in elderly patients with diffuse large B-cell lymphoma (DLBCL). A retrospective analysis was conducted on 175 elderly (≥ 60 years) DLBCL patients diagnosed between March 2015 and March 2023 at two medical centers, with a total of 1010 lesions. The baseline PET imaging-based radiomics features of the training cohort were processed using AutoML model AutoGluon to generate a radiomics score (radscore) and predict treatment response at the lesion and patient levels. Furthermore, a multivariable logistic analysis was used to design and evaluate a multivariable model in the training and validation cohorts. ROC curve analysis showed that the radscore generated by AutoML exhibited higher accuracy in predicting treatment response at the lesion level compared to metabolic parameters (SUVmax, MTV, and TLG) in both the training group (AUC: 0.791, 0.542, 0.667, 0.651, respectively) and the validation group (AUC: 0.712, 0.616, 0.639, 0.657, respectively). Multivariable logistic analysis indicated that NCCN-IPI (OR = 5.427, 95% CI: 1.163-25.317), BCL-2 (OR = 3.714, 95% CI: 1.406-9.816), TMTV (OR = 4.324, 95% CI: 1.095-17.067), and avg-radscore (OR = 3.176, 95% CI: 1.313-7. 686) were independent predictors of treatment response. The multivariable model comprising NCCN-IPI, BCL-2, TMTV, and avg-radscore outperformed conventional models and clinical-pathological models in predicting treatment response. (P<0.05). The radscore generated by AutoML can predict the treatment response of elderly DLBCL patients, potentially aiding in clinical decision-making.

Overview

  • The study aimed to develop and validate an automated machine learning (AutoML) model for predicting treatment response in elderly patients with diffuse large B-cell lymphoma (DLBCL) using PET imaging-based radiomics features.
  • A retrospective analysis was conducted on 175 elderly DLBCL patients diagnosed between March 2015 and March 2023 at two medical centers, with a total of 1010 lesions.
  • The primary objective was to evaluate the performance of the AutoML model in predicting treatment response at the lesion and patient levels, and compare it with metabolic parameters and clinical-pathological models.

Comparative Analysis & Findings

  • The AutoML model generated a radiomics score (radscore) that exhibited higher accuracy in predicting treatment response at the lesion level compared to metabolic parameters (SUVmax, MTV, and TLG) in both the training and validation cohorts.
  • Multivariable logistic analysis indicated that NCCN-IPI, BCL-2, TMTV, and avg-radscore were independent predictors of treatment response.
  • The multivariable model comprising NCCN-IPI, BCL-2, TMTV, and avg-radscore outperformed conventional models and clinical-pathological models in predicting treatment response (P<0.05).

Implications and Future Directions

  • The study demonstrates the potential of AutoML models in predicting treatment response in elderly DLBCL patients, which can aid in clinical decision-making.
  • Future studies should aim to validate the model in larger cohorts and explore its application in real-world clinical scenarios.
  • The model can also be used to identify high-risk patients who may benefit from more aggressive treatment strategies.
Read Full Article