Utility of pre-treatment FDG PET/CT-derived machine learning models for outcome prediction in classical Hodgkin lymphoma

Objectives Relapse occurs in similar to 20% of patients with classical Hodgkin lymphoma (cHL) despite treatment adaption based on 2dcoxy-2[F-18]fluoro-D-glucose positron emission tomography/computed tomography response. The objective was to evaluate pre-treatment FDG PET/CT-derived machine learning (ML) models for predicting outcome in patients with cHL. Methods All cHL patients undergoing pre-treatment PET/CT at our institution between 2008 and 2018 were retrospectively identified. A 1.5 x mean liver standardised uptake value (SUV) and a fixed 4.0 SUV threshold were used to segment PET/CT data. Feature extraction was performed using PyRadiomics with ComBat harmonisation. Training (80%) and test (20%) cohorts stratified around 2-year event-free survival (EFS), age, sex, ethnicity and disease stage were defined. Seven ML models were trained and hyperparameters tuned using stratified 5-fold cross-validation. Area under the curve (AUC) from receiver operator characteristic analysis was used to assess performance. Results A total of 289 patients (153 males), median age 36 (range 16-88 years), were included. There was no significant difference between training (n = 231) and test cohorts (n = 58) (p value > 0.05). A ridge regression model using a 1.5 x mean liver SUV segmentation had the highest performance, with mean training, validation and test AUCs of 0.82 +/- 0.002, 0.79 +/- 0.01 and 0.81 4- 0.12. However, there was no significant difference between a logistic model derived from metabolic tumour volume and clinical features or the highest performing radiomic model. Conclusions Outcome prediction using pre-treatment FDG PET/CT-derived ML models is feasible in cHL patients. Further work is needed to determine optimum predictive thresholds for clinical use.

Automated summary

This study evaluated the ability of machine learning models derived from pre-treatment FDG PET/CT to predict outcomes in cHL patients. The results showed that a ridge regression model using a 1.5 x mean liver SUV segmentation had the highest performance, with a high AUC when evaluated on training, validation, and test datasets.