Application of Machine Learning Analyses Using Clinical and [18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer

Predicting disease recurrence in breast cancer patients using machine learning models with clinical and radiomic characteristics: a retrospective study

BACKGROUND

The goal is to use three different machine learning models to predict the recurrence of breast cancer across a very heterogeneous sample of patients with varying disease kinds and stages.

METHODS

A heterogeneous group of patients with varying cancer kinds and stages, including both triple-negative breast cancer (TNBC) and non-triple-negative breast cancer (non-TNBC), was examined. Three distinct models were created using the following five machine learning techniques: Adaptive Boosting (AdaBoost), Random Under-sampling Boosting (RUSBoost), Extreme Gradient Boosting (XGBoost), support vector machines (SVM), and Logistic Regression. The clinical model used both clinical and pathology data in conjunction with the machine learning algorithms. The machine learning algorithms were combined with dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) imaging characteristics in the radiomic model, and the merged model combined the two types of data. Each technique was evaluated using several criteria, including the receiver operating characteristic (ROC) curve, precision, recall, and F1 score.

RESULTS

The results suggest that the integration of clinical and radiomic data improves the predictive accuracy in identifying instances of breast cancer recurrence. The XGBoost algorithm is widely recognized as the most effective algorithm in terms of performance.

CONCLUSION

The findings presented in this study offer significant contributions to the field of breast cancer research, particularly in relation to the prediction of cancer recurrence. These insights hold great potential for informing future investigations and clinical interventions that seek to enhance the accuracy and effectiveness of recurrence prediction in breast cancer patients.

The effect of data resampling methods in radiomics

Radiomic datasets can be class-imbalanced, for instance, when the prevalence of diseases varies notably, meaning that the number of positive samples is much smaller than that of negative samples. In these cases, the majority class may dominate the model's training and thus negatively affect the model's predictive performance, leading to bias. Therefore, resampling methods are often utilized to class-balance the data. However, several resampling methods exist, and neither their relative predictive performance nor their impact on feature selection has been systematically analyzed. In this study, we aimed to measure the impact of nine resampling methods on radiomic models utilizing a set of fifteen publicly available datasets regarding their predictive performance. Furthermore, we evaluated the agreement and similarity of the set of selected features. Our results show that applying resampling methods did not improve the predictive performance on average. On specific datasets, slight improvements in predictive performance (+ 0.015 in AUC) could be seen. A considerable disagreement on the set of selected features was seen (only 28.7% of features agreed), which strongly impedes feature interpretability. However, selected features are similar when considering their correlation (82.9% of features correlated on average).

The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer

OBJECTIVE

To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer.

METHODS

This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index).

RESULTS

Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808).

CONCLUSION

ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer.

ADVANCES IN KNOWLEDGE

ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.