Development of an absolute assignment predictor for triple-negative breast cancer subtyping using machine learning approaches

Abstract

Triple-negative breast cancer (TNBC) heterogeneity represents one of the main impediment to precision medicine for this disease. Recent concordant transcriptomics studies have shown that TNBC could be splitted into at least three subtypes with potential therapeutic implications.Although, a few studies have been done to predict TNBC subtype by means of transcriptomics data, subtyping was partially sensitive and limited by batch effect and dependence to a given dataset, which may penalize the switch to routine diagnostic testing. Therefore, we sought to build an absolute predictor (i.e. intra-patient diagnosis) based on machine learning algorithm with a limited number of probes. To this end, we started by introducing probe binary comparison for each patient (indicators). We based predictive analysis on this transformed data. Probe selection was first performed by combining both filter and wrapper methods for variable selection using cross validation. We thus tested three prediction models (random forest, gradient boosting [GB] and extreme gradient boosting) using this optimal subset of indicators as inputs. Nested crossvalidation allowed us to consistently choose the best model. Results showed that the 50 selected indicators highlighted biological characteristics associated with each TNBC subtype. The GB based on this subset of indicators has better performances as compared to the other models.

Gradient Boosting Machine Identified Predictive Variables for Breast Cancer Patients Pre- and Post-Radiotherapy: Preliminary Results of an 8-Year Follow-Up Study

“…Moreover, we employed the GBM algorithm to identify the most predictive variables, and we used the SHAP method to interpret the outputs. Previous studies have discussed the use of different machine learning algorithms such as random forest, GBM, and the extreme boosting machine to find predictive variables in patients with BC [ 44 , 45 ]. However, there is no consensus about which algorithm should be used because the accuracy of each model mainly depends on the dataset.…”

Artificial intelligence assists precision medicine in cancer treatment

“…For example, Warnat-Herresthal et al found that ML-based transcriptomics can assist in the diagnosis of acute myeloid leukemia (63). Moreover, Ben Azzouz et al used an ML approach based on transcriptomics data to calculate triple-negative breast cancer subtypes, in order to overcome the barrier of heterogeneity in the treatment of the disease (64). Finally, some ML-based transcriptomics have also been used in the development of prognostic biomarkers for prostate cancer (65), the diagnosis of colorectal cancer (66), and the prediction of immune response (67).…”

Machine learning for predicting the survival in osteosarcoma patients: Analysis based on American and Hebei Province cohort

“…Machine learning is a new type of artificial intelligence, which has been widely used in medical data analysis and is a powerful tool for improving clinical strategies [14][15][16]. Some tree-based machine learning methods (such as survival tree [ST], random survival forest [RSF], and gradient boosting machine [GBM]) can account for interaction and effect modification between variables and have been applied in some prognosis studies [17][18][19][20][21][22][23][24][25][26][27]. In many studies, in which the categorical variable was the dependent variable, the prediction performance of machine learning is better than that of traditional models [6,14,28,29].…”