Abstract P2-07-07: Development of a machine learning-based classifier for Oncotype DX® category prediction in a population of lymph node positive breast carcinoma patients

Abstract

Abstract INTRODUCTION: Oncotype DX® (ODX) Assay is a valuable prognostic and predictive tool in ER+, Her2- invasive breast cancer (IBC). Initially tested and validated in lymph node (LN) negative patients, the indications of this test have been expanded to include patients with limited LN-positive disease. Several prediction systems have been developed to predict the ODX Recurrence Score (RS) with substantial performance in predicting a high vs low RS score but with low performance when predicting the 3 classes that compose the standard ODX. Additionally, many of these prediction systems have not been developed and/or tested for a population of LN+ patients. OBJECTIVES: The primary objective of this study was to evaluate the performance of several previously published ODX RS predictive systems in a population of LN+ patients. Furthermore, we developed a machine-learning based classification system to accurately predict the ODX 3 category RS for this specific population. METHODS: We conducted a retrospective search of Stanford's pathology database for all patients with LN+ IBC diagnosed between January 2013 and December 2017 with an ODX RS available. A total of 119 patients were identified for inclusion in this cohort. Our multivariate pathologic feature-based discriminatory model aimed to classify each case as belonging to the low, intermediate or high ODX RS category. We performed model validation by the 10-fold cross validation (10F-CV) method. The model's performance was assessed by comparing simple accuracy, balanced accuracy, F1 score (harmonic average of the precision and recall) and several concordance classification metrics. RESULTS: Of the evaluated methods, Magee equations performed well in this population of LN+ patients with the modified Magee equation 2 displaying the best accuracy (70.9%) which was surprisingly better than originally reported (55.8%, in Klein et al. Mod Path. 2013). After an initial screen of methods and tuning of the best performing model, our model achieved an overall accuracy of 78.1% on 10F-CV with a 79.1 % balanced accuracy and no two-step discordances. This corresponded to an increase of weighted Cohen's kappa of 30% versus the best performing Magee equation in this cohort and an increase of 103% versus the modified Magee 1 equation (which uses the same features as our model except for tumor grade). DISCUSSION: Classifiers aimed at providing an alternative to Oncotype DX testing are available and perform consistently across datasets. We are currently validating our approach in a population of 1000 LN-negative patients from the MSKCC and the SEER database. Due to the substantial performance of our machine learning-based classifier based on standard reported pathologic features, our model may be considered an alternative to the ODX standard testing or a screening method for ODX testing, especially for cases with where the cost and availability of the ODX test are a concern. Citation Format: Beca F, Yang S-R, Gruber JG, Barry-Holson K, West R, Wen HY, Allison KH. Development of a machine learning-based classifier for Oncotype DX® category prediction in a population of lymph node positive breast carcinoma patients [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P2-07-07.