Supervised machine learning model to predict oncotype DX risk category in patients over age 50 Journal Article


Authors: Pawloski, K. R.; Gonen, M.; Wen, H. Y.; Tadros, A. B.; Thompson, D.; Abbate, K.; Morrow, M.; El-Tamer, M.
Article Title: Supervised machine learning model to predict oncotype DX risk category in patients over age 50
Abstract: Purpose: Routine use of the oncotype DX recurrence score (RS) in patients with early-stage, estrogen receptor-positive, HER2-negative (ER+/HER2−) breast cancer is limited internationally by cost and availability. We created a supervised machine learning model using clinicopathologic variables to predict RS risk category in patients aged over 50 years. Methods: From January 2012 to December 2018, we identified patients aged over 50 years with T1–2, ER+/HER2−, node-negative tumors. Clinicopathologic data and RS results were randomly split into training and validation cohorts. A random forest model with 500 trees was developed on the training cohort, using age, pathologic tumor size, histology, progesterone receptor (PR) expression, lymphovascular invasion (LVI), and grade as predictors. We predicted risk category (low: RS ≤ 25, high: RS > 25) using the validation cohort. Results: Of the 3880 tumors identified, 1293 tumors comprised the validation cohort in patients of median (IQR) age 62 years (56–68) with median (IQR) tumor size 1.2 cm (0.8–1.7). Most tumors were invasive ductal (80.3%) of low-intermediate grade (80.5%) without LVI (80.9%). PR expression was ≤ 20% in 27.3% of tumors. Specificity for identifying RS ≤ 25 was 96.3% (95% CI 95.0–97.4) and the negative predictive value was 92.9% (95% CI 91.2–94.4). Sensitivity and positive predictive value for predicting RS > 25 was lower (48.3 and 65.1%, respectively). Conclusion: Our model was highly specific for identifying eligible patients aged over 50 years for whom chemotherapy can be omitted. Following external validation, it may be used to triage patients for RS testing, if predicted to be high risk, in resource-limited settings. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Keywords: breast cancer; risk prediction; machine learning; recurrence score
Journal Title: Breast Cancer Research and Treatment
Volume: 191
Issue: 2
ISSN: 0167-6806
Publisher: Springer  
Date Published: 2022-01-01
Start Page: 423
End Page: 430
Language: English
DOI: 10.1007/s10549-021-06443-w
PUBMED: 34751852
PROVIDER: scopus
PMCID: PMC9281430
DOI/URL:
Notes: Article -- Export Date: 1 February 2022 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Monica Morrow
    772 Morrow
  2. Mithat Gonen
    1030 Gonen
  3. Hannah Yong Wen
    302 Wen
  4. Mahmoud B. El-Tamer
    105 El-Tamer
  5. Kelly Teresa Abbate
    14 Abbate
  6. Audree Blythe Tadros
    116 Tadros