1. Predicting ipsilateral recurrence in women treated for ductal carcinoma in situ using machine learning and multivariable logistic regression models.
- Author
-
Lamb LR, Mercaldo S, Kim G, Hovis K, Oseni TO, and Bahl M
- Subjects
- Humans, Female, Adult, Middle Aged, Aged, Aged, 80 and over, Child, Preschool, Mastectomy, Segmental, Logistic Models, Retrospective Studies, Machine Learning, Neoplasm Recurrence, Local diagnostic imaging, Neoplasm Recurrence, Local epidemiology, Neoplasm Recurrence, Local pathology, Carcinoma, Intraductal, Noninfiltrating diagnostic imaging, Carcinoma, Intraductal, Noninfiltrating therapy, Carcinoma, Intraductal, Noninfiltrating pathology, Carcinoma, Ductal, Breast pathology, Breast Neoplasms diagnostic imaging, Breast Neoplasms therapy
- Abstract
Purpose: To develop machine learning (ML) and multivariable regression models to predict ipsilateral breast event (IBE) risk after ductal carcinoma in situ (DCIS) treatment., Methods: A retrospective investigation was conducted of patients diagnosed with DCIS from 2007 to 2014 who were followed for a minimum of five years after treatment. Data about each patient were extracted from the medical records. Two ML models (penalized logistic regression and random forest) and a multivariable logistic regression model were developed to evaluate recurrence-related variables., Results: 650 women (mean age 56 years, range 27-87 years) underwent treatment for DCIS and were followed for at least five years after treatment (mean 8.0 years). 5.5% (n = 36) experienced an IBE. With multivariable analysis, the variables associated with higher IBE risk were younger age (adjusted odds ratio [aOR] 0.96, p = 0.02), dense breasts at mammography (aOR 3.02, p = 0.02), and < 5 years of endocrine therapy (aOR 4.48, p = 0.02). The multivariable regression model to predict IBE risk achieved an area under the receiver operating characteristic curve (AUC) of 0.75 (95% CI 0.67-0.84). The penalized logistic regression and random forest models achieved mean AUCs of 0.52 (95% CI 0.42-0.61) and 0.54 (95% CI 0.43-0.65), respectively., Conclusion: Variables associated with higher IBE risk after DCIS treatment include younger age, dense breasts, and <5 years of adjuvant endocrine therapy. The multivariable logistic regression model attained the highest AUC (0.75), suggesting that regression models have a critical role in risk prediction for patients with DCIS., Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Dr. Manisha Bahl is a consultant for Lunit (medical AI software company) and an expert panelist for 2nd.MD (digital health company). These relationships are not directly relevant to the submitted work. There are no other disclosures., (Copyright © 2022 Elsevier Inc. All rights reserved.)
- Published
- 2022
- Full Text
- View/download PDF