Deep Learning-Based Prediction Model for Breast Cancer Recurrence Using Adjuvant Breast Cancer Cohort in Tertiary Cancer Center Registry

Abstract

Several prognosis prediction models have been developed for breast cancer (BC) patients with curative surgery, but there is still an unmet need to precisely determine BC prognosis for individual BC patients in real time. This is a retrospectively collected data analysis from adjuvant BC registry at Samsung Medical Center between January 2000 and December 2016. The initial data set contained 325 clinical data elements: baseline characteristics with demographics, clinical and pathologic information, and follow-up clinical information including laboratory and imaging data during surveillance. Weibull Time To Event Recurrent Neural Network (WTTE-RNN) by Martinsson was implemented for machine learning. We searched for the optimal window size as time-stamped inputs. To develop the prediction model, data from 13,117 patients were split into training (60%), validation (20%), and test (20%) sets. The median follow-up duration was 4.7 years and the median number of visits was 8.4. We identified 32 features related to BC recurrence and considered them in further analyses. Performance at a point of statistics was calculated using Harrell's C-index and area under the curve (AUC) at each 2-, 5-, and 7-year points. After 200 training epochs with a batch size of 100, the C-index reached 0.92 for the training data set and 0.89 for the validation and test data sets. The AUC values were 0.90 at 2-year point, 0.91 at 5-year point, and 0.91 at 7-year point. The deep learning-based final model outperformed three other machine learning-based models. In terms of pathologic characteristics, the median absolute error (MAE) and weighted mean absolute error (wMAE) showed great results of as little as 3.5%. This BC prognosis model to determine the probability of BC recurrence in real time was developed using information from the time of BC diagnosis and the follow-up period in RNN machine learning model.

Privacy-preserving breast cancer recurrence prediction based on homomorphic encryption and secure two party computation

“…Our work used the same dataset with the previous work [ 31 ], and here we provide some overview and refer details to [ 31 ]. We collected data from 13,117 patients diagnosed with breast cancer and who underwent breast cancer surgery at Samsung Medical Center (SMC) between 2000 and 2016.…”

“…In other words, they visited SMC twice a year on average. See Fig 1 in [ 31 ] for the inclusion and exclusion criteria of breast cancer patients in this study and the characteristics of the study population is shown in Table 1 of the reference [ 31 ]. We identified 31 prognosis features to develop a breast cancer recurrence model by feature selection analysis and clinician’s knowledge.…”

“…The prognosis features used in the breast cancer model were 12 features related to the clinicopathologic category, four features related to treatment, and 15 follow-ups (time-dependent) features which refer to serial measurements during follow-up. The detailed chosen features are explained in the “Prognosis Feature Selection” section of [ 31 ] and more detailed information in the Supplementary Table 1 of [ 31 ].…”

“…Regarding this, a breast cancer recurrence prediction model using GRU is reported [ 31 ]. Here, we re-implemented the developed model by incorporating privacy-preserving methods and demonstrated the performance and usability of privacy-preserving data analysis by comparing the previous non-privacy model [ 31 ] and the proposed privacy-preserving method.…”

Towards Filling the Gaps around Recurrent Events in High-Dimensional Framework: Literature Review and Early Comparison

“…Gupta et al [2019] and Jing et al [2019] developed deep neural networks extensions for the analysis of recurrence, respectively. In addition, Kim et al [2021] proposed an application paper aiming at estimating time between two breast cancer recurrences. However, the methodology used in the latter was an extension of a recurrent neural network which was unfortunately not published in any peer-reviewed journal.…”