Abstract
Abstract Purpose: Identifying patients who may benefit from neoadjuvant chemotherapy will facilitate personalized treatment regarding chemotherapy and surgery. This study compares the predictive performance of an artificial neural network algorithm with nomogram to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in patients with advanced breast cancer.. Methods: Medical records of 359 patients with advanced breast cancer who received NAC prior to surgical resection between January 2017 and December 2019 were retrospectively reviewed. Random over sampling method was used to overcome data imbalance and random sampling method to divide patients into training and test sets at a split ratio of 7:3. Univariate and multivariate regression analyses were used to develop a nomogram and a machine learning model based on artificial neural network. Performance of the two models were evaluated using the validation sets in terms of area under the receiver operating characteristic curve (AUC).. Results: Multivariate logistic regression analysis showed that high level of estrogen receptor (ER) (OR 0.84, p < 0.001), positive human epidermal growth factor receptor 2 (HER2) status (OR 1.25, p < 0.001), complete response on magnetic resonance imaging (MRI) (OR 1.62, p < 0.001), abnormal CEA level after NAC (OR 0.86, p = 0.051), and abnormal CA15-3 level after NAC (OR 0.87, p = 0.074) were independent predictors of pCR. A nomogram and a neural network model to predict pCR were developed using the five predictors. Validation test showed AUCs of 0.789 [95 % confidence interval (CI), 0.707-0.871] for the nomogram and 0.876 [95 % CI, 0.808-0.943] for the neural network model.. Conclusion: We developed a nomogram and an artificial neural network (ANN)-based machine learning model to predict pCR after NAC. Both models showed excellent performance, but the ANN model performed better in terms of accuracy and discrimination. Machine-learning algorithms hold promise in medical application and provide better prediction than nomogram. Citation Format: Hee-Chul Shin, Ji-Jung Jung, Eun-Kyu Kim, Eunyoung Kang. Development of an aritifical neural network model and comparison with nomogram for prediction of pathological complete response after neoadjuvant chemotherapy in breast cancer [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P1-08-06.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.