AUTHOR=Huang Yibao , Zhu Qingqing , Xue Liru , Zhu Xiaoran , Chen Yingying , Wu Mingfu 

TITLE=Machine Learning-Assisted Ensemble Analysis for the Prediction of Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.817250

DOI=10.3389/fonc.2022.817250

ISSN=2234-943X

ABSTRACT=Objective: The role of neoadjuvant chemotherapy (NACT) before concurrent chemoradiotherapy (CCRT) or adjuvant chemotherapy after CCRT is still investigational. Non-response to platinum-based NACT is a major cause of poor prognosis. Herein, further studies are strongly warranted to better predict response to NACT (rNACT) in patients with locally advanced cervical cancer (LACC). This study aims to develop a machine learning (ML)-assisted model capable of accurately predicting the probability of rNACT.
Methods: We retrospectively collected 636 patients diagnosed with IB2 to IIA2 cervical cancer at the Tongji Hospital between January 1, 2015, and April 1, 2020. Five ML-assisted models were developed from candidate clinical features using two-step estimation methods. The receiver operating characteristic curve (ROC), decision curve analysis (DCA), and clinical impact curve (CIC) were performed to evaluate the robustness and clinical practicability of each model. 
Results: Finally, a total of 30 candidate variables were included, and the rNACT prediction model was established by an ML-based algorithm. The areas under the ROC curve (AUCs) of the random forest classifier (RFC) model, support vector machine(SVM), eXtreme gradient boosting (XGBoost), artificial neural network (ANN), and decision tree (DT) ranged from 0.682 to 0.847. Among them, RFC obtained the optimal prediction efficiency via adding inflammatory factors, which are platelet-to-lymphocyte ratio(PLR), neutrophil-to-lymphocyte ratio(NLR), neutrophil-to-albumin ratio(NAR), and lymphocyte-to-monocyte ratio(LMR), respectively.
Conclusions: We successfully developed ML-based prediction models for rNACT, particularly the RFC, which can improve the prediction of rNACT in patients with LACC. The practicality of prediction and early detection may facilitate the choice of treatment.