AUTHOR=Guan Weizheng , Wang Yuling , Zhao Huan , Lu Hui , Zhang Sai , Liu Jian , Shi Bo 

TITLE=Prediction models for lymph node metastasis in cervical cancer based on preoperative heart rate variability

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1275487

DOI=10.3389/fnins.2024.1275487

ISSN=1662-453X

ABSTRACT=The occurrence of lymph node metastasis (LNM) is one of the critical factors in determining the staging, treatment and prognosis of cervical cancer (CC). Heart rate variability (HRV) is associated with LNM in patients with CC. The purpose of this study was to validate the feasibility of machine learning (ML) models constructed with preoperative HRV as a feature of CC patients in predicting CC LNM.A total of 313292 patients with pathologically confirmed CC admitted to the Department of Gynaecological Oncology of the First Affiliated Hospital of Bengbu Medical UniversityCollege from November 2020 to SeptemberApril 2023 were included in the study. The patient' preoperative 5minute electrocardiogram data were collected, and HRV time-domain, frequency-domain and nonlinear analyses were subsequently performed, and six ML models were constructed based on 32 parameters. obtaining a total of 39 parameters. Six ML models were constructed by selecting the 11 HRV parameters with the highest rankings of feature importance. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificityprecision, recall and F1 score.Among the 6 ML models, the random forest (RF) model showed the best predictive performance, as specified by the following metrics on the test set: AUC (0.852), accuracy (0.744), sensitivity (0.783), and specificity (0.785).  , as shown by the AUC [0.922, 95% confidence interval (CI) : 0.888-0.956], accuracy (0.838, 95% CI: 0.788-0.888), precision (0.845, 95% CI: 0.795-0.895), recall (0.838, 95% CI: 0.788-0.888), and F1 score (0.837, 95% CI: 0.787-0.887).The RF model built with preoperative HRV parameters showed superior performance in CC LNM prediction, but multicenter studies with larger datasets are needed to validate our findings, and the physiopathological mechanisms between HRV and CC LNM need to be further explored.