Ensemble Learning Based Postpartum Hemorrhage Diagnosis for 5G Remote Healthcare

Yawei Zhang,Rong Zhao,Xin Wang,Ningyu Han

doi:10.1109/access.2021.3051215

Abstract

The fifth-generation (5G) communications enables various promising applications that was once impossible, e.g. remote healthcare with the help of fast and reliably delivery of medical data. Post-partum hemorrhage (PPH) refers to the massive blood loss after the birthing stage (within 24 hours), i.e. >500ml for the vaginal delivery, and >1000ml for the cesarean section. PPH is by far the most common cause of the mortality rate of pregnant women, as well as a primary cause of current pregnant mortality in China. Despite the great potential of prediction of PPH, there is currently no effective tool based on the limited raw data from the clinical trials. In the study, we retrospectively study the 3842 vaginal delivery cases in 2017 collected from Beijing Obstetrics and Gynecology Hospital, Capital Medical University. In particular, we obtain the prediction based diagnostic model relying on machine learning, and we adopt the ensemble learning to accomplish this task, by combining the results of various candidate methods. According to the experimental results, the accuracy of correct PPH diagnosis would approach 96.7%; the total disseminated intravascular coagulation (DIC) prediction accuracy approaches 90.3%. In this regard, we may conclude the proposed model based on machine learning would allow us to predict successfully the risk of PPH, and assess the critical level of PPH patient. We anticipate our study results would contribute to the reduction the mortality of pregnant women.

Highlights

The fifth-generation (5G) communications allow for highspeed and ultra-reliable data transmissions [1]–[3], which would boost various new demands and emerging applications [4], [5]
We study the ensemble learning in the context of postpartum hemorrhage (PPH) and thereby construct the complication prediction model, enabled by the recent advances on 5G communication and machine learning
DATASET FEATURE SELECTION In the work, our study aims to construct a prediction model of PPH and its complications based on the method of ensemble learning

Summary

INTRODUCTION

The fifth-generation (5G) communications allow for highspeed and ultra-reliable data transmissions [1]–[3], which would boost various new demands and emerging applications [4], [5]. We collect a total of 3842 vaginal delivery cases in 2017 from Beijing Obstetrics and Gynecology Hospital, Capital Medical University This large dataset potentially allows us to derive a reliable machine learning prediction model. The selection of base learners in ensemble learning (e.g. ANN, SVM, regression, etc.), which is of great importance for the performance, has been rarely exploited in the literatures on PPH data analysis To address this practical difficulty, we construct different EL schemes for both the PPH and DIC tasks, based on their features and limitations. Other performance metrics used for our imbalanced samples, e.g. the recall ratio, the F-measure as well as the Matthews correlation coefficient (MCC), are investigated In this regard, we would conclude our proposed model based on well-designed ensemble learning allows us to predict successfully the risk of PPH, and assess the critical level of PPH patients.

DATASET FEATURE SELECTION

RANDOM FOREST

EXTREME GRADIENT BOOSTING

ENSEMBLE LEARNING

PERFORMANCE EVALUATION FOR PPH PREDICTION

CONCLUSION