AUTHOR=Zhang Jiawen , Jiang Linhua , Zhu Xinguo 

TITLE=A Machine Learning-Modified Novel Nomogram to Predict Perioperative Blood Transfusion of Total Gastrectomy for Gastric Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.826760

DOI=10.3389/fonc.2022.826760

ISSN=2234-943X

ABSTRACT=Abstract 
Background Perioperative blood transfusion reserves are limited, and the outcome of blood transfusion remains unclear. Therefore, it is important to prepare plans for perioperative blood transfusions. This study aimed to establish a risk assessment model to guide clinical patient management.
Methods This retrospective comparative study involving 513 patients with TG between January 2018 and January 2021 was conducted using propensity score matching (PSM). The influencing factors were explored by logistic regression, correlation analysis, and machine learning; then, a nomogram was established.
Results After assessing the importance of factors through machine learning, blood loss, preoperative control nutritional status (CONUT), hemoglobin (Hb) and triglyceride-glucose (TyG) index were considered to be the modified transfusion-related factors. The modified model is not considered to be different from the original model in terms of performance and is simpler. A nomogram was created, the C-index was 0.834 and the DCA demonstrated good clinical benefit.
Conclusions A nomogram was established and modified with machine learning, which suggests the importance of the patient’s integral condition. This reminds us that caution should be exercised in transfusions, and if necessary, preoperative nutritional interventions or delayed surgery should be implemented for safety.