TY - JOUR
T1 - An Applicable Machine Learning Model Based on Preoperative Examinations Predicts Histology, Stage, and Grade for Endometrial Cancer
AU - Feng, Y.
AU - Wang, Z.X.
AU - Xiao, M.Z.
AU - Li, J.F.
AU - Su, Y.
AU - Delvoux, B.
AU - Zhang, Z.
AU - Dekker, A.
AU - Xanthoulea, S.
AU - Zhang, Z.Q.
AU - Traverso, A.
AU - Romano, A.
AU - Zhang, Z.Y.
AU - Liu, C.D.
AU - Gao, H.Q.
AU - Wang, S.Z.
AU - Qian, L.X.
N1 - Funding Information:
This work was generously sponsored by Beijing Municipal Administration of Hospitals Clinical medicine Development of special funding-YangFan Project (Project No. ZYLX201713).
Funding Information:
We thank the Chinese Scholarship Council (CSC) for their financial support for studying abroad.
Publisher Copyright:
Copyright © 2022 Feng, Wang, Xiao, Li, Su, Delvoux, Zhang, Dekker, Xanthoulea, Zhang, Traverso, Romano, Zhang, Liu, Gao, Wang and Qian.
PY - 2022/5/30
Y1 - 2022/5/30
N2 - PurposeTo build a machine learning model to predict histology (type I and type II), stage, and grade preoperatively for endometrial carcinoma to quickly give a diagnosis and assist in improving the accuracy of the diagnosis, which can help patients receive timely, appropriate, and effective treatment. Materials and MethodsThis study used a retrospective database of preoperative examinations (tumor markers, imaging, diagnostic curettage, etc.) in patients with endometrial carcinoma. Three algorithms (random forest, logistic regression, and deep neural network) were used to build models. The AUC and accuracy were calculated. Furthermore, the performance of machine learning models, doctors' prediction, and doctors with the assistance of models were compared. ResultsA total of 329 patients were included in this study with 16 features (age, BMI, stage, grade, histology, etc.). A random forest algorithm had the highest AUC and Accuracy. For histology prediction, AUC and accuracy was 0.69 (95% CI=0.67-0.70) and 0.81 (95%CI=0.79-0.82). For stage they were 0.66 (95% CI=0.64-0.69) and 0.63 (95% CI=0.61-0.65) and for differentiation grade 0.64 (95% CI=0.63-0.65) and 0.43 (95% CI=0.41-0.44). The average accuracy of doctors for histology, stage, and grade was 0.86 (with AI) and 0.79 (without AI), 0.64 and 0.53, 0.5 and 0.45, respectively. The accuracy of doctors' prediction with AI was higher than that of Random Forest alone and doctors' prediction without AI. ConclusionA random forest model can predict histology, stage, and grade of endometrial cancer preoperatively and can help doctors in obtaining a better diagnosis and predictive results.
AB - PurposeTo build a machine learning model to predict histology (type I and type II), stage, and grade preoperatively for endometrial carcinoma to quickly give a diagnosis and assist in improving the accuracy of the diagnosis, which can help patients receive timely, appropriate, and effective treatment. Materials and MethodsThis study used a retrospective database of preoperative examinations (tumor markers, imaging, diagnostic curettage, etc.) in patients with endometrial carcinoma. Three algorithms (random forest, logistic regression, and deep neural network) were used to build models. The AUC and accuracy were calculated. Furthermore, the performance of machine learning models, doctors' prediction, and doctors with the assistance of models were compared. ResultsA total of 329 patients were included in this study with 16 features (age, BMI, stage, grade, histology, etc.). A random forest algorithm had the highest AUC and Accuracy. For histology prediction, AUC and accuracy was 0.69 (95% CI=0.67-0.70) and 0.81 (95%CI=0.79-0.82). For stage they were 0.66 (95% CI=0.64-0.69) and 0.63 (95% CI=0.61-0.65) and for differentiation grade 0.64 (95% CI=0.63-0.65) and 0.43 (95% CI=0.41-0.44). The average accuracy of doctors for histology, stage, and grade was 0.86 (with AI) and 0.79 (without AI), 0.64 and 0.53, 0.5 and 0.45, respectively. The accuracy of doctors' prediction with AI was higher than that of Random Forest alone and doctors' prediction without AI. ConclusionA random forest model can predict histology, stage, and grade of endometrial cancer preoperatively and can help doctors in obtaining a better diagnosis and predictive results.
KW - machine learning
KW - endometrial carcinoma
KW - diagnosis
KW - prediction
KW - random forest
KW - preoperatively
U2 - 10.3389/fonc.2022.904597
DO - 10.3389/fonc.2022.904597
M3 - Article
C2 - 35712473
SN - 2234-943X
VL - 12
JO - Frontiers in Oncology
JF - Frontiers in Oncology
M1 - 904597
ER -