AUTHOR=Feng Ying , Wang Zhixiang , Xiao Meizhu , Li Jinfeng , Su Yuan , Delvoux Bert , Zhang Zhen , Dekker Andre , Xanthoulea Sofia , Zhang Zhiqiang , Traverso Alberto , Romano Andrea , Zhang Zhenyu , Liu Chongdong , Gao Huiqiao , Wang Shuzhen , Qian Linxue TITLE=An Applicable Machine Learning Model Based on Preoperative Examinations Predicts Histology, Stage, and Grade for Endometrial Cancer JOURNAL=Frontiers in Oncology VOLUME=12 YEAR=2022 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.904597 DOI=10.3389/fonc.2022.904597 ISSN=2234-943X ABSTRACT=Purpose

To 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 Methods

This 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.

Results

A 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.

Conclusion

A 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.