Diagnostic Accuracy of Liquid Biopsy in Endometrial Cancer

Abstract

Background: Liquid biopsy is a minimally invasive collection of a patient body fluid sample. In oncology, they offer several advantages compared to traditional tissue biopsies. However, the potential of this method in endometrial cancer (EC) remains poorly explored. We studied the utility of tumor educated platelets (TEPs) and circulating tumor DNA (ctDNA) for preoperative EC diagnosis, including histology determination. Methods: TEPs from 295 subjects (53 EC patients, 38 patients with benign gynecologic conditions, and 204 healthy women) were RNA-sequenced. DNA sequencing data were obtained for 519 primary tumor tissues and 16 plasma samples. Artificial intelligence was applied to sample classification. Results: Platelet-dedicated classifier yielded AUC of 97.5% in the test set when discriminating between healthy subjects and cancer patients. However, the discrimination between endometrial cancer and benign gynecologic conditions was more challenging, with AUC of 84.1%. ctDNA-dedicated classifier discriminated primary tumor tissue samples with AUC of 96% and ctDNA blood samples with AUC of 69.8%. Conclusions: Liquid biopsies show potential in EC diagnosis. Both TEPs and ctDNA profiles coupled with artificial intelligence constitute a source of useful information. Further work involving more cases is warranted.

Platelet-Based Liquid Biopsies through the Lens of Machine Learning

“…The dataset GSE156902 [ 8 , 24 ] contained cohorts of asymptomatic controls, multiple sclerosis patients, selected as a group of patients with a non-malignant disease with a significant inflammatory component, and patients with different forms of cancer. GSE158508 [ 3 ] contained cases of ovarian cancer patients, GSE184904 included endometrial cancer patients [ 21 ], and GSE89843 included non-small cell lung cancer (NSCLC) patients [ 15 ]. The dataset of sarcoma was previously published [ 25 ].…”

“…We also studied the utility of tumor-educated platelets and circulating tumor DNA for preoperative endometrial cancer diagnosis, including histology determination. We provided evidence that liquid biopsy can complement, if not replace, standard microscopic traditional biopsy evaluation [ 21 ]. The aforementioned studies lay the groundwork for a novel approach to liquid biopsies.…”

Platelet detection as a new liquid biopsy tool for human cancers

“…Two years later in 2017, Best et al showed high accuracy of detecting early- (81%) and late-stage (88%) of NSCLC using TEP transcriptome profiles, independent of age, smoking habit, whole-blood storage time and various inflammatory conditions ( 89 ). In a liquid biopsy study of endometrial cancer, the accuracies of utilizing TEP transcriptome profiles and circulating tumor DNA (ctDNA) coupled with artificial intelligence were compared and the authors reported higher accuracy and AUC of TEP-dedicated classifier in predicting endometrial cancer ( 90 ). Xu et al reported that TEP RNA profiles have high potential of distinguishing and staging CRC patients from other noncancerous intestinal diseases ( 91 ).…”

A narrative review for platelets and their RNAs in cancers: New concepts and clinical perspectives

“…[ 79 , 119 , 129 ] To avoid overestimating the diagnostic value, in addition to healthy donors, the control group should include suspected cases, such as the precursor stage of cancer, benign disease, and inflammatory cases, from which malignant disease is more difficult to discriminate. [ 10 , 139 ] Moreover, sex, age, obesity, smoking status, etc might affect the platelet RNA profile and should be properly matched with the experimental groups. [ 87 , 98 , 140 , 141 ] Furthermore, researchers found that the performance of platelet RNAs was not desirable in differentiating breast cancer from other cancers, suggesting that the inclusion of patients with other cancers is necessary to improve Sp during the screening phase.…”