Abstract 620P
Background
Cancer constitutes a major burden to global health and the critical role of early diagnosis for cancer management is self-evident. Even though various miRNA-based signatures have been developed, their clinical utilization is limited due to various reasons. In this article, we innovatively developed a signature based on pairwise expression of miRNAs (miRPs) for pan-cancer diagnosis using machine learning approach.
Methods
miRNA spectrum of 15832 patients with 13 different cancers from 10 cohorts were analyzed. 15148 patients were divided into training, validation, and test sets with a ratio of 7:2:1, while 648 patients were utilized as external test. Pairwise comparison was performed to generate miRP score, defined by the comparison between two miRNAs, in training set. Five different machine-learning (ML) algorithms (XGBoost, SVM, RandomForest, LASSO, and Logistic) were adopted for signature construction. The best ML algorithm and the optimal number of miRPs included were identified using AUC and youden index in validation. Performance of the ideal model was evaluated in test and external set based on AUC, Youden index, positive predictive value (PPV), negative predictive value (NPV), sensitivity, specificity, and accuracy. The AUC of entire cohorts was compared to previously published 25 signatures.
Results
The Random Forest approach including 31 miRPs (31-miRP) outperformed others and was retained for further evaluation. The AUC of 31-miRP ranges 0.980-1.000 in different set. Remarkably, 31-miRP exhibited advantages in differentiating different cancers from normal tissues. Moreover, 31-miRP demonstrate superiorities in detecting early-stage cancers, with AUC ranging from 0.961-0.998. Compared to previously published 25 different signatures, 31-miRP also demonstrated clear advantages. Remarkably, 31-miRP also exhibited promising capabilities in differentiating cancers from corresponding benign lesions.
Conclusions
The 31-miRP exhibited outstanding diagnostic performance, characterized by high accuracy and sensitivity, thereby holding potential as a reliable tool for cancer diagnosis at early stage. Nevertheless, its effectiveness still warrants further investigation in real-world setting in future.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
CAMS Innovation Fund for Medical Sciences (No.2021-I2M-1-050); National Natural Science Foundation for Young Scientists of China (No. 82203025).
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
39P - Prognostic significance of hypoxic microenvironment biomarkers in invasive ductal breast cancer
Presenter: Sungmin Kang
Session: Poster Display
Resources:
Abstract
40P - Intra-tumoral CD3, CD4, and CD8 as prognostic biomarkers in Asian breast cancer
Presenter: Jia Wern Pan
Session: Poster Display
Resources:
Abstract
41P - Brown fat activation demonstrated on FDG PET/CT predicts survival outcome
Presenter: Sonya Park
Session: Poster Display
Resources:
Abstract
42P - A promising anticancer drug for triple-negative breast cancer: OZ-001 suppresses tumor growth by dual targeting STAT3 and calcium signaling
Presenter: Jisun Kim
Session: Poster Display
Resources:
Abstract
43P - Performance evaluation of a combined risk model for breast cancer risk prediction in Indonesian population (TRIP Study)
Presenter: Marco Wijaya
Session: Poster Display
Resources:
Abstract
44P - Pathological complete response to neoadjuvant chemotherapy and outcomes in Her-2 negative locally advanced breast cancer
Presenter: Amrith Patel
Session: Poster Display
Resources:
Abstract
45P - Demographic determinants of pathological complete response after neoadjuvant chemotherapy in breast cancer
Presenter: Anvesh Dharanikota
Session: Poster Display
Resources:
Abstract
46P - Predicting toxicity following cancer chemotherapy by detecting transporter gene ABCB1 (C1236T, G2677T/A, C3435CT) polymorphism in breast cancer patients receiving chemotherapy with anthracycline and taxane either sequentially or concomitantly
Presenter: Tanuma Mistry
Session: Poster Display
Resources:
Abstract
47P - Sequencing of chemotherapy and surgery among older triple-negative and HER2-positive breast cancer patients with comorbidities
Presenter: Anvesh Dharanikota
Session: Poster Display
Resources:
Abstract
48P - The impact of preoperative axillary ultrasound on the false negative rate of sentinel lymph node biopsy in post neoadjuvant chemotherapy breast cancer patients
Presenter: Byshetty Rajendar
Session: Poster Display
Resources:
Abstract