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
461P - A randomized controlled trial of yoga in locally advanced non-small cell lung cancer patients receiving chemoradiotherapy
Presenter: Indranil Khan
Session: Poster Display
Resources:
Abstract
462P - Cognitive function of survivors with non-central nervous system cancer and its correlates: A community rehabilitation perspective
Presenter: Ann Kuo
Session: Poster Display
Resources:
Abstract
463P - The use of antipsychotic for managing delirium in patients with cancer
Presenter: Natasya Reina
Session: Poster Display
Resources:
Abstract
464P - The prevalence and correlates of frailty and pre-frailty in elderly patients with breast cancer: A cross-sectional study from China
Presenter: Min Xiao
Session: Poster Display
Resources:
Abstract
465P - Oncological care needs of people with mental illness: A single institution experience in Australia
Presenter: Hui Ling Yeoh
Session: Poster Display
Resources:
Abstract
466P - Identification of patient satisfaction predictors among women attending oncology daycare unit using validated survey questionnaire (PSS Tool): An institutional experience in central India
Presenter: Rajesh Patidar
Session: Poster Display
Resources:
Abstract
467P - Evaluation of the effectiveness of a cluster management model based on evidence-based concepts in oncology nutrition case management
Presenter: Li He
Session: Poster Display
Resources:
Abstract
468P - The patterns of use of Traditional Chinese Medicine (TCM) in cancer patients in Hong Kong
Presenter: Olivia L T Chan
Session: Poster Display
Resources:
Abstract
469P - The need of special care for adolescent and young adult (AYA) cancer survivors: Perspective from oncologists in India
Presenter: Nandini Menon
Session: Poster Display
Resources:
Abstract
470TiP - Randomised controlled trial to evaluate the efficacy and safety of moisturising creams with or without palm-oil-derived vitamin E concentrate in addition to urea-based cream or urea-based cream alone in Capecitabine-associated Palmar-Plantar Erythrodysesthesia (ECaPPE)
Presenter: Pei-Jye Voon
Session: Poster Display
Resources:
Abstract