A Novel Blood-Based microRNA Diagnostic Model with High Accuracy for Multi-Cancer Early Detection

Abstract

Early detection is critical to reduce cancer deaths as treating early stage cancers is more likely to be successful. However, patients with early stage diseases are often asymptomatic and thus less likely to be diagnosed. Here, we utilized four microarray datasets with a standardized platform to investigate comprehensive microRNA expression profiles from 7536 serum samples. A 4-miRNA diagnostic model was developed from the lung cancer training set (n = 416, 208 lung cancer patients and 208 non-cancer participants). The model showed 99% sensitivity and specificity in the lung cancer validation set (n = 3328, 1358 cancer patients and 1970 non-cancer participants); and the sensitivity remained to be >99% for patients with stage 1 disease. When applied to the additional combined dataset of 3792 participants including 2038 cancer patients across 12 different cancer types and 1754 independent non-cancer controls, the model demonstrated high sensitivities ranging from 83.2 to 100% for biliary tract, bladder, colorectal, esophageal, gastric, glioma, liver, pancreatic, and prostate cancers, and showed reasonable sensitivities of 68.2 and 72.0% for ovarian cancer and sarcoma, respectively, while maintaining 99.3% specificity. Our study provided a proof-of-concept data in demonstrating that the 4-miRNA model has the potential to be developed into a simple, inexpensive and noninvasive blood test for early detection of multiple cancers with high accuracy.

Keywords: blood-based diagnostic model; microRNA; multi-cancer early detection; noninvasive.

Figure 1

Case flow diagram. (A) Lung cancer dataset was split into a discovery and a validation set; (B) Ovarian, liver and bladder cancer datasets were combined into a single validation dataset after removing redundant samples.

Figure 2

Development and validation of the 4-miRNA diagnostic model in the lung cancer data set. Where applicable, different colors were used to denote different subject conditions. Dotted horizontal lines represent the cut-point for the diagnostic index of our model. (A) determination of the optimal number (dotted line) of miRNAs for the diagnostic model by 10-fold cross validation in the discovery set; (B) ROC analysis in the discovery set; (C) distribution of diagnostic index in the discovery set; (D) ROC analysis in the validation set; (E) distribution of diagnostic index in the validation set; (F) comparison of diagnostic index of paired serum samples (pre- vs. post-surgery) of 180 lung cancer patients; (G) distribution of diagnostic index in the clinical subsets of the validation set. The percentages shown in the graph were sensitivities in each cancer subgroup.

Figure 3

Performance of 4-miRNA diagnostic model in the datasets of additional cancers. (A) ROC analysis; (B) distribution of diagnostic index the 4-miRNA model. The percentages shown in the graph were sensitivities of each cancer type and specificity of non-cancer controls. Different colors denoted different subject conditions.