Swarm Intelligence-Enhanced Detection of Non-Small-Cell Lung Cancer Using Tumor-Educated Platelets.
Journal:
Cancer cell
Published Date:
Aug 14, 2017
Abstract
Blood-based liquid biopsies, including tumor-educated blood platelets (TEPs), have emerged as promising biomarker sources for non-invasive detection of cancer. Here we demonstrate that particle-swarm optimization (PSO)-enhanced algorithms enable efficient selection of RNA biomarker panels from platelet RNA-sequencing libraries (n = 779). This resulted in accurate TEP-based detection of early- and late-stage non-small-cell lung cancer (n = 518 late-stage validation cohort, accuracy, 88%; AUC, 0.94; 95% CI, 0.92-0.96; p < 0.001; n = 106 early-stage validation cohort, accuracy, 81%; AUC, 0.89; 95% CI, 0.83-0.95; p < 0.001), independent of age of the individuals, smoking habits, whole-blood storage time, and various inflammatory conditions. PSO enabled selection of gene panels to diagnose cancer from TEPs, suggesting that swarm intelligence may also benefit the optimization of diagnostics readout of other liquid biopsy biosources.
Authors
Keywords
Adult
Aged
Aged, 80 and over
Algorithms
Artificial Intelligence
Biomarkers, Tumor
Blood Platelets
Carcinoma, Non-Small-Cell Lung
Cohort Studies
Diagnosis, Computer-Assisted
Female
Gene Expression Profiling
High-Throughput Nucleotide Sequencing
Humans
Inflammation
Lung Neoplasms
Male
Middle Aged
Support Vector Machine