1. Swarm Intelligence-Enhanced Detection of Non-Small-Cell Lung Cancer Using Tumor-Educated Platelets.
- Author
-
Best MG, Sol N, In 't Veld SGJG, Vancura A, Muller M, Niemeijer AN, Fejes AV, Tjon Kon Fat LA, Huis In 't Veld AE, Leurs C, Le Large TY, Meijer LL, Kooi IE, Rustenburg F, Schellen P, Verschueren H, Post E, Wedekind LE, Bracht J, Esenkbrink M, Wils L, Favaro F, Schoonhoven JD, Tannous J, Meijers-Heijboer H, Kazemier G, Giovannetti E, Reijneveld JC, Idema S, Killestein J, Heger M, de Jager SC, Urbanus RT, Hoefer IE, Pasterkamp G, Mannhalter C, Gomez-Arroyo J, Bogaard HJ, Noske DP, Vandertop WP, van den Broek D, Ylstra B, Nilsson RJA, Wesseling P, Karachaliou N, Rosell R, Lee-Lewandrowski E, Lewandrowski KB, Tannous BA, de Langen AJ, Smit EF, van den Heuvel MM, and Wurdinger T
- Subjects
- Adult, Aged, Aged, 80 and over, Biomarkers, Tumor, Carcinoma, Non-Small-Cell Lung blood, Carcinoma, Non-Small-Cell Lung genetics, Cohort Studies, Female, Gene Expression Profiling, High-Throughput Nucleotide Sequencing, Humans, Inflammation blood, Inflammation diagnosis, Inflammation genetics, Lung Neoplasms blood, Lung Neoplasms genetics, Male, Middle Aged, Support Vector Machine, Algorithms, Artificial Intelligence, Blood Platelets physiology, Carcinoma, Non-Small-Cell Lung diagnosis, Diagnosis, Computer-Assisted methods, Lung Neoplasms diagnosis
- 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., (Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.)
- Published
- 2017
- Full Text
- View/download PDF