Diagnosis of head and neck cancer by AI-based tumor-educated platelet RNA profiling of liquid biopsies

Over 95% of head and neck cancers are squamous cell carcinoma (HNSCC). HNSCC is mostly diagnosed late, causing a poor prognosis despite the application of invasive treatment protocols. Tumor-educated platelets (TEPs) have been shown to hold promise as a molecular tool for early cancer diagnosis. We sequenced platelet mRNA isolated from blood of 101 patients with HNSCC and 101 propensity-score matched noncancer controls. Two independent machine learning classification strategies were employed using a training and validation approach to identify a cancer predictor: a particle swarm optimized support vector machine (PSO-SVM) and a least absolute shrinkage and selection operator (LASSO) logistic regression model. The best performing PSO-SVM predictor consisted of 245 platelet transcripts and reached a maximum area under the curve (AUC) of 0.87. For the LASSO-based prediction model, 1,198 mRNAs were selected, resulting in a median AUC of 0.84, independent of HPV status. Our data show that TEP RNA classification by different AI tools is promising in the diagnosis of HNSCC.

Authors

Institutions

Publication Details

Journal
JCI Insight
Published
2025-11-27
DOI
https://doi.org/10.1172/jci.insight.186680
Primary Topic
Cancer Genomics and Diagnostics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Diagnosis of head and neck cancer by AI-based tumor-educated platelet RNA profiling of liquid biopsies

Johannes A. Langendijk, Robert Paul Takes, Steven W. Mes, Thomas Klausch et al.
JCI Insight
Cancer Genomics and Diagnostics
article

Diagnosis of head and neck cancer by AI-based tumor-educated platelet RNA profiling of liquid biopsies

Johannes A. Langendijk, Robert Paul Takes, Steven W. Mes, Thomas Klausch, Myron G. Best, Elisabeth Bloemena, Jos B. Poell, Sjors G. J. G. In ‘t Veld, Edward P. Post, Irma M. Verdonck‐de Leeuw, Robert J. Baatenburg de Jong, C. René Leemans, C.H.J. Terhaard, Niels E. Wondergem, Ruud H. Brakenhoff, Femke Lamers, Wessel N. van Wieringen, Thomas Würdinger
article en

Abstract

Over 95% of head and neck cancers are squamous cell carcinoma (HNSCC). HNSCC is mostly diagnosed late, causing a poor prognosis despite the application of invasive treatment protocols. Tumor-educated platelets (TEPs) have been shown to hold promise as a molecular tool for early cancer diagnosis. We sequenced platelet mRNA isolated from blood of 101 patients with HNSCC and 101 propensity-score matched noncancer controls. Two independent machine learning classification strategies were employed using a training and validation approach to identify a cancer predictor: a particle swarm optimized support vector machine (PSO-SVM) and a least absolute shrinkage and selection operator (LASSO) logistic regression model. The best performing PSO-SVM predictor consisted of 245 platelet transcripts and reached a maximum area under the curve (AUC) of 0.87. For the LASSO-based prediction model, 1,198 mRNAs were selected, resulting in a median AUC of 0.84, independent of HPV status. Our data show that TEP RNA classification by different AI tools is promising in the diagnosis of HNSCC.

JCI InsightVol. 11(2)
Netherlands Institute for Neuroscience (NL), University Medical Center Groningen (NL), Radboud University Nijmegen (NL), Dutch Cancer Society (NL), Erasmus MC (NL), Radboud University Medical Center (NL), Academic Center for Dentistry Amsterdam (NL), University Medical Center Utrecht (NL), Amsterdam Neuroscience (NL), Center for Translational Molecular Medicine (NL), Amsterdam University Medical Centers (NL), Cancer Center Amsterdam (NL), Vrije Universiteit Amsterdam (NL), Erasmus University Rotterdam (NL)
Openalex Percentile: Top 54%
Cancer Genomics and Diagnostics
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.