Classification models using circulating neutrophil transcripts can detect unruptured intracranial aneurysm

Abstract

Background Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n = 94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n = 40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 9 IA-associated genes was used to verify gene expression in a subset of 49 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC) = 0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 7 of 9 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.

Gene expression profiles of ischemic stroke clots retrieved by mechanical thrombectomy are associated with disease etiology

“…We performed differential gene expression analysis between the samples of different TOAST classes in edgeR, as previously reported 11 12. In edgeR, we estimated common dispersion for all genes and performed differential expression testing on each transcript using an exact test analogous to Fisher’s exact test.…”

Isolation of RNA from Acute Ischemic Stroke Clots Retrieved by Mechanical Thrombectomy

“…Transcriptome profiling is a powerful tool for revealing expression patterns that are associated with complex diseases [9,15,16], such as stroke. The ability to extract satisfactory RNA from blood clots for downstream applications has been proven difficult with traditional extraction methods.…”

“…We performed a quantitative reverse transcription-polymerase chain reaction (RT-qPCR) as previously described [7][8][9]. Primers were created for three housekeeping genes: GAPDH, GPI, and HPRT1.…”

A Two-Gene-Based Diagnostic Signature for Ruptured Intracranial Aneurysms

“…Circulating neutrophils were shown to carry a signature related to IAs, providing a possibility to diagnose patients with IAs based on biomarkers in peripheral blood (23). Based on the circulating neutrophil transcriptome data, Meng et al constructed a model to predict unruptured IAs (24); this model was further improved by the integration of machine learning approaches and large cohorts (25). Quan et al reported that the expression of F2-isoprostanes and F4-neuroprostanes in the plasma of patients with IAs is significantly upregulated compared with healthy subjects, and these may be considered potential biomarkers for IA development (26).…”