Prediction of IDH mutation status of glioma based on terahertz spectral data

[Display omitted] •THz spectroscopy was applied to the analysis of IDH mutation status in glioma.•Six different THz spectral parameters were calculated in the study.•IDH mutant and wildtype glioma had different THz characteristics.•The LASSO algorithm was used to screen THz features, the PCA analysis to reduce dimensionality, and the Random Forest algorithm to establish a prediction model.•This research conducted a preliminary study on the possibility of glioma biomarker prediction by terahertz technology, and established a prediction model with an AUC of 0.844. Gliomas are the most common type of primary tumor in the central nervous system in adults. Isocitrate dehydrogenase (IDH) mutation status is an important molecular biomarker for adult diffuse gliomas. In this study, we were aiming to predict IDH mutation status based on terahertz time-domain spectroscopy technology. Ninety-two frozen sections of glioma tissue from nine patients were included, and terahertz spectroscopy data were obtained. Through Least Absolute Shrinkage and Selection Operator (LASSO), Principal component analysis (PCA), and Random forest (RF) algorithms, a predictive model for predicting IDH mutation status in gliomas was established based on the terahertz spectroscopy dataset with an AUC of 0.844. These results indicate that gliomas with different IDH mutation status have different terahertz spectral features, and the use of terahertz spectroscopy can establish a predictive model of IDH mutation status, providing a new way for glioma research.