Blood-based FTIR-ATR spectroscopy coupled with extreme gradient boosting for the diagnosis of type 2 diabetes
Peiwen Guang, Wendong Huang, Guo Liu, Xinhao Yang, Furong Huang, Maoxun Yang, Wangrong Wen, Li Li
Abstract
Timely diagnosis of type 2 diabetes and early intervention and treatment of it are important for controlling metabolic disorders, delaying and reducing complications, reducing mortality, and improving quality of life. Type 2 diabetes was diagnosed by Fourier transform mid-infrared (FTIR) attenuated total reflection (ATR) spectroscopy in combination with extreme gradient boosting (XGBoost). Whole blood FTIR-ATR spectra of 51 clinically diagnosed type 2 diabetes and 55 healthy volunteers were collected. For the complex composition of whole blood and much spectral noise, Savitzky-Golay smoothing was first applied to the FTIR-ATR spectrum. Then PCA was used to eliminate redundant data and got the best number of principle components. Finally, the XGBoost algorithm was used to discriminate the type 2 diabetes from healthy volunteers and the grid search algorithm was used to optimize the relevant parameters of the XGBoost model to improve the robustness and generalization ability of the model. The sensitivity of the optimal XGBoost model was 95.23% (20/21), the specificity was 96.00% (24/25), and the accuracy was 95.65% (44/46). The experimental results show that FTIR-ATR spectroscopy combined with XGBoost algorithm can diagnose type 2 diabetes quickly and accurately without reagents.