首页|Chongqing University Reports Findings in Machine Learning (Functional near-infra red spectroscopy-based diagnosis support system for distinguishing between mild and severe depression using machine learning approaches)
Chongqing University Reports Findings in Machine Learning (Functional near-infra red spectroscopy-based diagnosis support system for distinguishing between mild and severe depression using machine learning approaches)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating from Chongqing, P eople’s Republic of China, by NewsRx correspondents, research stated, “Early dia gnosis of depression is crucial for effective treatment. Our study utilizes func tional near-infrared spectroscopy (fNIRS) and machine learning to accurately cla ssify mild and severe depression, providing an objective auxiliary diagnostic to ol for mental health workers.” Our news editors obtained a quote from the research from Chongqing University, “ Develop prediction models to distinguish between severe and mild depression usin g fNIRS data. We collected the fNIRS data from 140 subjects and applied a comple te ensemble empirical mode decomposition with an adaptive noise-wavelet threshol d combined denoising method (CEEMDAN-WPT) to remove noise during the verbal flue ncy task. The temporal features (TF) and correlation features (CF) from 18 prefr ontal lobe channels of subjects were extracted as predictors. Using recursive fe ature elimination with cross-validation, we identified optimal TF or CF and exam ined their role in distinguishing between severe and mild depression. Machine le arning algorithms were used for classification. The combination of TF and CF as inputs for the prediction model yielded higher classification accuracy than usin g either TF or CF alone. Among the prediction models, the SVM-based model demons trates excellent performance in nested cross-validation, achieving an accuracy r ate of 92.8%.”
ChongqingPeople’s Republic of ChinaA siaCyborgsDiagnostics and ScreeningEmerging TechnologiesHealth and Medic ineMachine Learning
NETL
NSTL
