首页|Tongji University School of Medicine Reports Findings in Machine Learning (Machi ne learning based on functional and structural connectivity in mild cognitive im pairment)
Tongji University School of Medicine Reports Findings in Machine Learning (Machi ne learning based on functional and structural connectivity in mild cognitive im pairment)
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 out of Shanghai, People's Rep ublic of China, by NewsRx editors, research stated, "Alzheimer's disease (AD) is a chronic, degenerative neurological disorder characterized by progressive cogn itive decline and mental behavioral abnormalities. Mild cognitive impairment (MC I) is regarded as a transitional stage in the progression from normal elderly in dividuals to patients with AD." Our news journalists obtained a quote from the research from the Tongji Universi ty School of Medicine, "While studies have identified abnormalities in brain con nectivity in patients with MCI, including functional and structural connectivity, accurately identifying patients with MCI in clinical screening remains challen ging. We hypothesized that utilizing machine learning (ML) based on both functio nal and structural connectivity could yield meaningful results in distinguishing between patients with MCI and normal elderly individuals, so as to provide valu able information for early diagnosis and precise evaluation of patients with MCI . Following clinical criteria, we recruited 32 patients with MCI for the patient group, and 32 normal elderly individuals for the control group. All subjects un derwent examinations for resting-state functional magnetic resonance imaging (rs -fMRI) and diffusion tensor imaging (DTI). Subsequently, significant functional and structural connectivity features were selected and combined with a support v ector machine for classification of the patient and control groups. We observed significantly different functional connectivity in the frontal lobe and putamen between the MCI group and normal controls. The results based on functional conne ctivity features demonstrated a classification accuracy of 71.88% and an area under the curve (AUC) value of 0.78. In terms of structural connecti vity, we found that decreased fractional anisotropy in patients with MCI was sig nificantly associated with Montreal Cognitive Assessment scores, specifically in regions such as the precuneus and cingulate gyrus. The classification results u sing the structural connectivity feature yielded an accuracy of 92.19% and an AUC value of 0.99. Lastly, combining functional and structural connectivi ty features resulted in a classification accuracy and AUC value of 93.75 % and 0.99, respectively. In this study, we demonstrated a high classification per formance, underscoring the potential of both brain functional and structural con nectivity in distinguishing patients with MCI from normal elderly individuals."
ShanghaiPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
