EN | UA
EN | UA

Help Support

Back

Multivariate machine learning approach to estimate the prognosis of primary dysmenorrhea

Multivariate machine learning approach to estimate the prognosis of primary dysmenorrhea Multivariate machine learning approach to estimate the prognosis of primary dysmenorrhea
Multivariate machine learning approach to estimate the prognosis of primary dysmenorrhea Multivariate machine learning approach to estimate the prognosis of primary dysmenorrhea

What's new?

The abnormal pattern of GM volume plays a role in the process of future menstrual pain and may predict intensity of pain.

The grey matter volume may be used as an inherent imaging marker for the evaluation of menstrual pain intervention, as the GM volume predict the primary dysmenorrhea (PDM) patients during the pain-free phase and the fluctuations in the intensity of menstrual pain explained the investigators of the Center for Brain Imaging, Xidian University.

A total of 60 PDM patients and 54 matched healthy controls (HC) went through the pelvic and head MRI scans to measure myometrium apparent diffusion coefficient (ADC) and GM volume during their periovulatory phase.  The participants completed the questionnaire. The classification model was developed using a support vector machine algorithm and the significance of model performance by the permutation test. Multiple regression analysis was utilized to evaluate the relationship between intensity of menstrual pain and discriminative features.

A total of 75.44% of patients were correctly classified, with 83.33% recognized with PDM, based on the results of brain-based classification. The demographics and myometrium ADC-based categorizations were unable to clear the permutation tests. Further, the regression analysis exhibited 29.37% of the variance in pain intensity for myometrium ADC and demographical indicators. After reverting out these factors, GM characteristics demonstrated 60.33% of the remaining variance.

Source:

Pain

Article:

Whole brain structural MRI based classification of primary dysmenorrhea in pain-free phase: a machine learning study.

Authors:

Tao Chen et al.

Comments (0)

You want to delete this comment? Please mention comment Invalid Text Content Text Content cannot me more than 1000 Something Went Wrong Cancel Confirm Confirm Delete Hide Replies View Replies View Replies en
Try: