Abstract
Recent neuroimaging studies have indicated that abnormalities in brain structure and function may play an important role in the etiology of lifelong premature ejaculation (LPE). LPE patients have exhibited aberrant cortical structure, altered brain network function and abnormal brain activation in response to erotic pictures. However, it remains unclear whether resting-state whole brain functional connectivity (FC) is altered in LPE patients. Machine learning analysis has the advantage of screening the best classification features from high-throughput data (such as FC), which has the potential to identify the pathophysiological targets of disease by establishing classification indicators for patients and healthy controls (HCs). Therefore, the supported vector machine based classification model using FC as features was used in the present study to confirm the most specific FCs that distinguish LPE patients from healthy controls. After feature selection, the remained features were used to build the classification model, with an accuracy 0.85 ± 0.14, sensitivity of 0.92 ± 0.18, specificity of 0.72 ± 0.30, and recall index of 0.85 ± 0.17 across 1000 testing groups (100 times 10-folds cross validation). After that, two-sample t-tests with family-wise error correction were used to compare these features that occur more than 500 times during training steps between LPE patients and HCs. Four FCs, (1) between left medial part of orbital frontal cortex (mOFC) and right mOFC, (2) between the left rectus and right postcentral gyrus, (3) between the right insula and left pallidum, and (4) between the right middle part of temporal pole and right inferior part of temporal gyrus showed significant group difference. These results demonstrate that resting-state brain FC might be a discriminating feature to distinguish LPE patients from HCs. These classification features, especially the FC between bilateral mOFC, provide underlying abnormal central functional targets in LPE etiology, which offers a novel alternative target for future intervention in LPE treatment.
Highlights
In recent years, more and more neuroimaging studies have found that the etiology of sexual function dysfunction may be related to brain abnormalities, including brain structure, and functional aberrance (Zhao et al, 2015a,b; Chen et al, 2017; Jin et al, 2017; Li et al, 2018)
Our results provide more novel functional connectivity (FC)-derived indicators through a strategy of classification research to understand the potential abnormalities of brain function in lifelong premature ejaculation (LPE) patients
The classification algorithm in machine learning is useful for exploring the best classification features from high-throughput information, in which multivariate decoding algorithms like supported vector machine are trained on a portion of the data by weighting all connections in order to separate the known clinical status from healthy controls (HCs), rather than testing each connection independently for group differences
Summary
More and more neuroimaging studies have found that the etiology of sexual function dysfunction may be related to brain abnormalities, including brain structure, and functional aberrance (Zhao et al, 2015a,b; Chen et al, 2017; Jin et al, 2017; Li et al, 2018). Classifiers based on brain structure or brain function features have been used to distinguish psychiatric patients from healthy people, to distinguish different subtypes of patients, and to predict remission and non-remission when evaluating therapeutic effects (Fu et al, 2008; Grotegerd et al, 2014; Redlich et al, 2016; Du et al, 2018). These classification features offer useful insight for detecting the biological mechanisms of diseases. A recent study investigating the brain mechanism of venous erectile dysfunction used machine learning classification to distinguish patients from healthy controls, and revealed more various white matter-derived indices that might underlie imaging targets related to the neurobiological etiology of venous erectile dysfunction (Li et al, 2018)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
