Coronary microvascular disease (CMD) is a common form of heart disease in postmenopausal women. It is not due to plaque formation but dysfunction of microvessels that feed the heart muscle. The majority of the patients do not receive a proper diagnosis, are discharged prematurely and must go back to the hospital with persistent symptoms. Because of the lack of diagnostic biomarkers, in the current study, we focused on identifying novel circulating biomarkers of CMV that could potentially be used for developing a diagnostic test. We hypothesized that plasma metabolite composition is different for postmenopausal women with no heart disease, CAD, or CMD. A total of 70 postmenopausal women, 26 healthy individuals, 23 individuals with CMD and 21 individuals with CAD were recruited. Their full health screening and tests were completed. Basic cardiac examination, including detailed clinical history, additional disease and prescribed drugs, were noted. Electrocardiograph, transthoracic echocardiography and laboratory analysis were also obtained. Additionally, we performed full metabolite profiling of plasma samples from these individuals using gas chromatography-mass spectrometry (GC–MS) analysis, identified and classified circulating biomarkers using machine learning approaches. Stearic acid and ornithine levels were significantly higher in postmenopausal women with CMD. In contrast, valine levels were higher for women with CAD. Our research identified potential circulating plasma biomarkers of this debilitating heart disease in postmenopausal women, which will have a clinical impact on diagnostic test design in the future.
Data mining techniques with machine learning algorithm to predict patients of heart disease
