Abstract Body (Do not enter title and authors here): Introduction: Over the past decade, there has been increasing recognition of Ischemia with No Obstructive Coronary Arteries (INOCA) and myocardial infarction with No Obstructive Coronary Arteries (MINOCA) as a significant, lethal portion of the coronary heart disease (CHD) spectrum. Unfortunately, standard angiographic based diagnostic approaches are insensitive to its presence while other more sensitive approaches that include invasive physiologic and provocation testing have challenges to implementation. We believe the epigenetic approaches may provide a more tractable alternative. Specifically, we have shown that artificial intelligence (AI) guided integrated genetic-epigenetic tests can detect both anatomically and broadly defined CHD. Hypothesis: However, whether this approach can specifically detect non-obstructive pathologies such as INOCA and MINOCA is not known. Methods: To test that possibility, we conducted methylation sensitive digital PCR (MSdPCR) assessment of the six CpG sites included in the PrecisionCHD diagnostic test in 268 acute coronary syndrome (ACS) subjects admitted for whom Duke Jeopardy Scores (DJS), a previously validated measure of coronary artery obstruction, were available, then analyzed the data. Results: Average DJS value of these 268 subjects was 3.7 ± 2.8, with 43 subjects, including 27 with a myocardial infarction (MI), have DJS values of 0 (i.e., less than 50% obstruction in all major vessels). Least Square regression showed that a simple model consisting of age (p<0.004), sex (p<0.009) and both cg21161138 (p<0.006, AHRR) and cg04988978 (MPO, p<0.08) methylation predicting DJS (Adj R²=0.06; p<0.0003). Nominal logistic regression analyses using data from previously collected control subjects shows that DNA methylation data from all six MSdPCR sites effectively discriminated age matched “no CHD” controls from those with DJS values of 0 and MI (n=27) and those with DJS values of 0 presenting for angina in the context of existing CHD (n=16) with the area under the curve (AUC) for both sets of analyses being >0.95. Conclusions: We conclude that epigenetic approaches are viable tools for detecting INOCA-like pathologies. Furthermore, because these AI guided epigenetic approaches are also scalable and provide personalized information, these findings support the use of this technology to assist with the diagnosis of INOCA.