In the study, Koo et. al analyzed the value and ability of a type of A.I detention technology (AI-QCPHA) to identify hemodynamic and plaque characteristics of possible ACS (Acute coronary syndrome) cases. Patients that underwent a CTA test (Coronary Computed Tomography Angiography) at least 3 months to 1 year from the start of the ACS study were selected for this study. From data based on given ICA (invasive coronary angiography) and CTA imaging exam, every found lesion from each patient was sorted into two groups: culprit and non culprit. A standardization data set (Coronary Artery Disease Reporting and Data System) for high-risk plaque evaluation (lesions with ≥2 APCs (adverse plaque characteristics)) was used as a reference. This reference document was compared to the same model with additional AI-QCPHA elements. Out of 351 patients in total (average age of 65.9±11.7 years with 223 patients presenting myocardial infarction issues), 243 patients were sorted in the derivation while 108 in the validation group. From the results, the most effective AI-QCPHA features (using data from the derivation cohort) included plaque burden and total volume, fractional flow reverse in lesion, and average percent total myocardial blood flow. Overall, as evident by the data collected in the both the derivation (AUC: 0.86 vs 0.76; P < 0.001) and validation cohorts (AUC: 0.84 vs 0.78; P < 0.001), the AI-QCPHA software showed a higher level of predictability when compared to the reference data.