Acute coronary syndromes (ACS) are a leading cause of deaths worldwide, yet the diagnosis and treatment of this group of diseases represent a significant challenge for clinicians. The epidemiology of ACS is extremely complex and the relationship between ACS and patient risk factors is typically non-linear and highly variable across patient lifespan. Here, we aim to uncover deeper insights into the factors that shape ACS outcomes in hospitals across four Arabian Gulf countries. Further, because anemia is one of the most observed comorbidities, we explored its role in the prognosis of most prevalent ACS in-hospital outcomes (mortality, heart failure, and bleeding) in the region. We used a robust multi-algorithm interpretable machine learning (ML) pipeline, and 20 relevant risk factors to fit predictive models to 4,044 patients presenting with ACS between 2012 and 2013. We found that in-hospital heart failure followed by anemia was the most important predictor of mortality. However, anemia was the first most important predictor for both in-hospital heart failure, and bleeding. For all in-hospital outcome, anemia had remarkably non-linear relationships with both ACS outcomes and patients' baseline characteristics. With minimal statistical assumptions, our ML models had reasonable predictive performance (AUCs > 0.75) and substantially outperformed commonly used statistical and risk stratification methods. Moreover, our pipeline was able to elucidate ACS risk of individual patients based on their unique risk factors. Fully interpretable ML approaches are rarely used in clinical settings, particularly in the Middle East, but have the potential to improve clinicians' prognostic efforts and guide policymakers in reducing the health and economic burdens of ACS worldwide.