No abstract

Aims Of all spontaneous bleeding complications in patients with acute myocardial infarction (MI), upper gastrointestinal bleeding (UGIB) is common and of specific interest since it could be prevented by several prophylactic measures. We aimed to determine the incidence, associated outcomes, and predictors of UGIB following acute MI. Methods and results All patients with acute MI enrolled in the SWEDEHEART (Swedish Web-system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies) registry from January 2007 to June 2016 and discharged alive on any antithrombotic therapy (n = 149 477) were followed regarding UGIB for 1 year. Associated outcomes were determined by Cox proportional hazards regression with UGIB as a time-dependent covariate, adjusting for baseline characteristics, invasive treatment, and medical treatment at discharge. Predictors of UGIB were determined by logistic regression and machine learning models. At 1 year, UGIB had occurred in 2230 patients (cumulative incidence 1.5%) and was significantly associated with an increased risk of all-cause death [hazard ratio (HR) 2.86, 95% confidence interval (CI) 2.58–3.16] and stroke (HR 1.80, 95% CI 1.32–2.45) but not with recurrent MI (HR 1.17, 95% CI 0.97–1.42). The most important predictors of UGIB were haemoglobin, age, systolic blood pressure, blood glucose, smoking status, previous upper gastrointestinal bleeding, and antithrombotic and gastroprotective treatment. Conclusion After acute MI, readmission because of UGIB is common and significantly associated with poor prognosis. By using machine learning in addition to traditional logistic regression, new predictors of UGIB, such as blood glucose and smoking status, were identified.

Abstract. Sarajlic P, Frid en C, Lund LH, Manouras A, Venkateshvaran A, Larsson SC, Nordgren B, Opava CH, Lundberg IE, B€ ack M