Classification tree obtained by artificial intelligence for the prediction of heart failure after acute coronary syndromes. / Árboles de clasificación obtenidos mediante inteligencia artificial para la predicción de insuficiencia cardiaca tras el síndrome coronario agudo.

BACKGROUND: Coronary heart disease is the leading cause of heart failure (HF), and tools are needed to identify patients with a higher probability of developing HF after an acute coronary syndrome (ACS). Artificial intelligence (AI) has proven to be useful in identifying variables related to the development of cardiovascular complications. METHODS: We included all consecutive patients discharged after ACS in two Spanish centers between 2006 and 2017. Clinical data were collected and patients were followed up for a median of 53months. Decision tree models were created by the model-based recursive partitioning algorithm. RESULTS: The cohort consisted of 7,097 patients with a median follow-up of 53months (interquartile range: 18-77). The readmission rate for HF was 13.6% (964 patients). Eight relevant variables were identified to predict HF hospitalization time: HF at index hospitalization, diabetes, atrial fibrillation, glomerular filtration rate, age, Charlson index, hemoglobin, and left ventricular ejection fraction. The decision tree model provided 15 clinical risk patterns with significantly different HF readmission rates. CONCLUSIONS: The decision tree model, obtained by AI, identified 8 leading variables capable of predicting HF and generated 15 differentiated clinical patterns with respect to the probability of being hospitalized for HF. An electronic application was created and made available for free.

Management of myocardial infarction in the elderly. Insights from Spanish Minimum Basic Data Set.

BACKGROUND: We aimed to assess the impact of implementation of reperfusion networks, the type of hospital and specialty of the treating physician on the management and outcomes of ST segment elevation myocardial infarction in patients aged ⩾75 years. METHODS: We analysed data from the Minimum Basic Data Set of the Spanish public health system, assessing hospital discharges between 2004 and 2013. Discharges were distributed in three groups depending on the clinical management: percutaneous coronary intervention, thrombolysis or no reperfusion. Primary outcome measure was all cause in-hospital mortality. For risk adjustment, patient comorbidities were identified for each index hospitalization. RESULTS: We identified 299,929 discharges, of whom 107,890 (36%) were in-patients aged ⩾75 years. Older patients had higher prevalence of comorbidities, were less often treated in high complexity hospitals and were less frequently managed by cardiologists ( p<0.001). Both percutaneous coronary intervention and fibrinolysis were less often performed in elderly patients ( p<0.001). A progressive increase in the rate of percutaneous coronary intervention was observed in the elderly across the study period (from 17% in 2004 to 45% in 2013, p<0.001), with a progressive reduction of crude mortality (from 23% in 2004 to 19% in 2013, p<0.001). Adjusted analysis showed an association between being treated in high complexity hospitals, being treated by cardiologists and lower in-hospital mortality ( p <0.001). CONCLUSIONS: Elderly patients with ST segment elevation myocardial infarction are less often managed in high complexity hospitals and less often treated by cardiologists. Both factors are associated with higher in-hospital mortality.

Impact on Mortality of Different Network Systems in the Treatment of ST-segment Elevation Acute Myocardial Infarction. The Spanish Experience.

INTRODUCTION AND OBJECTIVES: To analyze the association between the development of network systems of care for ST-segment elevation myocardial infarction (STEMI) in the autonomous communities (AC) of Spain and the regional rate of percutaneous coronary intervention (PCI) and in-hospital mortality. METHODS: From 2003 to 2012, data from the minimum basic data set of the Spanish taxpayer-funded health system were analyzed, including admissions from general hospitals. Diagnoses of STEMI and related procedures were codified by the International Diseases Classification. Discharge episodes (n = 302 471) were distributed in 3 groups: PCI (n = 116 621), thrombolysis (n = 46 720), or no reperfusion (n = 139 130). RESULTS: Crude mortality throughout the evaluation period was higher for the no-PCI or thrombolysis group (17.3%) than for PCI (4.8%) and thrombolysis (8.6%) (P < .001). For the aggregate of all communities, the PCI rate increased (21.6% in 2003 vs 54.5% in 2012; P < .001) with a decrease in risk-standardized mortality rates (10.2% in 2003; 6.8% in 2012; P < .001). Significant differences were observed in the PCI rate across the AC. The development of network systems was associated with a 50% increase in the PCI rate (P < .001) and a 14% decrease in risk-standardized mortality rates (P < .001). CONCLUSIONS: From 2003 to 2012, the PCI rate in STEMI substantially increased in Spain. The development of network systems was associated with an increase in the PCI rate and a decrease in in-hospital mortality.

Patterns of inpatient care for acute myocardial infarction and 30-day, 3-month and 1-year cardiac diseases readmission rates in Spain.

BACKGROUND: Acute myocardial infarction (AMI) is a common cause of hospital discharges and readmissions. Readmissions may indicate poor patient care and avoidable health expenditure, being key in quality improvement strategies. Our aim was to analyse cardiac diseases (CDs) readmissions in patients with AMI in Spain. METHODS: A retrospective analysis of 33,538 hospital discharges with AMI being the "principal diagnosis" at hospitals of the Spanish National Health System in 2012 was performed using administrative data. We developed a logistic regression model and calculated 30-day, 3-month and 1-year CDs risk-standardized readmission rates (RSRRs) using a multivariate mixed model. RESULTS: Variables of the model (AMI location, age, previous angina pectoris/myocardial infarction or acute coronary syndrome, chronic kidney disease, rheumatic valvular disease, diabetes mellitus, vascular disease, female sex, chronic pulmonary disease, and anemia) were able to predict 30-day, 3-month and 1-year readmission rates and RSRRs after AMI (5.4%, 9.3% and 20.2%, respectively). For RSRRs the area under the ROC curve was 0.74 (p=0.0037), 0.77 (p=0.0041), and 0.73 (p=0.0025) for 1, 3months and 1-year readmission rate, respectively. Angioplasty, cardiology as the medical unit responsible for the discharge and a higher volume of activity (>204 AMI) were all significantly (p<0.001) associated with lower mortality, risk of development of heart failure and RSRRs. CONCLUSIONS: Angioplasty, cardiology as the medical unit responsible for the discharge and a higher volume of activity explain variability in CDs readmission rates after AMI, which can have implications for strategies to reduce readmissions rates.