RESUMEN
The Emergency Heart Failure Mortality Risk Grade (EHMRG) can predict short-term mortality in patients admitted for acute heart failure (AHF) in the emergency department (ED). This paper aimed to evaluate if TAPSE/PASp, an echocardiographic marker of ventricular desynchronization, can improve in-hospital death prediction in patients at moderate-to-high risk, according to EHMRG score classification. From 1 January 2018 to 30 December 2019, we retrospectively enrolled all the consecutive subjects admitted to our Internal Medicine Department for AHF from the ED. We performed bedside echocardiography within the first 24 h of admission. We evaluated EHMRG and NYHA in the ED, days of admission in Internal Medicine, and in-hospital mortality. We assessed cutoffs with ROC curve analysis and survival with Kaplan-Meier and Cox regression. We obtained a cohort of 439 subjects; 10.3% underwent in-hospital death. Patients with normal TAPSE/PASp in EHMRG Classes 4, 5a, and 5b had higher survival rates (100%, 100%, and 94.3%, respectively), while subjects with pathologic TAPSE/PASp had lower survival rates (81.8%, 78.3%, and 43.4%, respectively) (p < 0.0001, log-rank test). TAPSE/PASp, an echocardiographic marker of ventricular desynchronization, can further stratify the risk of in-hospital death evaluated by EHMRG.
RESUMEN
Critically ill patients affected by atrial fibrillation are at high risk of adverse events: however, the actual risk stratification models for haemorrhagic and thrombotic events are not validated in a critical care setting. With this paper we aimed to identify, adopting topological data analysis, the risk factors for therapeutic failure (in-hospital death or intensive care unit transfer), the in-hospital occurrence of stroke/TIA and major bleeding in a cohort of critically ill patients with pre-existing atrial fibrillation admitted to a stepdown unit; to engineer newer prediction models based on machine learning in the same cohort. We selected all medical patients admitted for critical illness and a history of pre-existing atrial fibrillation in the timeframe 01/01/2002-03/08/2007. All data regarding patients' medical history, comorbidities, drugs adopted, vital parameters and outcomes (therapeutic failure, stroke/TIA and major bleeding) were acquired from electronic medical records. Risk factors for each outcome were analyzed adopting topological data analysis. Machine learning was used to generate three different predictive models. We were able to identify specific risk factors and to engineer dedicated clinical prediction models for therapeutic failure (AUC: 0.974, 95%CI: 0.934-0.975), stroke/TIA (AUC: 0.931, 95%CI: 0.896-0.940; Brier score: 0.13) and major bleeding (AUC: 0.930:0.911-0.939; Brier score: 0.09) in critically-ill patients, which were able to predict accurately their respective clinical outcomes. Topological data analysis and machine learning techniques represent a concrete viewpoint for the physician to predict the risk at the patients' level, aiding the selection of the best therapeutic strategy in critically ill patients affected by pre-existing atrial fibrillation.
