Machine Learning–Driven Models to Predict Prognostic Outcomes in Patients Hospitalized With Heart Failure Using Electronic Health Records: Retrospective Study

Background With the prevalence of cardiovascular diseases increasing worldwide, early prediction and accurate assessment of heart failure (HF) risk are crucial to meet the clinical demand. Objective Our study objective was to develop machine learning (ML) models based on real-world electronic health records to predict 1-year in-hospital mortality, use of positive inotropic agents, and 1-year all-cause readmission rate. Methods For this single-center study, we recruited patients with newly diagnosed HF hospitalized between December 2010 and August 2018 at the First Affiliated Hospital of Dalian Medical University (Liaoning Province, China). The models were constructed for a population set (90:10 split of data set into training and test sets) using 79 variables during the first hospitalization. Logistic regression, support vector machine, artificial neural network, random forest, and extreme gradient boosting models were investigated for outcome predictions. Results Of the 13,602 patients with HF enrolled in the study, 537 (3.95%) died within 1 year and 2779 patients (20.43%) had a history of use of positive inotropic agents. ML algorithms improved the performance of predictive models for 1-year in-hospital mortality (areas under the curve [AUCs] 0.92-1.00), use of positive inotropic medication (AUCs 0.85-0.96), and 1-year readmission rates (AUCs 0.63-0.96). A decision tree of mortality risk was created and stratified by single variables at levels of high-sensitivity cardiac troponin I (<0.068 μg/L), followed by percentage of lymphocytes (<14.688%) and neutrophil count (4.870×109/L). Conclusions ML techniques based on a large scale of clinical variables can improve outcome predictions for patients with HF. The mortality decision tree may contribute to guiding better clinical risk assessment and decision making.

Machine Learning–Driven Models to Predict Prognostic Outcomes in Patients Hospitalized With Heart Failure Using Electronic Health Records: Retrospective Study (Preprint)

BACKGROUND With the prevalence of cardiovascular diseases increasing worldwide, early prediction and accurate assessment of heart failure (HF) risk are crucial to meet the clinical demand. OBJECTIVE Our study objective was to develop machine learning (ML) models based on real-world electronic health records to predict 1-year in-hospital mortality, use of positive inotropic agents, and 1-year all-cause readmission rate. METHODS For this single-center study, we recruited patients with newly diagnosed HF hospitalized between December 2010 and August 2018 at the First Affiliated Hospital of Dalian Medical University (Liaoning Province, China). The models were constructed for a population set (90:10 split of data set into training and test sets) using 79 variables during the first hospitalization. Logistic regression, support vector machine, artificial neural network, random forest, and extreme gradient boosting models were investigated for outcome predictions. RESULTS Of the 13,602 patients with HF enrolled in the study, 537 (3.95%) died within 1 year and 2779 patients (20.43%) had a history of use of positive inotropic agents. ML algorithms improved the performance of predictive models for 1-year in-hospital mortality (areas under the curve [AUCs] 0.92-1.00), use of positive inotropic medication (AUCs 0.85-0.96), and 1-year readmission rates (AUCs 0.63-0.96). A decision tree of mortality risk was created and stratified by single variables at levels of high-sensitivity cardiac troponin I (<0.068 μg/L), followed by percentage of lymphocytes (<14.688%) and neutrophil count (4.870×10⁹/L). CONCLUSIONS ML techniques based on a large scale of clinical variables can improve outcome predictions for patients with HF. The mortality decision tree may contribute to guiding better clinical risk assessment and decision making.

Positive Inotropic Agents in Myocardial Ischemia–Reperfusion Injury

Positive inotropic agents should be used judiciously when managing surgical patients with acute myocardial ischemia–reperfusion injury, as use of these inotropes is not without potential adverse effects.

Acute heart failure: vasoactive agents – does it matter?

Acute heart failure (AHF) is defined as the rapid onset of symptoms se­ condary to abnormal cardiac function. It is a syndrome and has a va­ riety of potential etiologies. AHF is a very polymorphic conception and can be related with abnormalities in cardiac rhythm, systolic or diastolic dysfunction or preload and afterload mismatch. The cornerstone of ma­ nagement includes therapy directed towards the underlying cause of heart failure. On the other hand, if the underlying cause is irreversible – a heart assist device or even heart transplantation may be needed. Therefore, while awaiting their availability, vital organ perfusion remains crucial. In these settings, intravenous cardio-/vaso- active agents are necessary. With few exceptions, most vasopressor and positive inotropic agents are symphatomimetic amines that exert their action by binding and sti­ mulating adrenergic receptors. They are powerful drugs with a considerable potential for toxicity. Vasopressor and inotropic support in case of AHF helps to win the time until a more definitive treatment becomes available. Therefore, AHF management must be directed to establish and eliminate deteriorational factors, however, not the correction of particular hemodynamic parameters.