Norepinephrine use in cardiogenic shock patients is associated with increased 30 day mortality

Comparison of machine learning and nomogram to predict 30-day in-hospital mortality in patients with acute myocardial infarction combined with cardiogenic shock: a retrospective study based on the eICU-CRD and MIMIC-IV databases

BACKGROUND

To evaluate the predictive utility of machine learning and nomogram in predicting in-hospital mortality in patients with acute myocardial infarction complicated by cardiogenic shock (AMI-CS), and to visualize the model results in order to analyze the impact of these predictors on the patients' prognosis.

METHODS

A retrospective analysis was conducted on 332 adult patients who were diagnosed with AMI-CS and admitted to the ICU for the first time within the eICU Collaborative Research Database (eICU-CRD). AdaBoost, XGBoost, LightGBM, Random Forest and logistic regression nomogram were developed utilizing the random forest recursive elimination (RF-RFE) and least absolute shrinkage and selection operator (LASSO) algorithms for feature selection.

RESULTS

Compared to the machine learning models, the nomogram demonstrated superior predictive accuracy for mortality in patients with AMI-CS, with an AUC value of 0.869 (95% CI: 0.803, 0.883) and an F1 score of 0.897 for the internal test set of nomogram, and an AUC of 0.770 (95% CI: 0.702, 0.801) and an F1 score of 0.832 for the external validation set.

CONCLUSIONS

Nomogram enhance the interpretability and transparency of the models, leading to more reliable prognostic predictions for AMI-CS patients. This facilitates clinicians in making precise decisions, thereby enhancing patient prognosis.

Corticosteroids in Cardiogenic Shock: A Retrospective Analysis of the Medical Information Mart for Intensive Care-IV Database

IMPORTANCE

While corticosteroid administration in septic shock has been shown to result in faster shock reversal and lower short-term mortality, the role of corticosteroids in the management of cardiogenic shock (CS) remains unexplored.

OBJECTIVES

Determine the impact of corticosteroid administration on 90-day mortality (primary outcome) in patients admitted to a critical care unit with CS.

DESIGN, SETTING, AND PARTICIPANTS

In this retrospective cohort study, we used the critical care database of Medical Information Mart for Intensive Care-IV, and included all adult patients diagnosed with CS excluding repeated admissions, patients with adrenal insufficiency, those receiving baseline corticosteroids, and those requiring extracorporeal life support. We considered exposure based on receiving systemic corticosteroids from 6 hours before to 24 hours post-critical care admission.

MAIN OUTCOMES AND MEASURES

We calculated Cox proportional hazards using multivariate analysis for 90-day mortality (primary outcome). We also explored the association of corticosteroid use with hospital length of stay, ventilator-free days (VFDs), vasopressor-free days, ventilator-associated pneumonia, central-line-associated bloodstream infections, and hyperglycemia.

RESULTS

We included 2000 eligible patients, with 143 (7.2%) receiving systemic corticosteroids. Corticosteroid-treated patients were younger (67.7 vs. 71.2 yr; p = 0.006), had higher Sequential Organ Failure Assessment scores at baseline (9.4 vs. 7.8; p < 0.001), and more often required vasopressors (78% vs. 63%; p < 0.001), and invasive mechanical ventilation (73% vs. 45%; p < 0.001). Corticosteroid use was associated with increased 90-day mortality in multivariate analysis (hazard ratio, 1.60; 95% CI, 1.25-2.05) and fewer VFDs (2.8 d fewer; 95% CI, 0.35-5.26) with no effect on other secondary outcomes.

CONCLUSIONS AND RELEVANCE

Use of corticosteroids may be associated with increased mortality and a reduction in VFDs in patients admitted to critical care with CS. These findings suggesting potential harm of corticosteroids in CS might reflect unmeasured confounding and require corroboration through additional observational studies and ultimately randomized clinical trials.

Safety and efficacy of up to 60 h of iv istaroxime in pre-cardiogenic shock patients: Design of the SEISMiC trial

AIMS

Cardiogenic shock (CS) is linked to high morbidity and mortality rates, posing a challenge for clinicians. Interventions to improve tissue perfusion and blood pressure are crucial to prevent further deterioration. Unfortunately, current inotropes, which act through adrenergic receptor stimulation, are associated with malignant arrhythmias and poorer outcomes. Due to its unique mechanism of action, istaroxime should improve haemodynamics without adrenergic overactivation. The SEISMiC study is designed to examine the safety and efficacy (haemodynamic effect) of istaroxime administrated in pre-CS patients.

METHODS AND RESULTS

The SEISMiC study is a multinational, multicentre, randomized, double-blind, placebo-controlled safety and efficacy study with two parts (A and B). The study enrols patients hospitalized for decompensated heart failure (pre-CS, not related to myocardial ischaemia) with persistent hypotension [systolic blood pressure (SBP) 70-100 mmHg for at least 2 h] and clinically confirmed congestion, NT-proBNP ≥1400 pg/mL, and LVEF≤40%. Subjects must not have taken intravenous (iv) vasopressors, inotropes or digoxin in the past 6 h. Eligible patients are randomized to receive IV infusion of istaroxime (different doses and regimens in Parts A and B) or placebo for up to 60 h. Central haemodynamics, ECG Holter monitoring, cardiac ultrasound and biomarkers are recorded at predefined time points during the trial. The study's primary efficacy endpoint is the SBP area under the curve from baseline curve from baseline to 6 and 24 h in the combined SEISMiC Parts A and B population. Key secondary efficacy endpoints include haemodynamic, laboratory and clinical measures in SEISMiC B alone in the combined SEISMiC A and B studies.

CONCLUSIONS

The study results will contribute to our understanding of the role of istaroxime in pre-CS patients and potentially provide insight into the drug's haemodynamic effects and safety in this population.

Value of APACHE II, SOFA and CardShock scoring as predictive tools for cardiogenic shock: A single-centre pilot study

AIMS

The aim of this study was to determine the value of the Acute Physiology and Chronic Health Evaluation II (APACHE II), Sequential Organ Failure Assessment (SOFA) and CardShock scoring systems in predicting the risk of in-hospital, 30 day and 3 year mortality in patients with cardiogenic shock (CS).

METHODS

This was a single-centre observational study conducted between May 2016 and December 2017. Data from consecutive patients with CS admitted to the intensive cardiac care unit (ICCU) were included in the analysis.

RESULTS

The study group comprised 63 patients with CS {median age 71.0 [interquartile range (IQR), 59-82]; 42 men}: 32 patients with ischaemic and 31 with non-ischaemic aetiology. The median APACHE II, SOFA and CardShock scores were 13 (IQR, 9.9-19.0) points, 8.0 (IQR, 6.0-10.0) points and 3.0 (IQR, 2.0-5.0) points, respectively. The in-hospital, 30 day and 3 year mortality rates were 39.7%, 41.3% and 77.8%, respectively. APACHE II and SOFA scores were significantly higher in the group of patients who died at 30 days (P = 0.043 and P = 0.045, respectively). The CardShock score was higher in patients with CS who died in hospital (P = 0.007) and within 30 days (P = 0.004). No score was statistically significant for 3 year mortality. Area under the curve (AUC) analysis showed that the CardShock score had the highest value in predicting in-hospital and 30 day mortality relative to APACHE II and SOFA, with a cut-off score of 5 points [AUC: 0.70; 95% confidence interval (CI): 0.59-0.81; P = 0.001] and 4 points (AUC: 0.71; 95% CI: 0.60-0.82; P < 0.001), respectively. The Bayesian Weibull model demonstrated the utility of all scales in estimating short-term risk in patients with CS, with the impact of APACHE II and SOFA on patient life expectancy decreasing to a non-significant level at approximately 32 days and CardShock at 33 days. The forest plots derived from the Bayesian logistic regression analysis show significant estimated coefficients with 94% highest density interval (HDI) for in-hospital and 30 day mortality. The use of invasive or non-invasive ventilation, a higher heart rate and a less negative fluid balance showed an unfavourable prognosis. Survival was associated with being in the pre-CS class, with a higher glomerular filtration rate and a higher platelet count.

CONCLUSIONS

APACHE II and SOFA could be used for the risk stratification of patients with CS admitted to the ICCU. CardShock proved to be a more appropriate tool for assessing short-term prognosis in patients with CS of all aetiologies, suggesting that there is potential for its promotion for use in daily clinical practice.

Management of cardiogenic shock: state-of-the-art

The management of cardiogenic shock is an ongoing challenge. Despite all efforts and tremendous use of resources, mortality remains high. Whilst reversing the underlying cause, restoring/maintaining organ perfusion and function are cornerstones of management. The presence of comorbidities and preexisting organ dysfunction increases management complexity, aiming to integrate the needs of vital organs in each individual patient. This review provides a comprehensive overview of contemporary literature regarding the definition and classification of cardiogenic shock, its pathophysiology, diagnosis, laboratory evaluation, and monitoring. Further, we distill the latest evidence in pharmacologic therapy and the use of mechanical circulatory support including recently published randomized-controlled trials as well as future directions of research, integrating this within an international group of authors to provide a global perspective. Finally, we explore the need for individualization, especially in the face of neutral randomized trials which may be related to a dilution of a potential benefit of an intervention (i.e., average effect) in this heterogeneous clinical syndrome, including the use of novel biomarkers, artificial intelligence, and machine learning approaches to identify specific endotypes of cardiogenic shock (i.e., subclasses with distinct underlying biological/molecular mechanisms) to support a more personalized medicine beyond the syndromic approach of cardiogenic shock.

Clinical Effect of Norepinephrine Combined with Esmolol Treatment in Patients with Septic Shock and Its Impact on Prognosis

Objective

To unveil the influence of norepinephrine (NE) combined with esmolol treatment on cardiac function, hemodynamics, inflammatory factor levels, and prognosis in patients with septic shock.

Methods

Ninety-six patients with septic shock admitted to our hospital from January 2021 to June 2023 were retrospectively analyzed and divided into the control and observation groups according to the different treatment methods. The control group was treated with standard anti-infection and fluid resuscitation, followed by NE administration [with an infusion rate of 0.1-0.5 μg/(kg-min)]. The observation group was treated with esmolol [starting pumping rate of 50 μg/(kg-min) and adjusting the pumping rate according to the target heart rate] in combination with the control group. Changes in hemodynamic parameters, including heart rate, mean arterial pressure, central venous pressure, cardiac index, stroke volume index, and systemic vascular resistance index, were monitored by pulse-indicating continuous cardiac output monitors before treatment (T0), 24h after treatment (T1), and 72h after treatment (T2); changes in cardiac function before and after 72h of treatment, indicators of inflammatory factors before and after treatment, and indicators of oxygenation metabolism were assessed; and adverse drug reactions during treatment were recorded in both groups.

Results

NE combined with esmolol treatment improved the efficacy of patients with septic shock; was beneficial for the enhancement of blood perfusion in patients; improved the patient's cardiac function, reduced myocardial injury, and suppressed the inflammatory response in patients; improved the oxygenation metabolism and the prognosis of patients; did not significantly increase the adverse drug reactions of patients and had a better safety profile.

Conclusion

NE combined with esmolol treatment can improve the efficacy of patients with septic shock, improve their cardiac function and hemodynamic indices, reduce myocardial injury and inflammatory response, and have a better safety profile, which is conducive to improving patient prognosis and reducing mortality.

ICU management of cardiogenic shock before mechanical support

PURPOSE OF REVIEW

Treatment of cardiogenic shock remains largely driven by expert consensus due to limited evidence from randomized controlled trials. In this review, we aim to summarize the approach to the management of patients with cardiogenic shock in the ICU prior to mechanical circulatory support (MCS).

RECENT FINDINGS

Main topics covered in this article include diagnosis, monitoring, initial management and key aspects of pharmacological therapy in the ICU for patients with cardiogenic shock.

SUMMARY

Despite efforts to improve therapy, short-term mortality in patients with cardiogenic shock is still reaching 40-50%. Early recognition and treatment of cardiogenic shock are crucial, including early revascularization of the culprit lesion with possible staged revascularization in acute myocardial infarction (AMI)-CS. Optimal volume management and vasoactive drugs titrated to restore arterial pressure and perfusion are the cornerstone of cardiogenic shock therapy. The choice of vasoactive drugs depends on the underlying cause and phenotype of cardiogenic shock. Their use should be limited to the shortest duration and lowest possible dose. According to recent observational evidence, assessment of the complete hemodynamic profile with a pulmonary artery catheter (PAC) was associated with improved outcomes and should be considered early in patients not responding to initial therapy or with unclear shock. A multidisciplinary shock team should be involved early in order to identify potential candidates for temporary and/or durable MCS.

Cardiogenic Shock: An Overview

Cardiogenic shock (CS) is a complex and dreadful condition for which effective treatments remain unclear. The concerningly high mortality rate of CS emphasizes a need for developing effective therapies to reduce its mortality and reverse its detrimental course. This article aims to provide an updated and evidence-based review of the pathophysiology of CS and the related pharmacotherapeutics with a special focus on vasoactive and inotropic agents.

Medical therapy of cardiogenic shock: Contemporary use of inotropes and vasopressors

Cardiogenic shock is a primary cardiac disorder that results in both clinical and biochemical evidence of tissue hypoperfusion and can lead to multi-organ failure and death depending on its severity. Inadequate cardiac contractility or cardiac power secondary to acute myocardial infarction remains the most frequent cause of cardiogenic shock, although its contribution has declined over the past two decades, compared with other causes. Despite some advances in cardiogenic shock management, this clinical syndrome is still burdened by an extremely high mortality. Its management is based on immediate stabilization of haemodynamic parameters so that further treatment, including mechanical circulatory support and transfer to specialized tertiary care centres, can be accomplished. With these aims, medical therapy, consisting mainly of inotropic drugs and vasopressors, still has a major role. The purpose of this article is to review current evidence on the use of these medications in patients with cardiogenic shock and discuss specific clinical settings with indications to their use.

Pharmacological treatment of cardiogenic shock - A state of the art review

Cardiogenic shock is a clinical syndrome of impaired tissue perfusion caused by primary cardiac dysfunction and inadequate cardiac output. It represents one of the most lethal clinical conditions in intensive care medicine with mortality >40%. Management of different clinical presentations of cardiogenic shock includes guidance of cardiac preload, afterload, heart rate and contractility by differential pharmacological modulation of volume, systemic and pulmonary vascular resistance and cardiac output besides reversing the triggering cause. Data from large registries and randomized controlled trials on optimal diagnostic guidance as well as choice of pharmacological agents has accrued significantly in recent years. This state-of-the-art review summarizes the basic concepts of cardiogenic shock, the diagnostic work-up and currently available evidence and guideline recommendations on pharmacological treatment of cardiogenic shock.

Explainable time-series deep learning models for the prediction of mortality, prolonged length of stay and 30-day readmission in intensive care patients

Background

In-hospital mortality, prolonged length of stay (LOS), and 30-day readmission are common outcomes in the intensive care unit (ICU). Traditional scoring systems and machine learning models for predicting these outcomes usually ignore the characteristics of ICU data, which are time-series forms. We aimed to use time-series deep learning models with the selective combination of three widely used scoring systems to predict these outcomes.

Materials and methods

A retrospective cohort study was conducted on 40,083 patients in ICU from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Three deep learning models, namely, recurrent neural network (RNN), gated recurrent unit (GRU), and long short-term memory (LSTM) with attention mechanisms, were trained for the prediction of in-hospital mortality, prolonged LOS, and 30-day readmission with variables collected during the initial 24 h after ICU admission or the last 24 h before discharge. The inclusion of variables was based on three widely used scoring systems, namely, APACHE II, SOFA, and SAPS II, and the predictors consisted of time-series vital signs, laboratory tests, medication, and procedures. The patients were randomly divided into a training set (80%) and a test set (20%), which were used for model development and model evaluation, respectively. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and Brier scores were used to evaluate model performance. Variable significance was identified through attention mechanisms.

Results

A total of 33 variables for 40,083 patients were enrolled for mortality and prolonged LOS prediction and 36,180 for readmission prediction. The rates of occurrence of the three outcomes were 9.74%, 27.54%, and 11.79%, respectively. In each of the three outcomes, the performance of RNN, GRU, and LSTM did not differ greatly. Mortality prediction models, prolonged LOS prediction models, and readmission prediction models achieved AUCs of 0.870 ± 0.001, 0.765 ± 0.003, and 0.635 ± 0.018, respectively. The top significant variables co-selected by the three deep learning models were Glasgow Coma Scale (GCS), age, blood urea nitrogen, and norepinephrine for mortality; GCS, invasive ventilation, and blood urea nitrogen for prolonged LOS; and blood urea nitrogen, GCS, and ethnicity for readmission.

Conclusion

The prognostic prediction models established in our study achieved good performance in predicting common outcomes of patients in ICU, especially in mortality prediction. In addition, GCS and blood urea nitrogen were identified as the most important factors strongly associated with adverse ICU events.