Integrating the STOP-BANG Score and Clinical Data to Predict Cardiovascular Events After Infarction: A Machine Learning Study

The Multicenter Collaborative to Enhance Biologic Understanding, Quality, and Outcomes in Cardiogenic Shock (VANQUISH Shock): Rationale and Design

BACKGROUND

Despite efforts to advance therapies in cardiogenic shock (CS), outcomes remain poor. This is likely due to several factors, including major gaps in our understanding of the pathophysiology, phenotyping of patients, and challenges with conducting adequately powered clinical studies. An unmet need exists for a comprehensive multicentre "all-comers" prospective registry to facilitate characterising contemporary presentation, treatment (in a device-agnostic fashion), and short- and intermediate-term outcomes and quality of life (QOL) of CS patients.

METHODS

The Multicenter Collaborative to Enhance Biological Understanding, Quality and Outcomes in Cardiogenic Shock (VANQUISH Shock) registry is a prospective observational registry that will study unrestricted adult patients with a primary diagnosis of CS at 4 North American centres with multidisciplinary shock programs. Both acute myocardial infarction (AMI-CS) and acute heart failure (HF-CS) etiologies will be included, and the registry will be device agnostic and widely inclusive. The primary end point will be survival at 30 days after hospital discharge. Secondary outcomes will include in-hospital adverse events and survival to 6 and 12 months. Patients will also undergo neurologic and health-related QOL assessments with the Cerebral Performance Category (CPC) and Short-Form 36 (SF-36) health survey tools before discharge and during follow-up. Serial biospecimens will facilitate biomarker studies.

CONCLUSIONS

The VANQUISH Shock registry provides a unique opportunity to study the pathophysiology, contemporary management, clinical course, and outcomes of CS. By capturing detailed and high-quality longitudinal data, the registry will address existing knowledge gaps and serve as a springboard for future mechanistic clinical studies to advance the field.

Novel Insights into the Predictors of Obstructive Sleep Apnea Syndrome in Patients with Chronic Coronary Syndrome: Development of a Predicting Model

Background

Obstructive sleep apnea syndrome (OSAS) is common in patients with chronic coronary syndrome (CCS); however, a predictive model of OSAS in patients with CCS remains rarely reported. The study aimed to construct a novel nomogram scoring system to predict OSAS comorbidity in patients with CCS.

Methods

Consecutive CCS patients scheduled for sleep monitoring at our hospital from January 2019 to September 2020 were enrolled in the current study. Coronary CT angiography or coronary angiography was used for the diagnosis of CCS, and clinical characteristics of the patients were collected. Significant predictors for OSAS in patients with moderate/severe CCS were estimated via logistic regression analysis, and a clinical nomogram was constructed. A calibration plot, examining discrimination (Harrell's concordance index) and decision curve analysis (DCA), was applied to validate the nomogram's predictive performance. Internal validity of the predictive model was assessed using bootstrapping (1000 replications).

Results

The nomograms were constructed based on available clinical variables from 527 patients which were significantly associated with moderate/severe OSAS in patients with CCS, including body mass index, impaired glucose tolerance, hypertension, diabetes mellitus, nonalcoholic fatty liver disease, and routine laboratory indices such as neutrophil to lymphocyte ratio, platelet-to-lymphocyte ratio, high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol. The C-index (0.793) and AUC (0.771, 95% CI: 0.731–0.811) demonstrated a favorable discriminative ability of the nomogram. Moreover, calibration plots revealed consistency between moderate/severe OSAS predicted by the nomogram and validated by the results of sleep monitoring. Clinically, DCA showed that the nomogram had good discriminative ability to predict moderate/severe OSAS in patients with CCS.

Conclusions

The risk nomogram constructed via the routinely available clinical variables in patients with CCS showed satisfying discriminative ability to predict comorbid moderate/severe OSAS, which may be useful for identification of high-risk patients with OSAS in patients with CCS.

Cardiogenic shock and machine learning: A systematic review on prediction through clinical decision support softwares

BACKGROUND AND AIM

Cardiogenic shock (CS) withholds a significantly high mortality rate between 40% and 60% despite advances in diagnosis and medical/surgical intervention. To date, machine learning (ML) is being implemented to integrate numerous data to optimize early diagnostic predictions and suggest clinical courses. This systematic review summarizes the area under the curve (AUC) receiver operating characteristics (ROCs) accuracy for the early prediction of CS.

METHODS

A systematic review was conducted within databases of PubMed, ScienceDirect, Clinical Key/MEDLINE, Embase, GoogleScholar, and Cochrane. Cohort studies that assessed the accuracy of early detection of CS using ML software were included. Data extraction was focused on AUC-ROC values directed towards the early detection of CS.

RESULTS

A total of 943 studies were included for systematic review. From the reviewed studies, 2.2% (N = 21) evaluated patient outcomes, of which 14.3% (N = 3) were assessed. The collective patient cohort (N = 698) consisted of 314 (45.0%) females, with an average age and body mass index of 64.1 years and 28.1 kg/m² , respectively. Collectively, 159 (22.8%) mortalities were reported following early CS detection. Altogether, the AUC-ROC value was 0.82 (α = .05), deeming it of superb sensitivity and specificity.

CONCLUSIONS

From the present comprehensively gathered data, this study accounts the use of ML software for the early detection of CS in a clinical setting as a valid tool to predict patients at risk of CS. The complexity of ML and its parallel lack of clinical evidence implies that further prospective randomized control trials are needed to draw definitive conclusions before standardizing the use of these technologies.

BRIEF SUMMARY

The catastrophic risk of developing CS continues to be a concern in the management of critical cardiac care. The use of ML predictive models have the potential to provide the accurate and necessary feedback for the early detection and proper management of CS. This systematic review summarizes the AUC-ROCs accuracy for the early prediction of CS.