An Explainable Machine Learning Approach Reveals Prognostic Significance of Right Ventricular Dysfunction in Nonischemic Cardiomyopathy.

OBJECTIVES: The authors implemented an explainable machine learning (ML) model to gain insight into the association between cardiac magnetic resonance markers and adverse outcomes of cardiovascular hospitalization and all-cause death (composite endpoint) in patients with nonischemic dilated cardiomyopathy (NICM). BACKGROUND: Risk stratification of patients with NICM remains challenging. An explainable ML model has the potential to provide insight into the contributions of different risk markers in the prediction model. METHODS: An explainable ML model based on extreme gradient boosting (XGBoost) machines was developed using cardiac magnetic resonance and clinical parameters. The study cohorts consist of patients with NICM from 2 academic medical centers: Beth Israel Deaconess Medical Center (BIDMC) and Brigham and Women's Hospital (BWH), with 328 and 214 patients, respectively. XGBoost was trained on 70% of patients from the BIDMC cohort and evaluated based on the other 30% as internal validation. The model was externally validated using the BWH cohort. To investigate the contribution of different features in our risk prediction model, we used Shapley additive explanations (SHAP) analysis. RESULTS: During a mean follow-up duration of 40 months, 34 patients from BIDMC and 33 patients from BWH experienced the composite endpoint. The area under the curve for predicting the composite endpoint was 0.71 for the internal BIDMC validation and 0.69 for the BWH cohort. SHAP analysis identified parameters associated with right ventricular (RV) dysfunction and remodeling as primary markers of adverse outcomes. High risk thresholds were identified by SHAP analysis and thus provided thresholds for top predictive continuous clinical variables. CONCLUSIONS: An explainable ML-based risk prediction model has the potential to identify patients with NICM at risk for cardiovascular hospitalization and all-cause death. RV ejection fraction, end-systolic and end-diastolic volumes (as indicators of RV dysfunction and remodeling) were determined to be major risk markers.

A Retrospective Comparison of the Effectiveness and Safety of Intravenous Olanzapine Versus Intravenous Haloperidol for Agitation in Adult Intensive Care Unit Patients.

OBJECTIVE: Intravenous (IV) olanzapine could be an alternative to first-generation antipsychotics for the management of agitation in intensive care unit (ICU) patients. We compared the effectiveness and safety of IV olanzapine to IV haloperidol for agitation management in adult patients in the ICU at a tertiary academic medical center. METHODS: A retrospective cohort study was conducted. The primary outcome was the proportion of patients who achieved a Richmond Agitation Sedation Scale (RASS) score of < +1 within 4 hours of IV olanzapine or IV haloperidol administration. Secondary outcomes included the proportion of patients who required rescue medications for agitation within 4 hours of initial IV olanzapine or IV haloperidol administration, incidence of adverse events and ICU length of stay. RESULTS: In the 192 patient analytic cohort, there was no difference in the proportion of patients who achieved a RASS score of < +1 within 4 hours of receiving IV olanzapine or IV haloperidol (49% vs. 42%, p = 0.31). Patients in the IV haloperidol group were more likely to receive rescue medications (28% vs 55%, p < 0.01). There was no difference in the incidence of respiratory events or hypotension between IV olanzapine and IV haloperidol. Patients in the IV olanzapine group experienced more bradycardia (11% vs. 3%, p = 0.04) and somnolence (9% vs. 1%, p = 0.02) compared to the IV haloperidol group. Patients in the IV olanzapine group had a longer median ICU length of stay (7.5 days vs. 5 days, p = 0.04). CONCLUSION: In this retrospective cohort study, there was no difference in the effectiveness of IV olanzapine compared to IV haloperidol for the management of agitation. IV olanzapine was associated with an increased incidence of bradycardia and somnolence.

Trends over time in drug administration during pediatric in-hospital cardiac arrest in the United States.

AIMS: To describe trends in pediatric in-hospital cardiac arrest drug administration and to assess temporal associations of the Pediatric Advanced Life Support (PALS) guideline changes with drug usage. METHODS: Pediatric patients <18 years old with in-hospital cardiac arrest recorded in the American Heart Association Get With The Guidelines-Resuscitation database between 2002 and 2018 were included. The annual adjusted odds of receiving each intra-arrest medication was determined. The association between changes in the PALS Guidelines and medication use over time was assessed interrupted time series analyses. RESULTS: A total of 6107 patients were analyzed. The adjusted odds of receiving lidocaine (0.33; 95% CI, 0.18, 0.61; p < 0.001), atropine (0.19; 95% CI 0.12, 0.30; p < 0.001) and bicarbonate (0.54; 95% CI 0.35, 0.86; p = 0.009) were lower in 2018 compared to 2002. For lidocaine, there were no significant changes in the step (-2.1%; 95% CI, -5.9%, 1.6%; p = 0.27) after the 2010 or 2015 (Step: -1.5%; 95% CI, -8.0%, 5.0; p = 0.65) guideline releases. There were no significant changes in the step for bicarbonate (-2.3%; 95% CI, -7.6%, 3.0%; p = 0.39) after the 2010 updates. For atropine, there was a downward step change after the 2010 guideline release (-5.9%; 95% CI, -10.5%, -1.3%; p = 0.01). CONCLUSIONS: Changes to the PALS guidelines for lidocaine and bicarbonate were not temporally associated with acute changes in the use of these medications; however, better alignment with these updates was observed over time. A minor update to the language surrounding atropine in the PALS text was associated with a modest acute change in the observed use of atropine. Future studies exploring other factors that influence prescribers in pediatric IHCA are needed.

Use of SOFA score in cardiac arrest research: A scoping review.

BACKGROUND: The Sequential Organ Failure Assessment (SOFA) score is a commonly used severity-of-illness score in cardiac arrest research. Due to its nature, the SOFA score often has missing data. How much data is missing and how that missing data is handled is unknown. OBJECTIVES: We conducted a scoping review on cardiac arrest studies using SOFA, focusing on missing data. DATA SOURCES: PubMed, Embase, and Web of Science. STUDY SELECTION: All English-language peer-reviewed studies of cardiac arrest with SOFA as an outcome or exposure were included. DATA EXTRACTION: For each study, quantity of missing SOFA data, analytic strategy to handle missing SOFA variables, whether/to what degree mortality influenced the amount of missing SOFA scores), SOFA score modifications, and number of SOFA measurements was extracted. DATA SYNTHESIS: We included 66 studies published between 2006-2019. Five studies were randomized controlled trials, 26 were prospective cohort studies, and 25 were retrospective cohort studies. SOFA was used as an outcome in 36 (55%) and a primary outcome in 10 (15%). Nine studies (14%) mentioned the quantity of missing SOFA data, which ranged from 0 to 76% (median: 10% [IQR: 6%, 42%]). Twenty-seven (41%) studies reported a method to handle missing SOFA. The most common method used excluded subjects with missing data (81%). In the 50 studies using serial SOFA scores, 11 (22%) documented mortality prior to SOFA measurement; which ranged from 3% to 76% (median: 12% [IQR: 6%-35%]). CONCLUSIONS: Missing data is common in cardiac arrest research using SOFA scores. Variability exists in reporting and handling missing SOFA variables.