Development and external validation of a dynamic risk score for early prediction of cardiogenic shock in cardiac intensive care units using machine learning.

AIMS: Myocardial infarction and heart failure are major cardiovascular diseases that affect millions of people in the USA with morbidity and mortality being highest among patients who develop cardiogenic shock. Early recognition of cardiogenic shock allows prompt implementation of treatment measures. Our objective is to develop a new dynamic risk score, called CShock, to improve early detection of cardiogenic shock in the cardiac intensive care unit (ICU). METHODS AND RESULTS: We developed and externally validated a deep learning-based risk stratification tool, called CShock, for patients admitted into the cardiac ICU with acute decompensated heart failure and/or myocardial infarction to predict the onset of cardiogenic shock. We prepared a cardiac ICU dataset using the Medical Information Mart for Intensive Care-III database by annotating with physician-adjudicated outcomes. This dataset which consisted of 1500 patients with 204 having cardiogenic/mixed shock was then used to train CShock. The features used to train the model for CShock included patient demographics, cardiac ICU admission diagnoses, routinely measured laboratory values and vital signs, and relevant features manually extracted from echocardiogram and left heart catheterization reports. We externally validated the risk model on the New York University (NYU) Langone Health cardiac ICU database which was also annotated with physician-adjudicated outcomes. The external validation cohort consisted of 131 patients with 25 patients experiencing cardiogenic/mixed shock. CShock achieved an area under the receiver operator characteristic curve (AUROC) of 0.821 (95% CI 0.792-0.850). CShock was externally validated in the more contemporary NYU cohort and achieved an AUROC of 0.800 (95% CI 0.717-0.884), demonstrating its generalizability in other cardiac ICUs. Having an elevated heart rate is most predictive of cardiogenic shock development based on Shapley values. The other top 10 predictors are having an admission diagnosis of myocardial infarction with ST-segment elevation, having an admission diagnosis of acute decompensated heart failure, Braden Scale, Glasgow Coma Scale, blood urea nitrogen, systolic blood pressure, serum chloride, serum sodium, and arterial blood pH. CONCLUSION: The novel CShock score has the potential to provide automated detection and early warning for cardiogenic shock and improve the outcomes for millions of patients who suffer from myocardial infarction and heart failure.

Medication Use in the Diagnostic Pediatric Lumbar Puncture.

The lumbar puncture (LP) is a common procedure in the pediatric emergency department. A retrospective review was conducted of patients who had LPs from 2012 to 2016 at 2 children's hospitals to (1) characterize medication use during the pediatric LP and (2) test the hypothesis that varied medication use influences LP outcome. Outcomes were defined as unsuccessful if the LP was documented as unsuccessful, had a cerebrospinal fluid (CSF) red blood cell (RBC) count >400 cells/µL, or if a second LP was performed within 24 hours. In total, 8463 patients were reviewed and 2806 (33%) were included in the study. We noted significant variation in LP medication use. When adjusted for patient demographics, location, weight, position, and provider experience, our regression model revealed that the use of fentanyl, ketamine, nitrous oxide, and propofol were best associated with LP success. These data suggest the need for a standardized LP medication protocol as provider choice in medication significantly influences LP outcome.

An innovative medical school curriculum to address human papillomavirus vaccine hesitancy.

BACKGROUND: Vaccination rates against Human Papillomavirus (HPV) in the US remain alarmingly low. Physicians can significantly influence a parent's decision to vaccinate their children. However, medical education often lacks training on specific strategies for communicating with vaccine hesitant parents. METHODS: We created an innovative curriculum designed to teach medical students how to address HPV vaccine hesitancy. The curriculum consisted of (1) a presentation on the epidemiology, biology, and disease morbidity associated with HPV, (2) a video that teaches specific communication strategies and (3) role-playing simulations. This curriculum was delivered to medical students at two separate sites. Medical students were surveyed before and after completing the educational curriculum. The surveys assessed student comfort talking to HPV vaccine hesitant parents and their likelihood to recommend the HPV vaccine. RESULTS: Pre- and post-intervention surveys were completed by 101 of the 132 participants (77% response rate). After the intervention, student awareness of the benefits of the HPV vaccine increased by a mean of 0.82 points (Likert scale 1-5, p < 0.01) and student comfort talking to vaccine hesitant parents increased by a mean of 1.37 points (p < 0.01). Prior to the intervention, students more strongly recommended the HPV vaccine to females compared to males, but this gender disparity was eliminated after the intervention (p < 0.01). Personal vaccination status was independately associated with a higher likelihood of recommending the HPV vaccine both before and after the intervention. CONCLUSION: Our innovative curriculum improved medical student comfort level discussing HPV vaccination with hesitant parents and increased the perceived likelihood of recommending HPV vaccination. The intervention is easy to implement, scalable, and requires minimal resources. Educating future providers on this important topic has the potential to improve vaccination rates nationwide and thus should be considered for all medical students.