Deep learning for transesophageal echocardiography view classification

Transesophageal echocardiography (TEE) imaging is a vital tool used in the evaluation of complex cardiac pathology and the management of cardiac surgery patients. A key limitation to the application of deep learning strategies to intraoperative and intraprocedural TEE data is the complexity and unstructured nature of these images. In the present study, we developed a deep learning-based, multi-category TEE view classification model that can be used to add structure to intraoperative and intraprocedural TEE imaging data. More specifically, we trained a convolutional neural network (CNN) to predict standardized TEE views using labeled intraoperative and intraprocedural TEE videos from Cedars-Sinai Medical Center (CSMC). We externally validated our model on intraoperative TEE videos from Stanford University Medical Center (SUMC). Accuracy of our model was high across all labeled views. The highest performance was achieved for the Trans-Gastric Left Ventricular Short Axis View (area under the receiver operating curve [AUC] = 0.971 at CSMC, 0.957 at SUMC), the Mid-Esophageal Long Axis View (AUC = 0.954 at CSMC, 0.905 at SUMC), the Mid-Esophageal Aortic Valve Short Axis View (AUC = 0.946 at CSMC, 0.898 at SUMC), and the Mid-Esophageal 4-Chamber View (AUC = 0.939 at CSMC, 0.902 at SUMC). Ultimately, we demonstrate that our deep learning model can accurately classify standardized TEE views, which will facilitate further downstream deep learning analyses for intraoperative and intraprocedural TEE imaging.

Outcomes of Extremely Prolonged (> 50 d) Venovenous Extracorporeal Membrane Oxygenation Support

OBJECTIVES

There has been a sustained increase in the utilization of venovenous extracorporeal membrane oxygenation (ECMO) over the last decade, further exacerbated by the COVID-19 pandemic. We set out to describe our institutional experience with extremely prolonged (> 50 d) venovenous ECMO support for recovery or bridge to lung transplant candidacy in patients with acute respiratory failure.

DESIGN

Retrospective cohort study.

SETTING

A large tertiary urban care center.

PATIENTS

Patients 18 years or older receiving venovenous ECMO support for greater than 50 days, with initial cannulation between January 2018 and January 2022.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

One hundred thirty patients were placed on venovenous ECMO during the study period. Of these, 12 received prolonged (> 50 d) venovenous ECMO support. Eleven patients (92%) suffered from adult respiratory distress syndrome (ARDS) secondary to COVID-19, while one patient with prior bilateral lung transplant suffered from ARDS secondary to bacterial pneumonia. The median age of patients was 39 years (interquartile range [IQR], 35-51 yr). The median duration of venovenous ECMO support was 94 days (IQR, 70-128 d), with a maximum of 180 days. Median time from intubation to cannulation was 5 days (IQR, 2-14 d). Nine patients (75%) were successfully mobilized while on venovenous ECMO support. Successful weaning of venovenous ECMO support occurred in eight patients (67%); 6 (50%) were bridged to lung transplantation and 2 (17%) were bridged to recovery. Of those successfully weaned, seven patients (88%) were discharged from the hospital. All seven patients discharged from the hospital were alive 6 months post-decannulation; 83% (5/6) with sufficient follow-up time were alive 1-year after decannulation.

CONCLUSIONS

Our experience suggests that extremely prolonged venovenous ECMO support to allow native lung recovery or optimization for lung transplantation may be a feasible strategy in select critically ill patients, further supporting the expanded utilization of venovenous ECMO for refractory respiratory failure.

Effect of UNOS policy change and exception status request on outcomes in patients bridged to heart transplant with an intra-aortic balloon pump

BACKGROUND

Intra-aortic balloon pumps (IABP) are used to bridge select end-stage heart disease patients to heart transplant (HT). IABP use and exception requests both increased dramatically after the UNOS policy change (PC). The purpose of this study was to evaluate the effect of PC and exception status requests on waitlist and post-transplant outcomes in patients bridged to HT with IABP support.

METHODS

We analyzed adult, first-time, single-organ HT recipients from the UNOS Registry either on IABP at the time of registration for HT or at the time of HT. We compared waitlist and post-HT outcomes between patients from the PRE (October 18, 2016 to May 30, 2018) and POST (October 18, 2018 to May 30, 2020) eras using Kaplan-Meier curves and time-to-event analyses.

RESULTS

A total of 1267 patients underwent HT from IABP (261 pre-policy/1006 post-policy). On multivariate analysis, PC was associated with an increase in HT (sub-distribution hazard ratio (sdHR): 2.15, p < .001) and decrease in death/deterioration (sdHR: 0.55, p = .011) on the waitlist with no effect on 1-year post-HT survival (p = .8). The exception status of patients undergoing HT was predominantly seen in the POST era (29%, 293/1006); only four patients in the PRE era. Exception requests in the POST era did not alter patient outcomes.

CONCLUSIONS

In patients bridged to heart transplant with an IABP, policy change is associated with decreased rates of death/deterioration and increased rates of heart transplantation on the waitlist without affecting 1-year post-transplant survival. While exception status use has markedly increased post-PC, it is not associated with patient outcomes.

Mortality and Readmission Rates Among Patients With COVID-19 After Discharge From Acute Care Setting With Supplemental Oxygen

IMPORTANCE

To optimize patient outcomes and preserve critical acute care access during the COVID-19 pandemic, the Los Angeles County Department of Health Services developed the SAFE @ HOME O2 Expected Practice (expected practice), enabling ambulatory oxygen management for COVID-19.

OBJECTIVE

To assess outcomes of patients with COVID-19 pneumonia discharged via the expected practice approach to home or quarantine housing with supplemental home oxygen.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective cohort study included 621 adult patients with COVID-19 pneumonia who were discharged from 2 large urban public hospitals caring primarily for patients receiving Medicaid from March 20 to August 19, 2020. Patients were included in the analysis cohort if they received emergency or inpatient care for COVID-19 and were discharged with home oxygen.

INTERVENTIONS

Patients receiving at least 3 L per minute of oxygen, stable without other indication for inpatient care, were discharged from either emergency or inpatient encounters with home oxygen equipment, educational resources, and nursing telephone follow-up within 12 to 18 hours of discharge. Nurses provided continued telephone follow up as indicated, always with physician back-up.

MAIN OUTCOMES AND MEASURES

All-cause mortality and all-cause 30-day return admission.

RESULTS

A total of 621 patients with COVID-19 pneumonia (404 male [65.1%] and 217 female [34.9%]) were discharged with home oxygen. Median age of these patients was 51 years (interquartile range, 45-61 years), with 149 (24.0%) discharged from the emergency department and 472 (76%) discharged from inpatient encounters. The all-cause mortality rate was 1.3% (95% CI, 0.6%-2.5%) and the 30-day return hospital admission rate was 8.5% (95% CI, 6.2%-10.7%) with a median follow-up time of 26 days (interquartile range, 15-55 days). No deaths occurred in the ambulatory setting.

CONCLUSIONS AND RELEVANCE

In this cohort study, patients with COVID-19 pneumonia discharged on home oxygen had low rates of mortality and return admission within 30 days of discharge. Ambulatory management of COVID-19 with home oxygen has an acceptable safety profile, and the expected practice approach may help optimize outcomes, by ensuring right care in the right place at the right time and preserving access to acute care during the COVID-19 pandemic.

Impact of Left Ventricular to Mitral Valve Ring Mismatch on Recurrent Ischemic Mitral Regurgitation After Ring Annuloplasty

BACKGROUND

In ischemic mitral regurgitation (IMR), ring annuloplasty is associated with a significant rate of recurrent MR. Ring size is based on intertrigonal distance without consideration of left ventricular (LV) size. However, LV size is an important determinant of mitral valve (MV) leaflet tethering before and after repair. We aimed to determine whether LV-MV ring mismatch (mismatch of LV size relative to ring size) is associated with recurrent MR in patients with IMR after restrictive ring annuloplasty.

METHODS

Patients with moderate or severe IMR from the 2 Cardiothoracic Surgical Trials Network IMR trials who received MV repair were examined at 1 year after surgery. Baseline LV size was assessed by LV end-diastolic dimension and LV end-systolic dimension (LVESd). LV-MV ring mismatch was calculated as the ratio of LV to ring size (LV end-diastolic dimension/ring size and LVESd/ring size).

RESULTS

At 1 year after ring annuloplasty, 45 of 214 patients with MV repair (21%) had moderate or greater MR. In univariable logistic regression analysis, larger LVESd (P=0.02) and LVESd/ring size (P=0.007) were associated with recurrent MR. In multivariable models adjusted for age, sex, baseline LV ejection fraction, and severe IMR, only LVESd/ring size (odd ratio per 0.5 increase, 2.20; 95% confidence interval, 1.05-4.62; P=0.038) remained significantly associated with 1-year MR recurrence.

CONCLUSIONS

LV-MV ring size mismatch is associated with increased risk of MR recurrence. This finding may be helpful in guiding choice of ring size to prevent recurrent MR in patients undergoing MV repair and in identifying patients who may benefit from MV repair with additional subvalvular intervention or MV replacement rather than repair alone.

CLINICAL TRIAL REGISTRATION

URL:http://clinicaltrials.gov. Unique identifiers: NCT00806988 and NCT00807040.