Spatiotemporal Deep Learning-Based Cine Loop Quality Filter for Handheld Point-of-Care Echocardiography.

The reliability of automated image interpretation of point-of-care (POC) echocardiography scans depends on the quality of the acquired ultrasound data. This work reports on the development and validation of spatiotemporal deep learning models to assess the suitability of input ultrasound cine loops collected using a handheld echocardiography device for processing by an automated quantification algorithm (e.g. ejection fraction estimation). POC echocardiograms (n=885 DICOM cine loops from 175 patients) from two sites were collected using a handheld ultrasound device and annotated for image quality at the frame-level. Attributes of high-quality frames for left ventricular (LV) quantification included a temporally-stable LV, reasonable coverage of LV borders, and good contrast between the borders and chamber. Attributes of low-quality frames included temporal instability of the LV and/or imaging artifacts (e.g., lack of contrast, haze, reverberation, acoustic shadowing). Three different neural network architectures were investigated - (a) frame-level convolutional neural network (CNN) which operates on individual echo frames (VectorCNN), (b) single-stream sequence-level CNN which operates on a sequence of echo frames (VectorCNN+LSTM) and (c) two-stream sequence-level CNNs which operate on a sequence of echo and optical flow frames (VectorCNN+LSTM+Average, VectorCNN+LSTM+MinMax, and VectorCNN+LSTM+ConvPool). Evaluation on a sequestered test dataset containing 76 DICOM cine loops with 16,914 frames showed that VectorCNN+LSTM can effectively utilize both spatial and temporal information to regress the quality of an input frame (accuracy: 0.925, sensitivity = 0.860, specificity = 0.952), compared to the frame-level VectorCNN that only utilizes spatial information in that frame (accuracy: 0.903, sensitivity = 0.791, specificity = 0.949). Furthermore, an independent sample t-test indicated that the cine loops classified to be of adequate quality by the VectorCNN+LSTM model had a statistically significant lower bias in the automatically estimated EF (mean bias = - 3.73 ± 7.46 %, versus a clinically obtained reference EF) compared to the loops classified as inadequate (mean bias = -15.92 ± 12.17 %) (p = 0.007). Thus, cine loop stratification using the proposed spatiotemporal CNN model improves the reliability of automated point-of-care echocardiography image interpretation.

Testing clinical selection criteria for intraoperative transoesophageal echocardiography in isolated coronary artery bypass graft surgery.

Background: There is a lack of evidence associating intraoperative transoesophageal echocardiography (TOE) use with improved outcomes among coronary artery bypass graft (CABG) surgery subpopulations. Methods: This matched retrospective cohort study used a US private claims dataset to compare outcomes among different CABG surgery patient populations with vs without TOE. Statistical analyses involved exact matching on pre-selected subgroups (congestive heart failure, single vessel, and multivessel CABG) and used fine and propensity-score balanced techniques to conduct multiple matched comparisons and sensitivity analyses. Results: Of 42 249 patients undergoing isolated CABG surgery, 24 919 (59.0%) received and 17 330 (41.0%) did not receive TOE. After matching, intraoperative TOE was significantly associated with a lower, 30-day mortality: 2.63% vs 3.20% (odds ratio [OR]: 0.81; 95% confidence interval [CI]: 0.71-0.92; P=0.002). In the subgroup matched comparisons, intraoperative TOE was significantly associated with a lower, 30-day mortality rate among those with congestive heart failure: 4.20% vs 5.26% (OR: 0.78; 95% CI: 0.66-0.94; P=0.007) and among those undergoing multivessel CABG with congestive heart failure: 4.23% vs 5.24% (OR: 0.80; 95% CI: 0.65-0.97; P=0.025), but not among those undergoing multivessel CABG without congestive heart failure: 1.83% vs 2.15% (OR: 0.85; 95% CI: 0.70-1.02; P=0.089, nor any of the remaining three subgroups. Conclusions: Among US adults undergoing isolated CABG surgery, intraoperative TOE was associated with improved outcomes in patients with congestive heart failure (vs without) and among patients undergoing multivessel (vs single vessel) CABG. These findings support prioritised TOE allocation to these patient populations at centres with limited TOE capabilities.

The Society of Thoracic Surgeons Adult Cardiac Surgery Database: Intraoperative Echocardiography Reporting.

OBJECTIVES: To identify trends in the reporting of intraoperative transesophageal echocardiographic (TEE) data in the Society of Thoracic Surgeons (STS) Adult Cardiac Surgery Database (ACSD) and the Adult Cardiac Anesthesiology (ACA) module by period, practice type, and geographic distribution, and to elucidate ongoing areas for practice improvement. DESIGN: A retrospective study. SETTING: STS ACSD. PARTICIPANTS: Procedures reported in the STS ACSD between July 2017 and December 2021 in participating programs in the United States. INTERVENTIONS: None MEASUREMENTS AND MAIN RESULTS: Intraoperative TEE is reported for 73% of all procedures in ACSD. Although the intraoperative TEE data reporting rate increased from 2017 to 2021 for isolated coronary artery bypass graft surgery, it remained low at 62.2%. The reporting of relevant echocardiographic variables across a wide range of procedures has steadily increased over the study period but also remained low. The reporting in the ACA module is high for most variables and across all anesthesia care models; however, the overall contribution of the ACA module to the ACSD remains low. CONCLUSIONS: This progress report suggests a continued need to raise awareness regarding current practices of reporting intraoperative TEE in the ACSD and the ACA, and highlights opportunities for improving reporting and data abstraction.

Pragmatic Evaluation of a Deep-Learning Algorithm to Automate Ejection Fraction on Hand-Held, Point-of-Care Echocardiography in a Cardiac Surgical Operating Room.

OBJECTIVE: To test the correlation of ejection fraction (EF) estimated by a deep-learning-based, automated algorithm (Auto EF) versus an EF estimated by Simpson's method. DESIGN: A prospective observational study. SETTING: A single-center study at the Hospital of the University of Pennsylvania. PARTICIPANTS: Study participants were ≥18 years of age and scheduled to undergo valve, aortic, coronary artery bypass graft, heart, or lung transplant surgery. INTERVENTIONS: This noninterventional study involved acquiring apical 4-chamber transthoracic echocardiographic clips using the Philips hand-held ultrasound device, Lumify. MEASUREMENTS AND MAIN RESULTS: In the primary analysis of 54 clips, compared to Simpson's method for EF estimation, bias was similar for Auto EF (-10.17%) and the experienced reader-estimated EF (-9.82%), but the correlation was lower for Auto EF (r = 0.56) than the experienced reader-estimated EF (r = 0.80). In the secondary analyses, the correlation between EF estimated by Simpson's method and Auto EF increased when applied to 27 acquisitions classified as adequate (r = 0.86), but decreased when applied to 27 acquisitions classified as inadequate (r = 0.46). CONCLUSIONS: Applied to acquisitions of adequate image quality, Auto EF produced a numerical EF estimate equivalent to Simpson's method. However, when applied to acquisitions of inadequate image quality, discrepancies arose between EF estimated by Auto EF and Simpson's method. Visual EF estimates by experienced readers correlated highly with Simpson's method in both variable and inadequate imaging conditions, emphasizing its enduring clinical utility.

Extracorporeal Carbon Dioxide Removal to De-escalate Venovenous Extracorporeal Membrane Oxygenation in Severe COVID-19 Acute Respiratory Distress Syndrome.

OBJECTIVES: In a subset of patients with COVID-19 acute respiratory distress syndrome (ARDS), there is a need for extracorporeal membrane oxygenation (ECMO) for pulmonary support. The primary extracorporeal support tool for severe COVID-19 ARDS is venovenous (VV) ECMO; however, after hypoxemic respiratory failure resolves, many patients experience refractory residual hypercarbic respiratory failure. Extracorporeal carbon dioxide removal (ECCO2R) for isolated hypercarbic type II respiratory failure can be used in select cases to deescalate patients from VV ECMO while the lung recovers the ability to exchange CO2. The objective of this study was to describe the authors' experience in using ECCO2R as a bridge from VV ECMO. DESIGN: Hemolung Respiratory Assist System (RAS) is a commercially available (ECCO2R) device, and the United States Food and Drug Administration accelerated its use under its Emergency Use Authorization for the treatment of refractory hypercarbic respiratory failure in COVID-19-induced ARDS. This created an environment in which selected and targeted mechanical circulatory support therapy for refractory hypercarbic respiratory failure could be addressed. This retrospective study describes the application of Hemolung RAS as a VV ECMO deescalation platform to treat refractory hypercarbic respiratory failure after the resolution of hypoxemic COVID-19 ARDS. SETTING: A quaternary-care academic medical center, single institution. PARTICIPANTS: Patients with refractory hypercarbic respiratory failure after COVID-19 ARDS who were previously supported with VV ECMO. MEASUREMENTS AND MAIN RESULTS: Twenty-one patients were placed on ECCO2R after VV ECMO for COVID-19 ARDS. Seventeen patients successfully were transitioned to ECCO2R and then decannulated; 3 patients required reescalation to VV ECMO secondary to hypercapnic respiratory failure, and 1 patient died while on ECCO2R. Five (23.8%) of the 21 patients were transitioned off of VV ECMO to ECCO2R, with a compliance of <20 (mL/cmH2O). Of these patients, 3 with low compliance were reescalated to VV ECMO. CONCLUSIONS: Extracorporeal carbon dioxide removal can be used to continue supportive methods for patients with refractory type 2 hypercarbic respiratory failure after COVID-19 ARDS for patients previously on VV ECMO. Patients with low compliance have a higher rate of reescalation to VV ECMO.

Placement of Temporary Left Ventricular Assist Device Using Monitored Anesthesia Care and Regional Anesthesia.

Patients with advanced cardiogenic shock requiring mechanical circulatory support are uniquely susceptible to clinical deterioration. Limiting physiologic perturbations via avoidance of general anesthesia and endotracheal intubation by awake Impella 5.5 placement is safe and may represent a novel strategy in mechanical circulatory support initiation among patients in cardiogenic shock. (Level of Difficulty: Intermediate.).

Evolution in the treatment of gastroesophageal reflux disease over the last century: from a crural-centered to a lower esophageal sphincter-centered approach and back.

The surgical management of gastroesophageal reflux disease (GERD) has evolved significantly over the past century, driven by increased understanding of the physiology of the reflux barrier, its anatomic components, and surgical innovation. Initially, emphasis was on reduction of hiatal hernias and crural closure as the etiology behind GERD was felt to be solely related to the anatomic alterations caused by hiatal hernias. With persistence of reflux-related changes in some patients despite crural closure, along with the development of what is now modern manometry and the discovery of a high-pressure zone at the distal esophagus, focus evolved to surgical augmentation of the lower esophageal sphincter (LES). With this transition to an LES-centric approach, attention shifted to reconstruction of the angle of His, ensuring sufficient intra-abdominal esophageal length, development of the now commonly employed Nissen fundoplication, and creation of devices that directly augment the LES such as magnetic sphincter augmentation. More recently, the role of crural closure in antireflux and hiatal hernia surgery has again received renewed attention due to the persistence of postoperative complications including wrap herniation and high rates of recurrences. Rather than simply preventing transthoracic herniation of the fundoplication as was originally thought, diaphragmatic crural closure has been documented to have a key role in re-establishing intra-abdominal esophageal length and contributing to the restoration of normal LES pressures. This progression from a crural-centric to a LES-centric approach and back has evolved along with our understanding of the reflux barrier and will continue to do so as more advances are made in the field. In this review, we will discuss the evolution of surgical techniques over the past century, highlighting key historical contributions that have shaped our management of GERD today.

Predictors of Intraoperative Echocardiography: Analysis of The Society of Thoracic Surgeons Database.

BACKGROUND: Intraoperative transesophageal echocardiography (TEE) is associated with improved outcomes after cardiac surgery, but unexplained practice pattern variation exists. This study aimed to identify and quantify the predictors of intraoperative TEE use among patients undergoing isolated coronary artery bypass graft surgery (CABG) or cardiac valve surgery. METHODS: This observational cohort study used The Society of Thoracic Surgeon (STS) Adult Cardiac Surgery Database data to identify and quantify the predictors of intraoperative TEE use among adult patients aged 18 years or more undergoing either isolated CABG or open cardiac valve repair or replacement surgery between January 1, 2011, and December 31, 2019. Generalized linear mixed models were used to measure the relationship between intraoperative TEE and patient characteristics, surgical volume, and geographic location, while accounting for clustering within hospitals (primary analysis) or surgeons (secondary analysis). RESULTS: Of 1,973,655 patients, 1,365,708 underwent isolated CABG and 607,947 underwent cardiac valve surgery. Overall, intraoperative TEE was used in 62% of surgeries. The primary hospital-level generalized linear mixed models analysis demonstrated that the strongest predictor of intraoperative TEE use was the hospital where the surgery occurred-with a median odds ratio for TEE of 10.13 in isolated CABG and 5.30 in cardiac valve surgery. The secondary surgeon-level generalized linear mixed models analysis demonstrated similar findings. CONCLUSIONS: Intraoperative TEE use (vs lack of use) during surgery was more strongly associated with hospital and surgeon practice patterns than with any patient-level factor, surgical volume, or geographic location.

Neighborhood Socioeconomic Status Independently Predicts Outcomes After Mitral Valve Surgery.

BACKGROUND: Socioeconomic status has increasingly recognized influence on outcomes after cardiac surgery. However, singular metrics fail to fully capture the socioeconomic context within which patients live, which vary greatly between neighborhoods. We sought to explore the impact of neighborhood-level socioeconomic status on patients undergoing mitral valve surgery in the United States. METHODS: Adults undergoing first-time, isolated mitral valve surgery were queried from The Society of Thoracic Surgeons Adult Cardiac Surgery Database between 2012 and 2018. Socioeconomic status was quantified using the Area Deprivation Index, a weighted composite including average housing prices, household incomes, education, and employment levels. The associations between regional deprivation, access to mitral surgery, valve repair rates, and outcomes were evaluated using logistic regression. RESULTS: Among 137,100 patients included, patients with socioeconomic deprivation had fewer elective presentations, more comorbidity burden, and more urgent/emergent surgery. Patients from less disadvantaged areas received operations from higher volume surgeons and had higher repair rates (highest vs lowest quintile: 72% vs 51%, P < .001, more minimally-invasive approach (33% vs 20%, P < .001), lower composite complication rate (42% vs 50%, P < .001), and lower 30-day mortality (1.8% vs 3.9%, P < .001). After hierarchical multivariable adjustment, the Area Deprivation Index significantly predicted 30-day mortality and repair rate (P < .001). CONCLUSIONS: In a risk-adjusted national analysis of mitral surgery, patients from more deprived areas were less likely to undergo mitral repair and more likely to have complications. Further work at targeting neighborhood-level disparity is important to improving mitral surgical outcomes in the United States.

Impact of Hospital Practice and Staffing Differences on Transesophageal Echocardiography Use in Cardiac Valve or Coronary Artery Bypass Graft Surgery.

OBJECTIVES: To identify and quantify the predictors of intraoperative transesophageal echocardiography (TEE) use among the patients undergoing cardiac valve or isolated coronary artery bypass graft (CABG) surgery. DESIGN: An observational cohort study. SETTING: This study used the Centers for Medicare and Medicaid Services administrative claims dataset of the beneficiaries undergoing valve or isolated CABG surgery between 2013 to 2015. PARTICIPANTS: Adults aged ≥65 years of age undergoing cardiac valve or isolated CABG surgery. INTERVENTIONS: Generalized linear mixed-model (GLMM) analyses were used to examine the relationship between the TEE and patient characteristics, hospital factors, and staffing differences, while accounting for clustering within hospitals. The proportion of variation in TEE use attributable to patient-level characteristics was quantified using odds ratios. Hospital-level factors and staffing differences were quantified using the median odds ratios (MOR) and interval odds ratios (IOR). MEASUREMENTS AND MAIN RESULTS: Among 261,860 patients (123,702 valve procedures and 138,158 isolated CABG), the GLMM analysis demonstrated that the strongest predictor for intraoperative TEE use was the hospital where the surgery occurred (MOR for TEE of 2.57 in valve and 4.16 in isolated CABG). The TEE staffing variable reduced the previously unexplained across-hospital variability by 9% in valve and 21% in isolated CABG, and hospitals with anesthesiologist TEE staffing (versus mixed) were more likely to use TEE in both valve and CABG (MOR for TEE of 1.21 in valve and 1.84 in isolated CABG). CONCLUSION: Hospital practice was the strongest predictor for TEE use overall. In isolated CABG surgery, hospitals with anesthesiologist TEE staffing were a primary predictor for TEE use.

Comprehensive Monitoring in Patients With Dual Lumen Right Atrium to Pulmonary Artery Right Ventricular Assist Device.

Right ventricular assist devices (RVADs) can be used in patients with acute right heart failure. A novel device that has recently been deployed is the right atrium to pulmonary artery (RA-PA) dual lumen single cannula (DLSC). One of the limitations is that it occupies a large proportion of the right ventricular outflow tract and PA; therefore, standard continuous hemodynamic monitoring with a pulmonary artery catheter is commonly not used. Serial echocardiography is pivotal for device deployment, monitoring device position, assessing RV readiness for decannulation, and surveilling for short-term complications. We performed a retrospective case series of 24 patients with RA-PA DLSC RVAD assessing echocardiographic RV progression and vasoactive infusion requirements. The overall survival was 66.6%. The average vasoactive infusion score at the time of cannulation was 24.9 ± 43.9, at decannulation in survivors 4.6 ± 4.9 vs . 25.4 ± 21.5 in nonsurvivors, and 2.7 ± 4.9 at 48 hours post decannulation. On echocardiography, the average visual estimate of RV systolic function encoded (0 = none and 5 = severe) in survivors was 3.9 ± 1.2, 2.8 ± 1.6, 2.5 ± 1.7, and 2.8 ± 1.9, respectively, and in nonsurvivors 3.8 ± 1.6 and 3.4 ± 1.8, respectively. This demonstrated an RV systolic function improvement over time in survivors as opposed to nonsurvivors. This was also demonstrated in RV size visual estimate, respectively. Quantitatively, at the predefined four timepoints, the RV:LV, tricuspid annular plane systolic excursion, and fractional area change all improve over time and there is statistically significant difference in survivors versus nonsurvivors. In this study, we describe a cohort of patients treated with RA-PA DLSC RVAD. We illustrate the critical nature of echocardiographic measures to rate the progression of RV function, improvement in vasoactive infusion requirements, and ventilator parameters with the RA-PA DLSC.

Extracorporeal CO2 reduction for COVID-19: hypercapnic respiratory failure post extracorporeal membrane oxygenation.

COVID-19-induced acute respiratory distress syndrome (ARDS) has challenged medical providers. In severe cases, patients present with poor lung compliance, requiring not only lung protective mechanical ventilation strategies, but also extracorporeal support. Due to the nature of the pandemic, the extracorporeal carbon dioxide removal device called Hemolung Respiratory Assist System became available under the Food and Drug Administration Emergency Use Authorization for patients with COVID-19-induced ARDS. This allowed application of the device to treat patients with recrudescent ARDS following an acute aspiration pneumonia following two previous veno-venous extracorporeal membrane oxidation treatment series, in the setting of hypercapnic respiratory acidosis.

Association of Intraoperative Transesophageal Echocardiography and Clinical Outcomes After Open Cardiac Valve or Proximal Aortic Surgery.

Importance: Intraoperative transesophageal echocardiography (TEE) is used frequently in cardiac valve and proximal aortic surgical procedures, but there is a lack of evidence associating TEE use with improved clinical outcomes. Objective: To test the association between intraoperative TEE use and clinical outcomes following cardiac valve or proximal aortic surgery. Design, Setting, and Participants: This matched, retrospective cohort study used national registry data from the Society of Thoracic Surgeon (STS) Adult Cardiac Surgery Database (ACSD) to compare clinical outcomes among patients undergoing cardiac valve or proximal aortic surgery with vs without intraoperative TEE. Statistical analyses used optimal matching within propensity score calipers to conduct multiple matched comparisons including within-hospital and within-surgeon matches, a negative control outcome analysis, and sensitivity analyses. STS ACSD data encompasses more than 90% of all hospitals that perform cardiac surgery in the US. The study cohort consisted of all patients aged at least 18 years undergoing open cardiac valve repair or replacement surgery and/or proximal aortic surgery between 2011 and 2019. Statistical analysis was performed from October 2020 to April 2021. Exposures: The exposure was receipt of intraoperative TEE during the cardiac valve or proximal aortic surgery. Main Outcomes and Measures: The primary outcome was death within 30 days of surgery. The secondary outcomes were (1) a composite outcome of stroke or 30-day mortality and (2) a composite outcome of reoperation or 30-day mortality. Results: Of the 872 936 patients undergoing valve or aortic surgery, 540 229 (61.89%) were male; 63 565 (7.28%) were Black and 742 384 (85.04%) were White; 711 326 (81.5%) received TEE and 161 610 (18.5%) did not receive TEE; the mean (SD) age was 65.61 years (13.17) years. After matching, intraoperative TEE was significantly associated with a lower 30-day mortality rate compared with no TEE: 3.81% vs 5.27% (odds ratio [OR], 0.69 [95% CI, 0.67-0.72]; P < .001), a lower incidence of stroke or 30-day mortality: 5.56% vs 7.01% (OR, 0.77 [95% CI, 0.74-0.79]; P < .001), and a lower incidence of reoperation or 30-day mortality: 7.18% vs 8.87% (OR, 0.78 [95% CI, 0.76-0.80]; P < .001). Results were similar across all matched comparisons (including within-hospital, within-surgeon matched analyses) and were robust to a negative control and sensitivity analyses. Conclusions and Relevance: Among adults undergoing cardiac valve or proximal aortic surgery, intraoperative TEE use was associated with improved clinical outcomes in this cohort study. These findings support routine use of TEE in these procedures.

Bridging preference-based instrumental variable studies and cluster-randomized encouragement experiments: Study design, noncompliance, and average cluster effect ratio.

Instrumental variable (IV) methods are widely used in medical research to draw causal conclusions when the treatment and outcome are confounded by unmeasured confounding variables. One important feature of such studies is that the IV is often applied at the cluster level, for example, hospitals' or physicians' preference for a certain treatment where each hospital or physician naturally defines a cluster. This paper proposes to embed such observational IV data into a cluster-randomized encouragement experiment using nonbipartite matching. Potential outcomes and causal assumptions underpinning the design are formalized and examined. Testing procedures for two commonly used estimands, Fisher's sharp null hypothesis and the pooled effect ratio (PER), are extended to the current setting. We then introduce a novel cluster-heterogeneous proportional treatment effect model and the relevant estimand: the average cluster effect ratio. This new estimand is advantageous over the structural parameter in a constant proportional treatment effect model in that it allows treatment heterogeneity, and is advantageous over the PER estimand in that it does not suffer from Simpson's paradox. We develop an asymptotically valid randomization-based testing procedure for this new estimand based on solving a mixed-integer quadratically constrained optimization problem. The proposed design and inferential methods are applied to a study of the effect of using transesophageal echocardiography during coronary artery bypass graft surgery on patients' 30-day mortality rate. R package ivdesign implements the proposed method.

Prolonged mechanical rib separation is a key element to prevent thoracic compartment syndrome in penetrating chest trauma: A case report.

Penetrating cardiac injury in trauma patients is highly morbid. Most cases do not survive long enough to manifest the severe physiologic consequences of massive blood product resuscitation, namely, thoracic compartment syndrome and right ventricular (RV) failure. This case exhibits a thoracic compartment syndrome and RV failure so severe that the open chest management required mechanical separation of a clamshell thoracotomy. The resuscitation and the techniques utilized to maintain an open chest will be described.

Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.

OBJECTIVE: This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations. METHODS: This retrospective, observational cohort study, used a random 5% sample of 770,777 fee-for-service Medicare beneficiaries with an inpatient hospitalization between 2009-2011. The machine learning algorithms tested included: support vector machine, random forest, multilayer perceptron, extreme gradient boosted tree, and logistic regression. The extreme gradient boosted tree algorithm outperformed the alternatives and was the machine learning method used for the final risk model. Primary outcome was 30-day mortality. Secondary outcomes were: rehospitalization, and any of 23 adverse clinical events occurring within 30 days of the index admission date. RESULTS: The machine learning algorithm performance was evaluated by both the area under the receiver operating curve (AUROC) and Brier Score. The risk model demonstrated high performance for prediction of: 30-day mortality (AUROC = 0.88; Brier Score = 0.06), and 17 of the 23 adverse events (AUROC range: 0.80-0.86; Brier Score range: 0.01-0.05). The risk model demonstrated moderate performance for prediction of: rehospitalization within 30 days (AUROC = 0.73; Brier Score: = 0.07) and six of the 23 adverse events (AUROC range: 0.74-0.79; Brier Score range: 0.01-0.02). The machine learning risk model performed comparably on a second, independent validation dataset, confirming that the risk model was not overfit. CONCLUSIONS AND RELEVANCE: We have developed and validated a robust, claims-based, machine learning risk model that is applicable to both medical and surgical patient populations and demonstrates comparable predictive accuracy to existing risk models.

Validation of Claims Data for the Identification of Intraoperative Transesophageal Echocardiography During Cardiac Surgery.

OBJECTIVE: The goal of this study was to assess the validity of Current Procedural Terminology (CPT) claims data for the identification of intraoperative transesophageal echocardiography (TEE) during cardiac surgery. DESIGN: This study was a retrospective, cohort analysis. SETTING: This study used data from electronic medical records (EMRs), in combination with CPT billing claims data, from two hospitals within the Penn Medicine Health System-Penn Presbyterian Medical Center and the Hospital of the University of Pennsylvania. PARTICIPANTS: The cohort consisted of adult patients, aged ≥18 years, undergoing open cardiac valve surgery (repair or replacement), coronary artery bypass graft surgery, or aortic surgery between April 1 and October 31, 2019. INTERVENTIONS: Agreement between TEE identified using CPT billing code(s) (93312-8 with or without 93320-1 or 93325) and TEE identified by manual EMR review. MEASUREMENTS AND MAIN RESULTS: As identified by a reference standard (ie, EMR review) of the 873 cases that met inclusion criteria, 867 (99.31%) cases were performed with TEE and six cases were performed without TEE (<1%). Of the 867 cases performed with TEE, CPT code(s) correctly identified 866 cases, as indicated by having at least one of the CPT codes (93312-8 with or without 93320-1 or 93325). These CPT codes identified intraoperative TEE with a 99.88% sensitivity, 100.00% specificity, 100.00% positive predictive value, and 85.71% negative predictive value. When billing claims for TEE were restricted to the CPT code 93312 alone, the results were identical. CONCLUSIONS: Billing claims using CPT code(s) identified true intraoperative TEE with a high sensitivity, specificity, excellent positive predictive value, and moderate negative predictive value. These results demonstrated that claims data are a valuable data source from which to study the effect of TEE in cardiac surgical patients.

Association between Transesophageal Echocardiography and Clinical Outcomes after Coronary Artery Bypass Graft Surgery.

BACKGROUND: Coronary artery bypass graft (CABG) surgery is the most widely performed cardiac surgery in the United States. Transesophageal echocardiography (TEE) is frequently used in a variety of cardiac surgical procedures, but its clinical benefit in isolated CABG surgery is unclear, and guidelines remain indeterminate. The aim of this study was to compare clinical outcomes among patients undergoing isolated CABG surgery with versus without TEE in order to test the hypothesis that TEE would be associated with improved clinical outcomes after CABG surgery. METHODS: A matched retrospective cohort study was conducted among Medicare beneficiaries undergoing isolated CABG surgery with versus without intraoperative monitoring using TEE in the United States. The primary analysis was a near/far instrumental variable match that paired hospitals with similar characteristics and patient populations but with opposing probabilities for using TEE in CABG surgery. Outcomes included 30-day mortality, a composite outcome of stroke or 30-day mortality, length of hospitalization, and incidence of esophageal perforation. RESULTS: Of 114,871 patients undergoing isolated CABG surgery, 65,471 (57%) underwent TEE and 49,400 (43%) did not. Hospital-level instrumental variable matched analysis demonstrated that among the subset of 968 matched hospitals, TEE receipt was associated with lower 30-day mortality (3.7% vs 4.9%, P < .001), a lower incidence of the composite outcome of stroke or 30-day mortality (4.5% vs 5.6%, P < .001), no difference in length of hospitalization (10.32 vs 10.52 days, P = .26), and no difference in the incidence of esophageal perforation (0.01% vs 0.01%, P = .63). These results were replicated in surgeon-level and patient-level matched-pair instrumental variable analyses, and all analyses were robust to sensitivity analyses that tested for biases introduced by unmeasured confounding. CONCLUSIONS: The findings from this study suggest that TEE may offer a clinical benefit to cardiac surgical patients undergoing isolated CABG surgery.