Machine Learning and Natural Language Processing to Improve Classification of Atrial Septal Defects in Electronic Health Records.

Background: International Classification of Disease (ICD) codes can accurately identify patients with certain congenital heart defects (CHDs). In ICD-defined CHD data sets, the code for secundum atrial septal defect (ASD) is the most common, but it has a low positive predictive value for CHD, potentially resulting in the drawing of erroneous conclusions from such data sets. Methods with reduced false positive rates for CHD among individuals captured with the ASD ICD code are needed for public health surveillance.

A Generalized Machine Learning Model for Identifying Congenital Heart Defects (CHDs) Using ICD Codes.

Background: International Classification of Diseases (ICD) codes utilized for congenital heart defect (CHD) case identification in datasets have substantial false-positive (FP) rates. Incorporating machine learning (ML) algorithms following case selection by ICD codes may improve the accuracy of CHD identification, enhancing surveillance efforts.

Methods: Traditional ML methods were applied to four encounter-level datasets, 2010-2019, for 3334 patients with validated diagnoses and with at least one CHD ICD code identified.

ASPEN survey of parenteral nutrition access issues: How the system fails the patient.

Background: Product shortages and a lack of qualified providers to manage care may impact the safety and efficacy of parenteral nutrition (PN). This survey assessed the frequency and extent to which limitations to PN-related access affects patients.

Methods: Outpatient/patients receiving home PN were surveyed.

Cardiovascular disease risk factors in congenital heart disease survivors are associated with heart failure.

Background: Despite advances in treatment and survival, individuals with congenital heart defects (CHD) have a higher risk of heart failure (HF) compared to the general population.

Objective: To evaluate comorbidities associated with HF in patients with CHD with a goal of identifying potentially modifiable risk factors that may reduce HF-associated morbidity and mortality.

Methods: Five surveillance sites in the United States linked population-based healthcare data and vital records.

Racial and Ethnic Disparities in Health Care Usage and Death by Neighborhood Poverty Among Individuals With Congenital Heart Defects, 4 US Surveillance Sites, 2011 to 2013.

Background: Socioeconomic factors may lead to a disproportionate impact on health care usage and death among individuals with congenital heart defects (CHD) by race, ethnicity, and socioeconomic factors. How neighborhood poverty affects racial and ethnic disparities in health care usage and death among individuals with CHD across the life span is not well described.

Methods And Results: Individuals aged 1 to 64 years, with at least 1 CHD-related () code were identified from health care encounters between January 1, 2011, and December 31, 2013, from 4 US sites.

Anatomic and physiologic classification of adults with congenital heart disease to predict adverse outcomes: Use of administrative codes compared to clinical staging.

Background: The 2018 anatomic physiologic (AP) classification American Heart Association/American College of Cardiology (AHA/ACC) Guidelines for Adults with Congenital Heart Disease (ACHD) encompasses both native and post-operative anatomy and physiology to guide care management. As some physiologic conditions and post-operative states lack specific International Classification of Diseases (ICD) 9- Clinical Modification (CM) and 10-CM codes, an ICD code-based classification approximating the ACHD AP classification is needed for population-based studies.

Methods: A total of 232 individuals, aged ≥ 18 years at the time of a health encounter between January 1, 2010 and December 31, 2019 and identified with at least one of 87 ICD codes for a congenital heart defect were validated through medical chart review.

High sensitivity troponin I as a biomarker for cardiac allograft vasculopathy: Evaluation of diagnostic potential and clinical utility.

Introduction: Cardiac allograft vasculopathy (CAV) limits long-term survival in heart transplant (HTx) recipients. The use of biomarkers in CAV surveillance has been studied, but none are used in clinical practice. The predictive value of high-sensitivity troponin I (hsTnI) has not been extensively investigated in HTx recipients.

Positive Predictive Value of , and , Codes for Identification of Congenital Heart Defects.

Background Administrative data permit analysis of large cohorts but rely on (), and () codes that may not reflect true congenital heart defects (CHDs). Methods and Results CHDs in 1497 cases with at least 1 encounter between January 1, 2010 and December 31, 2019 in 2 health care systems, identified by at least 1 of 87 / CHD codes were validated through medical record review for the presence of CHD and CHD native anatomy. Interobserver and intraobserver reliability averaged >95%.

Supervised Text Classification System Detects Fontan Patients in Electronic Records With Higher Accuracy Than Codes.

Background The Fontan operation is associated with significant morbidity and premature mortality. Fontan cases cannot always be identified by () codes, making it challenging to create large Fontan patient cohorts. We sought to develop natural language processing-based machine learning models to automatically detect Fontan cases from free texts in electronic health records, and compare their performances with code-based classification.

Evaluation of right ventricular strain in two separate cohorts with precapillary pulmonary hypertension.

Evaluation for right ventricular (RV) dysfunction is an important part of risk assessment in care of patients with pulmonary hypertension (PH) as it is associated with morbidity and mortality. Echocardiography provides a widely available and acceptable method to assess RV function. RV global longitudinal strain (RVGLS), a measure of longitudinal shortening of RV deep muscle fibers obtained by two-dimensional echocardiography, was previously shown to predict short-term mortality in patients with PH.

Health Care Usage Among Adolescents With Congenital Heart Defects at 5 Sites in the United States, 2011 to 2013.

Background We sought to characterize health care usage for adolescents with congenital heart defects (CHDs) using population-based multisite surveillance data. Methods and Results Adolescents aged 11 to 18 years with ≥1 CHD-related diagnosis code and residing in 5 US sites were identified in clinical and administrative data sources for the years 2011 to 2013. Sites linked data on all inpatient, emergency department (ED), and outpatient visits.

How Well Do Codes Predict True Congenital Heart Defects? A Centers for Disease Control and Prevention-Based Multisite Validation Project.

Background The Centers for Disease Control and Prevention's Surveillance of Congenital Heart Defects Across the Lifespan project uses large clinical and administrative databases at sites throughout the United States to understand population-based congenital heart defect (CHD) epidemiology and outcomes. These individual databases are also relied upon for accurate coding of CHD to estimate population prevalence. Methods and Results This validation project assessed a sample of 774 cases from 4 surveillance sites to determine the positive predictive value (PPV) for identifying a true CHD case and classifying CHD anatomic group accurately based on 57 codes.

Initial attendance and retention in adult healthcare as criteria for transition success among organ transplant recipients.

Background: Adolescent and young adult (AYA) solid organ transplant recipients experience worsening medical outcomes during transition to adult healthcare. Current understanding and definitions of transition success emphasize first initiation of appointment attendance in adult healthcare; however, declines in attendance over time after transfer remain possible, particularly as AYAs are further removed from their pediatric provider and assume greater independence in their care.

Methods: The current study assessed health-care utilization, medical outcomes, and transition success among 49 AYA heart, kidney, or liver recipients recently transferred to adult healthcare.

Individuals aged 1-64 years with documented congenital heart defects at healthcare encounters, five U.S. surveillance sites, 2011-2013.

Background: Many individuals born with congenital heart defects (CHD) survive to adulthood. However, population estimates of CHD beyond early childhood are limited in the U.S.

Single-Barrel, Double-Barrel, and Fenestrated Endografts to Facilitate Transcatheter Pulmonary Valve Replacement in Large RVOT.

Objectives: The aim of this study was to test the hypothesis that narrowing the landing zone using commercially available endografts would enable transcatheter pulmonary valve replacement (TPVR) using commercially available transcatheter heart valves.

Background: TPVR is challenging in an outsized native or patch-repaired right ventricular outflow tract (RVOT). Downsizing the RVOT for TPVR is currently possible only using investigational devices.

Bleeding and thrombotic risk in pregnant women with Fontan physiology.

Background/objectives: Pregnancy may potentiate the inherent hypercoagulability of the Fontan circulation, thereby amplifying adverse events. This study sought to evaluate thrombosis and bleeding risk in pregnant women with a Fontan.

Methods: We performed a retrospective observational cohort study across 13 international centres and recorded data on thrombotic and bleeding events, antithrombotic therapies and pre-pregnancy thrombotic risk factors.

Hepatocellular carcinoma and the Fontan circulation: Clinical presentation and outcomes.

Background: Fontan-associated liver disease (FALD) is universal in patients with a Fontan circulation. Hepatocellular carcinoma (HCC) is one of its severe expressions, and, though rare, frequently fatal. The purpose of this study was to describe the clinical presentation, risk factors, and outcomes of HCC in patients with a Fontan circulation.

Predicting 30-day readmission after congenital heart surgery across the lifespan.

Introduction: Hospital readmission is an important driver of costs among patients with CHD. We assessed predictors of 30-day rehospitalisation following cardiac surgery in CHD patients across the lifespan.

Methods: This was a retrospective analysis of 981 patients with CHD who had cardiac surgery between January 2011 and December 2012.

Characteristics of Adults With Congenital Heart Defects in the United States.

Background: In the United States, >1 million adults are living with congenital heart defects (CHDs), but gaps exist in understanding the health care needs of this growing population.

Objectives: This study assessed the demographics, comorbidities, and health care use of adults ages 20 to 64 years with CHDs.

Methods: Adults with International Classification of Disease-9th Revision-Clinical Modification CHD-coded health care encounters between January 1, 2008 (January 1, 2009 for Massachusetts) and December 31, 2010 were identified from multiple data sources at 3 U.

Motivations, Barriers, and Outcomes of Patient-Reported Shared Decision Making in Eosinophilic Esophagitis.

Background: Little is known about patient choice in treatment of eosinophilic esophagitis (EoE).

Aim: Determine motivators and barriers to using common EoE therapies and describe patient-reported shared decision making (SDM) and satisfaction with treatment.

Methods: We developed and administered a Web-based survey on factors influencing EoE treatment choice, SDM, and satisfaction.

High Patient Disease Burden in a Cross-sectional, Multicenter Contact Registry Study of Eosinophilic Gastrointestinal Diseases.

Objectives: Clinical features of eosinophilic esophagitis (EoE) have been well-described in the literature, however, characterization of features experienced by patients with other eosinophilic gastrointestinal diseases (EGIDs) is lacking. Using data collected from a patient contact registry, we sought to characterize and contrast patient-reported gastrointestinal and extragastrointestinal symptoms and comorbidities in non-EoE EGIDs, including eosinophilic gastritis, gastroenteritis and colitis, relative to EoE.

Methods: We conducted a cross-sectional study of contact registry data collected from 2015 to 2018.