Machine Learning Quantification of Pulmonary Regurgitation Fraction from Echocardiography.

Assessment of pulmonary regurgitation (PR) guides treatment for patients with congenital heart disease. Quantitative assessment of PR fraction (PRF) by echocardiography is limited. Cardiac MRI (cMRI) is the reference-standard for PRF quantification. We created an algorithm to predict cMRI-quantified PRF from echocardiography using machine learning (ML). We retrospectively performed echocardiographic measurements paired to cMRI within 3 months in patients with ≥ mild PR from 2009 to 2022. Model inputs were vena contracta ratio, PR index, PR pressure half-time, main and branch pulmonary artery diastolic flow reversal (BPAFR), and transannular patch repair. A gradient boosted trees ML algorithm was trained using k-fold cross-validation to predict cMRI PRF by phase contrast imaging as a continuous number and at > mild (PRF ≥ 20%) and severe (PRF ≥ 40%) thresholds. Regression performance was evaluated with mean absolute error (MAE), and at clinical thresholds with area-under-the-receiver-operating-characteristic curve (AUROC). Prediction accuracy was compared to historical clinician accuracy. We externally validated prior reported studies for comparison. We included 243 subjects (median age 21 years, 58% repaired tetralogy of Fallot). The regression MAE = 7.0%. For prediction of > mild PR, AUROC = 0.96, but BPAFR alone outperformed the ML model (sensitivity 94%, specificity 97%). The ML model detection of severe PR had AUROC = 0.86, but in the subgroup with BPAFR, performance dropped (AUROC = 0.73). Accuracy between clinicians and the ML model was similar (70% vs. 69%). There was decrement in performance of prior reported algorithms on external validation in our dataset. A novel ML model for echocardiographic quantification of PRF outperforms prior studies and has comparable overall accuracy to clinicians. BPAFR is an excellent marker for > mild PRF, and has moderate capacity to detect severe PR, but more work is required to distinguish moderate from severe PR. Poor external validation of prior works highlights reproducibility challenges.

PREVALENCE AND TYPES OF GENDER-AFFIRMING SURGERY AMONG A SAMPLE OF TRANSGENDER ENDOCRINOLOGY PATIENTS PRIOR TO STATE EXPANSION OF INSURANCE COVERAGE.

OBJECTIVE: Transgender individuals now have many options for medical intervention, including gender-affirmation surgeries. However, it is unknown how common it is for transgender individuals to undergo these surgeries. The purpose of this cross-sectional study was to assess the prevalence of gender-affirming surgeries among transgender patients in 2015, which was immediately prior to insurance changes that made gender-affirming surgery more affordable for Massachusetts residents. METHODS: A retrospective chart review of 99 transgender patients was performed at the Endocrinology Clinic at Boston Medical Center, an urban safety net hospital. The records for 99 transgender subjects who received treatment between 2004-2015, including 28 transmen and 71 transwomen, were examined. The outcome measures were the types of medical interventions chosen by transgender patients, which included hormone therapy, chest surgery, gonadectomy, genital surgery, and facial surgery. RESULTS: Thirty-five percent of subjects had undergone at least one gender-affirming surgery. Transmen were more likely to have had surgery than transwomen (54% vs. 28%). Twenty-five percent of patients had chest surgery, 13% had genital surgery or gonadectomy, and 8% had facial surgery. CONCLUSION: In 2015, a majority of transgender endocrinology clinic patients had not undergone any type of gender-affirmation surgery. Among those who did elect to have a surgery, genital surgery or gonadectomy were uncommon. The low rate of surgery among this sample of transgender patients may be attributable to the financial cost, lack of interest in surgery, or that genital surgery is not a high priority for transgender individuals relative to surgery to change visible features such as face and chest. Abbreviation: HT = hormone therapy.

Exercise-Induced Electrocardiography Changes in Pulmonary Arterial Hypertension.

Cardiopulmonary exercise testing (CPET) is an important tool in assessing the functional status of patients with pulmonary arterial hypertension (PAH). During CPET, continuous electrocardiography (ECG) is used as a marker of exercise-induced ischemia or arrhythmia. We hypothesize that ECG changes with exercise may be an early indicator of clinical worsening in PAH and could predict adverse outcomes. Clinical, hemodynamic, and CPET data of 155 children and young adult patients with PAH who underwent CPET between 2012 and 2019 in our pulmonary hypertension (PH) center were included in this retrospective analysis. ECGs were analyzed for ST depressions and T-wave inversions, along with coincident hemodynamic data. These data were correlated with adverse outcomes divided into 2 categories: severe worsening (death or receiving lung transplant) and mild to moderate worsening (PAH medication escalation, hospitalization, shunt creation, or listing for lung transplant). The median age was 19 years (range 7 to 40 years), 69% were female, and the average follow-up time was 5 years (range 1 to 8 years). A total of 63 patients (41%) had at least 1 adverse outcome. A total of 39 patients (25%) demonstrated significant ST-T-wave changes with exercise. Patients with ST-T-wave changes were 20% more likely to die or need lung transplant than those without. The multiple linear regression found that ST-T-wave changes were a predictor of elevated mean pulmonary arterial pressure (mPAP) found on catheterization (R = 0.489, p = 0.003), although not of pulmonary vascular resistance index (R = -0.112, p = 0.484). An mPAP of 55 mm Hg was the most sensitive and specific point in identifying when ST-T-wave changes with exercise begin to appear. In conclusion, ST-T-wave changes on exercise ECG are significantly associated with adverse outcomes in PH in a medium-term follow-up study, and the presence of ST-T-wave changes correlates with higher mPAP. These ECG changes with exercise may be used as early indicators of clinical worsening in PH and predictors of adverse outcomes.