DuBrock, Hilary M.

Abstract Rationale Pulmonary arterial hypertension (PAH) is a rare and progressive disease, where the guideline-recommended diagnostic confirmation is via right heart catheterization (RHC). However, due to non-specific symptomology, patients often experience delays in diagnosis that potentially impact disease outcomes. We sought to develop a machine learning (ML) based approach for early and appropriate detection of PAH. Methods Three cohorts were derived from Mayo Clinic electronic health record (EHR): confirmed PAH (N = 1,169), No PH (N = 11,600) and Other PH (Group 2-5 PH, N = 817), based on 2022 ESC/ERS guidelines. The study index was defined as the earliest diagnosis dates for PH cohorts (PAH & Other PH) or the latest PH negative echocardiogram (ECHO) or RHC for the No-PH cohort. Patients included in the study had at least one symptom (dyspnea, fatigue, syncope, chest pain, or lower extremity swelling) within one year prior to the study index. A two-step sequential ML modelling strategy was applied: Step 1 differentiated PH (PAH + Other PH) from No PH and step 2 differentiated PAH from Other PH. Models were trained using a combination of structured data, unstructured clinical notes to detect symptoms using natural language processing and ECG waveforms captured one year prior to study index. Models were tested both with and without ECHO parameters. SHAP (SHapley Additive explanations) values were used to determine important features contributing to models (without ECG waveforms). Results Models including ECHO parameters performed better compared to those without (Figure 1). The top feature impacting model without ECHO parameters was dyspnea in the preceding three months followed by heart failure and systolic blood pressure for the PH vs no PH; and T wave peak in V1 and ANA level in PAH vs other PH cohort. The top feature impacting model with ECHO was tricuspid regurgitation velocity followed by heart failure and right atrial pressure for the PH vs no PH; and mean blood pressure and left ventricular diameter in the PAH vs other PH cohort. Figure 1: Model performance in the two-step sequential approach PR-AUC=Precision Recall-Area Under Curve Conclusion This study demonstrates that ML models can aid in the identification of PAH in symptomatic patient populations. While ECG can identify patients for further testing, ECHO can further increase the accuracy and the need to refer patients to RHC for confirming diagnosis of PAH. This abstract is funded by: Merck & Co., Inc., Rahway, NJ, USA

ABSTRACT Clinical worsening events are increasingly recognized as a meaningful outcome in pulmonary arterial hypertension (PAH). We applied machine‐learning models to real‐world data to identify clinical features that may predict clinical worsening events in PAH. Data were obtained retrospectively from the electronic health records of adults diagnosed with PAH at Mayo Clinic locations (January 2015–December 2019). Machine‐learning LASSO regularized logistic regression models were developed to analyze the association between 100 clinical features and occurrence of clinical worsening events. In total, 455 patients were included (mean age 62.1 years; 59.3% female). Of these, 232 (51.0%) experienced a clinical worsening event after a median (quartile 1, quartile 3) of 10.9 (4.1, 21.4) months. The best‐performing model had an area under the curve of 0.78, sensitivity of 78%, and specificity of 59%. The model identified 11 clinical features associated with clinical worsening events in PAH with a non‐zero coefficient: baseline age, body mass index (BMI), creatinine level, red cell (erythrocyte) distribution width (RDW), mean pulmonary arterial pressure, pulmonary vascular resistance, sodium concentration, and QT interval, along with dyspnea, number of clinic visits, and other forms of heart disease within a 1‐month window before a clinical worsening event. Baseline RDW and BMI, and number of clinic visits within the 1‐month window were statistically significantly associated with clinical worsening events. Our study used machine‐learning models to identify clinical features associated with risk of clinical worsening events in PAH. Automation of risk prediction could lead to earlier therapeutic intervention to optimize patient outcomes.

ABSTRACT In normal health, the liver and lungs enjoy a close anatomic, physiologic, and functional relationship. In the context of pulmonary vascular disease, however, there is accumulating evidence that the interplay between the gut microbiome, hepatic system, and pulmonary vasculature (so‐called “gut‐liver‐lung” axis) plays an important role in driving disease pathogenesis and determining clinical outcomes. Despite recognizing the importance of the gut‐liver‐lung axis in pulmonary vascular disease however, little is known about the clinical characteristics, circulating factors, and physiologic pathways that mediate this important axis of communication. In this clinical and translationally focused review, we provide an overview of liver‐lung communication in normal physiology, and contrast this with gut‐liver‐lung derangements in pulmonary arterial hypertension, portopulmonary hypertension, and hepatopulmonary syndrome. We conclude with identifying key gaps in knowledge that will need to be addressed in order to manipulate the gut‐liver‐lung axis to prevent worsening pulmonary vascular disease, develop novel therapeutics, and improve patient outcomes.

ABSTRACT Pulmonary arterial hypertension (PAH) is a progressive disease with significant morbidity and mortality. Due to nonspecific symptoms, diagnosis can be challenging and subject to substantial delays. Using data from Mayo Clinic′s electronic health records, we looked at causes of delayed diagnosis and whether earlier diagnosis means better outcomes. This retrospective cohort study included adults with PAH confirmed by right heart catheterization (RHC) between 2015 and 2019. Univariate and multivariate analyses evaluated the association of 229 clinical and laboratory features with time to PAH diagnosis and survival outcomes. Early diagnosis was defined as < 6 months and a delayed diagnosis as ≥ 22.2 months from an eligible event. Survival probability was determined using Kaplan‐Meier analysis . The study enrolled 160 patients. The most common initial PAH symptoms were dyspnea (42.5%) and fatigue (16.9%). It took a median of 7, 13, 26, and 123 days from eligible event to the first X‐ray, electrocardiogram, echocardiogram, and RHC, respectively. Factors most closely associated with delayed diagnosis were chronic obstructive pulmonary disease, normal creatinine, high systolic blood pressure, acute respiratory infection, normal iron, normal diastolic blood pressure, and being male aged 18.5 to < 25 years. Compared with delayed diagnosis patients (22.6%), more early diagnosis patients saw a pulmonologist (35.3%) before another provider. After 5 years, 73% of patients in the early diagnosis and 31% in the delayed diagnosis group were still alive. This study identified factors associated with a delayed diagnosis of PAH and found that earlier diagnosis and treatment initiation were associated with significantly improved survival.

Background: Pulmonary hypertension (PH) is a life-threatening disease affecting up to 1% of the global population. Diagnosis can be challenging and is often delayed due to the need for advanced imaging and invasive procedures. The use of artificial intelligence applied to ECGs (ECG-AI) has been shown to detect subtle patterns in voltage-time data and may be a valuable tool for the early detection of PH. Hypothesis and Purpose: To evaluate the performance of a previously trained, ECG-AI algorithm to detect PH (ECG-AI PH) using real-world data (RWD) collected in a multicenter, validation study. A joint primary hypothesis required sensitivity (Sn), specificity (Sp), positive predictive value (PPV), and negative predictive value (NPV) to exceed the null values of 76%, 70%, 10% and 90%. Study Design and Methods: This retrospective validation study was conducted at 5 geographically diverse U.S. health systems. Adult subjects were eligible for inclusion if they had a 12-lead ECG paired with an echocardiogram (Echo) in which tricuspid regurgitation velocity (TRV) was recorded, following presentation with dyspnea. Patients were classified according to echocardiographic criteria as either PH (PH+, TRV >3.4 m/s) or controls (PH-, TRV ≤2.8 m/s) to simulate the real-world use of ECG-AI, where a positive result could lead to a follow-up Echo. The study database was locked before processing the digital ECGs with ECG-AI PH. Performance was also estimated in a subset of subjects that later had a right heart catheterization using mPAP ≥ 20mmHg as the definition of PH. Results: A total of 14281 subjects (53% female, 63% aged 50+ years) met the inclusion criteria, including 3019 PH+ cases and 11262 PH- controls (Figure). Sn and Sp were 84.0% (95% CI: 82.6%, 85.3%) and 71.7% (95% CI: 70.9%, 72.6%), respectively. The positive and negative predictive values were 18.9% (95% CI: 18.4%, 19.4%) and 98.3% (95% CI: 98.1%, 98.4%), respectively, at 7.3% prevalence. Each endpoint met pre-defined performance criteria. In the subset of 1683 subjects with a follow up RHC, performance remained robust (Sn 85% (1155/1358); Sp 46% (151/325)). Conclusion: While ECG-AI PH was first developed as an investigational tool to detect PH, continued development as software as a medical device for clinical use demonstrated that the algorithm retained strong performance to detect PH in diverse, non-overlapping clinical settings and patient populations.

Introduction: Pulmonary hypertension (PH) is a life-threatening, progressive disease with non-specific symptoms, often leading to delayed diagnosis. Early identification of World Health Organization Group 1 (Pulmonary Arterial Hypertension, PAH) and Group 4 (Chronic Thromboembolic Pulmonary Hypertension, CTEPH) is essential, as effective therapies can improve outcomes. Hypothesis: An electrocardiogram-based AI algorithm for PH detection (ECG-AI PH) may enable earlier diagnosis and reduce healthcare utilization, including hospitalizations and procedures. Methods: Retrospective analysis used a de-identified data platform of >7M clinical records from a multistate integrated health system. Adult precapillary PH patients (mPAP >20 mmHg, PVR >2 WU, PCWP ≤15 mmHg) were identified as PAH or CTEPH based on ICD codes, use of approved therapies, or surgical interventions (for CTEPH) between 2002 and 2024. ECG-AI PH was applied to ECGs within 30 days of diagnostic right heart catheterization, using a 5:1 randomly sampled PH-negative control cohort. Training set patients were excluded. Clinical event frequency was compared between two intervals: from first possible PH symptom (dyspnea, syncope, chest pain, fatigue, lower limb swelling) to diagnosis, and from symptom onset to first positive ECG-AI PH prediction. Results: A total of 1882 PAH and 359 CTEPH patients met inclusion criteria. Of these, 1340 PAH and 258 CTEPH patients had symptom codes prior to diagnosis. Both groups showed prolonged intervals from symptom onset to diagnosis, with multiple diagnostic procedures and hospitalizations (Figure). ECG-AI PH performance evaluation on the test set included 647 PAH and 152 CTEPH patients. ECG-AI PH achieved AUCs of 0.90 and 0.89 for PAH and CTEPH, sensitivities of 80.3% and 76.8%, and specificities of 83.4% and 82.4%. Among those tested, 576 PAH and 95 CTEPH patients had a positive ECG-AI PH prediction after symptom onset but before diagnosis. Compared to the current patient journey, the interval between initial symptoms and a positive output from ECG-AI PH was shorter and had fewer diagnostic tests/visits. Conclusion: ECG-AI PH demonstrated strong performance in detecting PAH and CTEPH. It may reduce diagnostic delays, support earlier PH-focused screening (e.g., echocardiograms evaluating the right heart), enable earlier intervention, and reduce pre-diagnosis healthcare burden, benefitting both patient outcomes and healthcare system efficiency.

Abstract Rationale Pulmonary hypertension (PH) is associated with significant morbidity and mortality. Ground-glass opacities (GGOs) are common in Group 1 PH, but their clinical significance is unclear. Objectives We sought to characterize the clinical features and outcomes of patients with Group 1 PH with and without GGOs in the PVDOMICS study, a prospective multicenter cohort study aimed at deep phenotyping PH. Methods Patients with incident and prevalent PH were enrolled across seven U.S. centers. We included patients with Group 1 PH and excluded those with parenchymal lung disease or without chest imaging, resulting in a cohort of 242 patients. Results GGOs were common among patients with Group 1 PH (43% prevalence), associated with female sex, younger age, prostanoid use, and longer disease duration. GGOs were more common among patients with familial pulmonary arterial hypertension and pulmonary veno-occlusive disease. GGOs were associated with established markers of disease severity, including echocardiographic (right ventricular systolic pressure and tricuspid annular plane systolic excursion), biomarkers (N-terminal pro B-type natriuretic peptide), and worse hemodynamics (higher mean pulmonary artery pressure, pulmonary vascular resistance, and pulmonary artery wedge pressure). GGOs were associated with worse transplant-free survival (hazard ratio, 2.49; 95% confidence interval = 1.43–4.32; P = 0.001) and had independent prognostic value for predicting transplant-free survival after adjusting for European Society of Cardiology and European Respiratory Society risk stratification (hazard ratio, 2.19; 95% confidence interval = 1.20–3.99; P = 0.01). Conclusions Overall, GGOs were associated with specific clinical characteristics and disease phenotypes, as well as worse hemodynamics, longer disease duration, prostanoid use, and worse survival. Future studies evaluating the pathophysiology and “omic” correlates of GGOs are warranted. Clinical trial registered with www.clinicaltrials.gov (NCT02980887).