(New York, NY – May 19, 2026) – Pulmonologists and experts in respiratory medicine from the Mount Sinai Health System will present new research at the American Thoracic Society (ATS) 2026 International Conference in Orlando from May 15–May 20. Mount Sinai doctors and researchers are available to comment on their presentations, as well as breaking and trending respiratory topics.
Sessions and Symposiums
*All abstracts listed below are under embargo until the scheduled start time of the event*:
Sunday, May 17
11:30 am – 1:15 pm ET
Location: Area H, Halls WA2-WA3 (Level II, OCCC West Concourse)
A32 MAPPING THE ASTHMA LANDSCAPE: A DEEP DIVE INTO COMPREHENSIVE PHENOTYPING AND INHALED INNOVATIONS
Poster Board # P1414 Assessing Inflammatory and Clinical Markers in Predicting Asthma Exacerbations in Real-world and Genomic Data-based Asthma Insights Through Network Analysis (REGAIN) Cohort
• A major goal of asthma care is to reduce exacerbations. Recent secondary analysis of clinical trials suggest that blood eosinophils (BEC) and exhaled nitric oxide (FeNO) have significant weight in prognostication of future asthma exacerbations. FeNO reflects type 2 activity in the airway and the chemotactic pull to the airways. BEC reflects circulating IL-5 and available effector cells. The predictive value of these biomarkers for exacerbation risk in routine subspecialty care is less understood. This research assesses prognostic value of type 2 inflammatory biomarkers and clinical characteristics in predicting future asthma exacerbations in a specialty clinic population.
Scientific Abstract
Co-Authors: Michelle Duong, MD, Pulmonary and Critical Care Fellow at The Mount Sinai Hospital; Linda Rogers, MD, FCCP, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai; and Clinical Director of the Adult Asthma Program at the Mount Sinai Respiratory Institute
11:30 am – 1:15 pm ET
Location: Area B, Halls WA2-WA3 (Level II, OCCC West Concourse)
A80-1 BEYOND AHI: COGNITIVE, NEURAL, AND PAIN CONSEQUENCES OF SLEEP-DISORDERED BREATHING
Poster Board # P196 Longitudinal Effect of Sleep Apnea Burdens on Plasma Alzheimer’s Disease Biomarker in Cognitively Normal Older Adults
• Obstructive Sleep Apnea (OSA) is common in the elderly, and may accelerate amyloid accumulation in the brain. To assess OSA’s potential mechanistic contributions, the researchers explored longitudinal effects of sleep apnea burdens on the plasma beta-amyloid (Aβ) 42/40 ratio in cognitively normal older adults.
Scientific Symposium
Co-author: Andrew Varga, MD, neuroscientist and physician at The Mount Sinai Integrative Sleep Center; Associate Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai
2:15 – 4:15 pm ET
Location: W202 (Level II, OCCC West Concourse)
A103 BEYOND ONE-SIZE-FITS-ALL: DOSE, TIMING, AND CONTEXT IN MODERN DAY CRITICAL CARE
Poster Board # 118 Temporal Stability and Performance Drift of a Deployed AI Clinical Deterioration Prediction Model
• As AI clinical decision support models become increasingly integrated into hospital workflows, ongoing evaluation of deployed models is essential to detect performance drift. Despite growing deployment of clinical AI systems, few studies have reported real-world, longitudinal evaluation of model performance. The researchers evaluated the temporal stability of MEWS++, a clinical deterioration prediction model, deployed in production to monitor patients admitted to step-down units in a large tertiary care medical center.
Scientific Abstract
Co-Author: Pranai Tandon, MD, Assistant Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai
3:30 – 3:45 pm ET
Location: W304 E-H (Level III, OCCC West Concourse)
A90 ONE AIRWAY, MANY OUTCOMES: RETHINKING ASTHMA AND COPD ACROSS THE LIFESPAN
From Wheeze to Obstruction: Is it Possible to Integrate Asthma and COPD Guidelines?
• This session challenges the traditional dichotomy between asthma and COPD by exploring their overlapping features and shared mechanisms. While historically treated as distinct diseases, recent research highlights common pathways in inflammation, airway remodeling, and immune response. The talk will examine clinical, molecular, and imaging data that blur the boundaries between the two conditions, and discuss how a more integrated understanding could reshape diagnosis, treatment, and research strategies. Objectives are 1.) differentiate the key pathobiological features of asthma and COPD, and identify areas of mechanistic and clinical overlap; 2.) evaluate recent clinical trial data, including the use of biologics such as dupilumab, and their implications for treating COPD with type 2 inflammation; and 3.) apply current knowledge to improve diagnostic accuracy including imaging outcomes and biomarkers
Scientific Symposium
Speaker: Monica Kraft, MD, Chair of the Department of Medicine, Mount Sinai Health System
Monday, May 18
10:15 – 10:27 am ET
Location: West F1 (Level II, OCCC West Concourse)
B20 MODERN METRICS: ENDOTYPES, PHENOTYPES, AND STATE-OF-THE-ART SIGNAL ANALYSIS IN SLEEP-DISORDERED BREATHING
Determinants of Divergent Cardiovascular Outcomes in Obstructive Sleep Apnea: Myocardial Infarction vs. Stroke/Transient Ischemic Attack in the Sleep Apnea Cardiovascular Endpoints (SAVE) Trial
• A large body of literature shows that Obstructive Sleep Apnea (OSA) is associated with broad cardiovascular outcomes, like heart attacks and stroke. Yet the main treatment for OSA—Continuous Positive Airway Pressure (CPAP)—has not been shown in trials to reduce the likelihood of cardiovascular events broadly for such patients with OSA. The researchers studied if there was a “different risk” between OSA characteristics, such as variables from sleep studies, and individual events of heart attack or stroke—rather than grouping all cardiovascular events together. The experts looked at the SAVE trial data, a previous large randomized controlled trial, to determine such signals within the data set.
Scientific Abstract
Co-Author: Jason Lynch, MD, Internal Medicine Resident at the Icahn School of Medicine at Mount Sinai; Vaishnavi Kundel, MD, Associate Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Program Director of the Sleep Medicine Fellowship at the Icahn School of Medicine at Mount Sinai
10:27 – 10:39 am ET
Location: West F1 (Level II, OCCC West Concourse)
B20 MODERN METRICS: ENDOTYPES, PHENOTYPES, AND STATE-OF-THE-ART SIGNAL ANALYSIS IN SLEEP-DISORDERED BREATHING
Associations of Polysomnography Metrics With Myocardial Infarction and Stroke Risk in Obstructive Sleep Apnea: Findings From the Multi-Ethnic Study of Atherosclerosis
• Obstructive sleep apnea (OSA) may have differential effects on stroke and heart attack risk and studying individual cardiovascular outcomes rather than composite cardiovascular endpoints reveal additional nuance. Apnea-Hypopnea Index (AHI) is a widely used clinical metric for OSA, but it has limited ability to predict cardiovascular risk. This research aims to identify which polysomnography metrics are associated with incident of heart attack and stroke in an epidemiologic cohort; and any polysomnography metrics that affect cardiac and cerebrovascular outcomes differently.
Scientific Abstract
Co-Author: Bolong Xu, BA, BSc, MD, Internal Medicine Resident at the Icahn School of Medicine at Mount Sinai; Vaishnavi Kundel, MD, Associate Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Program Director of the Sleep Medicine Fellowship at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area F, Halls WA2-WA3 (Level II, OCCC West Concourse)
B56 POLLUTION PUZZLE: CONNECTING EXPOSURE, EDUCATION, AND ACTION
Poster Board #P1001 Associations Between Indoor Air Pollution and Blood Pressure Over Pregnancy: Evidence From an Urban Pregnancy Cohort Study
• Exposure to ambient air pollution worsens blood pressure and cardiovascular health, and pregnancy may be a particularly sensitive window of exposure. Indoor air pollution exposures can exceed ambient levels, but associations with cardiovascular health over pregnancy are not well-described. In this urban prospective pregnancy cohort study, researchers evaluated associations between indoor air quality and maternal blood pressure over the course of pregnancy.
Scientific Abstract
Co-Author: Aliza Gross, MD, Internal Medicine Resident at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area D, Halls WA2-WA3 (Level II, OCCC West Concourse)
B80-3 MODERN APPROACHES TO OBSTRUCTIVE SLEEP APNEA AND CARDIOVASCULAR DISEASE: DATA-DRIVEN INSIGHTS AND CLINICAL TRANSLATION
Poster Board # P668 Parsimonious Prediction Models in Mesa to Identify Non-sleepy Individuals With Obstructive Sleep Apnea at Risk for Cardiovascular Events
• Obstructive sleep apnea (OSA) is a major risk factor for cardiovascular disease, yet many individuals with OSA are non-sleepy or minimally symptomatic and therefore may remain undiagnosed or untreated despite elevated cardiovascular risk. Current clinical approaches rely heavily on symptoms such as daytime sleepiness, which may fail to identify high-risk individuals. The objective of this research is to develop parsimonious and interpretable prediction models within the Multi-Ethnic Study of Atherosclerosis (MESA) cohort to identify non-sleepy individuals with OSA who are at increased risk for cardiovascular events and subclinical atherosclerosis progression.
Scientific Abstract
Co-Author: Neomi Shah, MD, MPH, MSc, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Artificial Intelligence & Human Health, Chief of the Division of Digital and Data Driven Medicine at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area D, Halls WA2-WA3 (Level II, OCCC West Concourse)
B80-3 MODERN APPROACHES TO OBSTRUCTIVE SLEEP APNEA AND CARDIOVASCULAR DISEASE: DATA-DRIVEN INSIGHTS AND CLINICAL TRANSLATION
Poster Board #P670 The Utility and Challenges of Extracting Symptom Data From Electronic Health Records Using Natural Language Processing for Cardiovascular Diseases and Obstructive Sleep Apnea
• Chart review to identify clinical events historically has been challenging and labor intensive. However clinical notes contain rich and important information beyond just International Classification of Diseases codes, which if analyzed, could improve the understanding of patients’ disease trajectories. Thus, large language models (LLM) are increasingly utilized in healthcare settings with potential capabilities to identify clinical events from notes, but the available pre-trained LLMs are designed for general rather than healthcare-specific purposes. The researchers aim to refine and deploy a pretrained LLM with healthcare-specific training to extract long-term cardiovascular events and sleep apnea diagnoses; as the first step in this research, they analyze the relationship in World Trade Center exposed populations.
Scientific Abstract
Co-Author: Yutong Dong, MD, Pulmonary and Critical Care Fellow at The Mount Sinai Hospital
11:30 am – 1:15 pm ET
Location: Area D, Halls WA2-WA3 (Level II, OCCC West Concourse)
B80-3 MODERN APPROACHES TO OBSTRUCTIVE SLEEP APNEA AND CARDIOVASCULAR DISEASE: DATA-DRIVEN INSIGHTS AND CLINICAL TRANSLATION
Poster Board # P675 In Silico Trial Emulation to Optimize Eligibility Criteria for CPAP Trials in Obstructive Sleep Apnea and Cardiovascular Outcomes
• Randomized controlled trials have not shown the impact of CPAP on cardiovascular disease outcomes in Obstructive sleep apnea (OSA). This study aims to establish a data-driven set of eligibility criteria to identify patients with OSA most likely to derive cardiovascular benefit from CPAP therapy using real-world data.
Scientific Abstract
Co-Author: Neomi Shah, MD, MPH, MSc, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Artificial Intelligence & Human Health, Chief of the Division of Digital and Data Driven Medicine at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area D, Halls WA2-WA3 (Level II, OCCC West Concourse)
B80-3 MODERN APPROACHES TO OBSTRUCTIVE SLEEP APNEA AND CARDIOVASCULAR DISEASE: DATA-DRIVEN INSIGHTS AND CLINICAL TRANSLATION
Poster Board # P679 Improving the Generalizability of Sleep-based Cardiovascular Risk Prediction Using Super Learner Ensemble
• Machine learning (ML) holds promise for sleep-based cardiovascular event (CVE) risk prediction, yet real-world clinical translation remains challenging. ML models developed in epidemiological cohorts often fail to generalize to new populations because of distribution shifts arising from differences in patient selection, geographic setting, or data collection period. Other challenges, including missing values, sparse and censored events, high-dimensional predictors, and limited sample size, further limit generalizability. ML models may learn subtle cohort-specific artifacts that are associated with outcomes by chance, rather than stable invariant mechanisms. Moreover, conventional imputation methods for handling missing data can amplify noise and obscure clinically informative missingness under distribution shifts. This research aims to develop and evaluate sleep-based cardiovascular risk prediction models better positioned for future clinical translation by mitigating real-world generalizability challenges.
Late Breaking Abstract
Co-Author: Neomi Shah, MD, MPH, MSc, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Artificial Intelligence & Human Health, Chief of the Division of Digital and Data Driven Medicine at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area C, Halls WA2-WA3 (Level II, OCCC West Concourse)
B80-4 CUTTING-EDGE DIAGNOSTICS FOR LUNG CANCER: NEW FRONTIERS IN NODULE RISK STRATIFICATION AND ADVANCED INTERVENTIONAL TOOLS
Poster Board # P419 Evaluation of Sequential AI Risk Scoring for Malignancy Prediction in Indeterminate Lung Nodules
• Artificial Intelligence (AI) models using CT imaging have shown promise in estimating risk of malignancy for pulmonary nodules, but are trained at a single timepoint. The performance and behavior of these models on patients with indeterminate nodules followed with longitudinal imaging is unclear. The researchers externally validated a deep learning lung nodule risk prediction model (RADLogics Inc, NY, NY). This model is based on a system architecture that employs multiple neural networks for nodule descriptor extraction, which are then fused to generate a final risk score. The malignancy probability score is termed the RADLogics Malignancy Index (RMI), ranging from 0-1. The researchers evaluated whether change in AI risk score across follow-up imaging added predictive value for malignancy prediction.
Scientific Abstract
Co-Author: Pranai Tandon, MD, Assistant Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai
11:30 am – 1:15 pm ET
Location: Area C, Halls WA2-WA3 (Level II, OCCC West Concourse
B80-4 CUTTING-EDGE DIAGNOSTICS FOR LUNG CANCER: NEW FRONTIERS IN NODULE RISK STRATIFICATION AND ADVANCED INTERVENTIONAL TOOLS
Poster Board # P430 Closing the Gap: Post-Imaging Follow-up Disparities in Never-Smokers With Incidental Lung Nodules
• Incidentally detected lung nodules (ILNs) are increasingly identified in never-smokers as imaging utilization rises, yet subsequent management remains inconsistent and may contribute to missed or delayed diagnoses. Variation in follow-up and diagnostic evaluation reflects both nodule characteristics and social determinants of health, including race and insurance status, which shape access, timeliness, and completion of care. The researchers examined whether, among never-smokers with ILNs, race and insurance status are associated with outpatient follow-up, completion of diagnostic procedures, and cancer detection.
Scientific Abstract
Co-Author: Christian Lo Cascio, MD, Assistant Professor of Medicine ((Pulmonary, Critical Care and Sleep Medicine) and Thoracic Surgery at the Icahn School of Medicine, Mount Sinai
Tuesday, May 19
2:39 – 2:51 pm ET
Location: West F2 (Level II, OCCC West Concourse)
C100 UNRAVELING CARDIOVASCULAR RISK IN SLEEP APNEA THROUGH PRECISION SCIENCE: GENETIC, MECHANISTIC, AND EPIDEMIOLOGIC PERSPECTIVES
Prototyping OSA: A New Framework for Predicting Cardiovascular Outcomes and CPAP Benefit
• Obstructive sleep apnea (OSA) affects one billion people worldwide. While observational studies have demonstrated that OSA independently associates with major adverse cardiac events (MACE), randomized controlled trials have not shown significant reduction in MACE among patients randomized to CPAP. This discrepancy may be explained by recent studies demonstrating that OSA is a heterogeneous disease with distinct subgroups. The researchers hypothesized that unsupervised cluster analysis using multiple data domains (i.e., substance use, comorbidities, cardiovascular medications, demographics, cardiovascular vitals, sleep apnea symptoms, etc.) could identify heterogeneity amongst OSA patients in terms of disease presentation, intrinsic MACE risk, associated MACE risk, and response to CPAP therapy.
Scientific Abstract
Co-author: Neomi Shah, MD, MPH, MSc, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Artificial Intelligence & Human Health, Chief of the Division of Digital and Data Driven Medicine at the Icahn School of Medicine at Mount Sinai
2:39 – 2:51 pm ET
Location: West F2 (Level II, OCCC West Concourse)
C100 UNRAVELING CARDIOVASCULAR RISK IN SLEEP APNEA THROUGH PRECISION SCIENCE: GENETIC, MECHANISTIC, AND EPIDEMIOLOGIC PERSPECTIVES
Phenotype-based Thresholding of Hypoxemia and Autonomic Markers in Continuous Positive Airway Pressure (CPAP) Treatment for Cardiovascular Outcomes in Obstructive Sleep Apnea (OSA)
• Randomized clinical trials evaluating CPAP for cardiovascular risk reduction in obstructive sleep apnea (OSA) have largely shown neutral overall results, suggesting substantial heterogeneity in treatment response across patient subgroups. Emerging physiologic work has suggested that markers beyond the apnea-hypopnea index (AHI), including nocturnal hypoxemia burden and autonomic response patterns, may better identify patients more likely to experience cardiovascular benefit from CPAP therapy. In this study, heterogeneity-of-treatment-effect focused machine learning approaches were applied to the ISAACC trial to independently identify many of the same physiologic concepts previously reported in the field, including the importance of hypoxemia and autonomic state. The model further demonstrated that these relationships are highly context-dependent and interact with clinical characteristics such as BMI, cardiovascular phenotype, and medication use.
Clinical Topics in Pulmonary Medicine
Co-author: Neomi Shah, MD, MPH, MSc, Professor of Medicine (Pulmonary, Critical Care, and Sleep Medicine) and Artificial Intelligence & Human Health, Chief of the Division of Digital and Data Driven Medicine at the Icahn School of Medicine at Mount Sinai
About the Mount Sinai Health System
Mount Sinai Health System is one of the largest academic medical systems in the New York metro area, with more than 47,000 employees working across seven hospitals, more than 400 outpatient practices, more than 600 research and clinical labs, a school of nursing, and leading schools of medicine and graduate education. Mount Sinai advances health for all people, everywhere, by taking on the most complex health care challenges of our time—discovering and applying new scientific learning and knowledge; developing safer, more effective treatments; educating the next generation of medical leaders and innovators; and supporting local communities by delivering high-quality care to all who need it.
Through the integration of its hospitals, labs, and schools, Mount Sinai offers comprehensive health care from conception through geriatrics, leveraging innovative approaches such as artificial intelligence and informatics while keeping patients’ medical and emotional needs at the center of all treatment. The Health System includes more than 6,400 primary and specialty care physicians and 10 free-standing joint-venture centers throughout the five boroughs of New York City, Westchester, Long Island, and Florida. Hospitals within the System are consistently ranked by Newsweek’s® “The World’s Best Smart Hospitals,” “Best in State Hospitals,” “World’s Best Hospitals,” and “Best Specialty Hospitals” and by U.S. News & World Reports® “Best Hospitals” and “Best Children’s Hospitals.” The Mount Sinai Hospital is on the U.S. News & World Report® “Best Hospitals” Honor Roll for 2025-2026.
For more information, visit https://www.mountsinai.org or find Mount Sinai on Facebook, Twitter and YouTube.