Mount Sinai experts to present new research on AI models that predict chronic respiratory failure and detect airway obstruction at ATS 2025 International Conference

(Press-News.org) World renowned pulmonologists and experts in respiratory medicine from the Mount Sinai Health System will present new research at the American Thoracic Society (ATS) 2025 International Conference in San Francisco from May 18–May 21. Please let me know if you would like to coordinate an interview about their work. Mount Sinai doctors and researchers are also available to comment on breaking news and trending topics.

Sessions and Symposiums

*All abstracts listed below are under embargo until the scheduled start time of the event*:

Sunday, May 18
11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
A32 IT’S NOT EASY BEING WHEEZY: ASTHMA AND COPD CLINICAL STUDIES
Poster Board # P1369: Nasal Epithelial Gene Expression Analyses of Candidate Senescence Genes Identify MMP2 and FN1 Associated With Asthma Susceptibility and Severity in the ATLANTIS Study
• Cellular senescence, or stress response and DNA damage, has been associated with asthma. However, the gene expression that links cellular senescence to asthma remain unknown. The researchers investigated nasal epithelial mRNA expression of more than 80 candidate senescence genes, selected by a lung-focused SenNet tissue mapping team, to reveal potential genes associated with senescence and asthma.
Thematic Poster Session
Participant: Xingnan Li, PhD, Associate Professor of Medicine (Data-Driven and Digital Medicine) at the Icahn School of Medicine at Mount Sinai
Area L, Hall F (North Building, Exhibition Level), Moscone Center

2:15 – 4:15 PM Pacific (11:15 am – 1:15 pm Eastern)
A109 SMOKE, SNOOZE, AND ICU BLUES: THE INFLUENCE OF ENVIRONMENTAL EXPOSURES AND CRITICAL CARE CONDITIONS ON SLEEP
Poster Board # 809: Atypical N3 Sleep Pattern in Critically Ill Patients and Its Role as a Marker of Outcome
• Intensive care unit patients often experience sleep disturbances. Of those, atypical N3 (AN3) sleep—characterized by delta wave patterns with limited theta and sigma activity— has been linked to sepsis-associated encephalopathy and neurodegenerative diseases. This observational study investigated this sleep pattern, AN3, as a potential biomarker for ICU patient outcomes.
RAPiD: Rapid Abstract Poster Discussion Session
Participant: Christiana Choi, MD, Resident at Mount Sinai Morningside and Mount Sinai West
Room 2022/2024 (West Building, Level 2), Moscone Center

Monday, May 19
11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
B33 WHEEZING THROUGH THE MECHANISMS: UNPACKING ASTHMA’S SECRETS
Poster Board # P1555: Distal Lung Inflammation Correlates With Systemic Inflammation and Small Airway Disease: Data From the ATLANTIS Study
• The purpose of the AssessmenT of smalL Airways involvemeNT In aSthma (ATLANTIS) study was to assess the presence and extent of small airways disease (SAD) in asthma, which physiological tests best identify SAD and whether SAD was associated with relevant clinical outcomes. As part of the ATLANTIS study, a subset of participants underwent bronchoscopy with endobronchial and transbronchial biopsy. The researchers hypothesized that distal airway inflammation would be associated with SAD and proximal airway inflammation with large airway disease.
Thematic Poster Session
Co-author: Monica Kraft, MD, Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine), and System Chair for the Department of Medicine at the Icahn School of Medicine at Mount Sinai       
Area M, Hall F (North Building, Exhibition Level), Moscone Center

11:30 a.m.-1:15 pm Pacific (8:30-10:15 am Eastern)
B54 CASE REPORTS IN BRONCHIECTASIS AND CF
Poster Board # P630: Never Just a Cough: Spontaneous Lung Herniation and Its Concomitant Complications
• Spontaneous lung intercostal herniation (SLIH) is a rare condition characterized by protrusion of lung tissue through thoracic wall defects, typically occurring without prior trauma or surgery. Predisposing factors include chronic obstructive pulmonary disease (COPD) and increased intra-thoracic pressure from severe coughing or straining. To date, only 120 cases have been reported, underscoring its rarity in clinical practice. The researchers will present a case of SLIH following severe coughing, with concomitant bronchocutaneous fistula and lymphocytic pleural effusion.
Thematic Poster Session
Presenter: Aesha Patel, DO, Resident at Mount Sinai Morningside and Mount Sinai West
Area L, Hall F (North Building, Exhibition Level), Moscone Center

11:30 a.m.-1:15 pm Pacific (8:30-10:15 am Eastern)
B78 MACHINE MINDS AND SLEEPING FINDS: AI, IMAGING, AND DIAGNOSTIC BREAKTHROUGHS IN SLEEP APNEA
11:30 a.m.-1:15 pm Pacific (8:30-10:15 am Eastern)
Poster Board # P474: Continuous Deep Learning Approach for Accelerated MR Imaging Annotations for Subcutaneous and Visceral Adipose Tissue Quantification in Sleep Apnea Patients
• Central abdominal obesity, particularly visceral adiposity may be a key player in mediating obstructive sleep apnea (OSA)-related cardiovascular disease risk. Accurately measuring changes in visceral (VAT) and subcutaneous adipose tissue (SAT) volumes and metabolic activity could be crucial for evaluating the effectiveness of OSA therapies such as continuous positive airway pressure (CPAP) and novel weight-loss drugs. Manual analysis of abdominal adipose tissue on MRI can be time-intensive. The researchers developed a dynamic training approach leveraging pre-trained AI models for abdominal fat segmentation in patients with OSA who underwent 18F-FDG positron emission tomography (PET) / magnetic resonance imaging (MRI), before and after CPAP.
Thematic Poster Session
Participant: Valentin Fauveau, MS, Senior Programmer Analyst at the BioMedical Engineering and Imaging Institute at the Icahn School of Medicine at Mount Sinai
Area D, Hall F (North Building, Exhibition Level), Moscone Center

Poster Board # P483: Physiology Guided Machine Learning Approach for Predicting Excessive Daytime Sleepiness in Sleep Apnea
• The current metric of obstructive sleep apnea severity, the apnea-hypopnea index (AHI), is inconsistently related to excessive daytime sleepiness. The researchers aim to combine purportedly independent measures across ventilatory, hypoxic, arousal, and autonomic burdens; and assess the utility in predicting daytime sleepiness in a large cohort.
Thematic Poster Session
Presenter: Sajila Wickramaratne, PhD, Associate Scientist at the Icahn School of Medicine at Mount Sinai
Area D, Hall F (North Building, Exhibition Level), Moscone Center

Poster Board # P484: Using Generative AI to Reliably Retrieve and Summarize Symptoms From Electronic Health Records in Sleep Apnea
• Electronic Health Record (EHR) data contain vital information that are a snapshot of symptoms reported by a patient during an encounter with a physician. In particular, for sleep apnea patients, pertinent information that could guide treatment and its management are embedded in these clinical notes. Large language models (LLM) are a class of Generative AI models, which can extract information from clinical notes to identify key patient data. The use of these LLM’s for extracting key patient symptoms relevant to sleep apnea pathophysiology has not been tested.
Thematic Poster Session
Presenter: Sajila Wickramaratne, PhD, Associate Scientist at the Icahn School of Medicine at Mount Sinai
Area D, Hall F (North Building, Exhibition Level), Moscone Center

11:30 a.m.-1:15 pm Pacific (8:30-10:15 am Eastern)
Poster Board # P489: Applying Artificial Intelligence to Measure Abdominal Adipose Metrics in Obstructive Sleep Apnea Before and After CPAP Therapy
• Obstructive sleep apnea (OSA) is associated with an increased risk of cardiovascular disease, but the effectiveness of continuous positive airway pressure (CPAP) therapy in improving cardiovascular outcomes has been inconsistent. Visceral obesity has emerged as a potential mediator in this relationship and is a known risk factor for cardiovascular disease. This study aimed to explore the relationship between OSA severity and abdominal obesity metrics, including visceral and subcutaneous adipose tissue (VAT and SAT) volumes and VAT metabolic activity, and to assess changes in these metrics following CPAP intervention, using [18F]-Fluoro-2-deoxy-D-glucose (FDG) positron emission tomography (PET) combined with magnetic resonance imaging (MRI).
Poster Discussion Session
Participant: Jennifer Prevot, MD, Pulmonary and Critical Care Medicine Fellow at Mount Sinai Hospital
Area D, Hall F (North Building, Exhibition Level), Moscone Center

11:30 a.m.-1:15 pm Pacific (8:30-10:15 am Eastern)
B80-1 FROM BENCH TO BEDSIDE: INNOVATIVE BIOMARKERS, SCREENING APPROACHES, AND PERSONALIZED TREATMENTS IN LUNG CANCER
Poster Board # P780: Incidental Lung Nodule Program for Early Detection of Lung Cancer: Downstream Testing, Complications, and Proportion of Early-stage Cancers
• More than 1.5 million incidental lung nodules (ILNs) are detected in the U.S. yearly, and more than 60% may be lost to follow-up. Up to 5% of patients with ILNs are diagnosed with lung cancer. Programs using Natural Language Processing (NLP) to capture patients with ILNs reported on their imaging tests have been proposed as a safety net to avoid losses to follow-up. In 2023, the researchers launched such a program in two hospitals of a large healthcare system. This study analyzes the rates of downstream diagnostic tests performed due to the intervention of the program, and assesses potential harms that might occur.
Thematic Poster Session
Presenter: Catherine Zaw, MD/MPH, Pulmonary and Critical Care Fellow at Mount Sinai Morningside and Mount Sinai West
Area G, Hall F (North Building, Exhibition Level), Moscone Center

2:15 – 4:15 PM Pacific (11:15 am – 1:15 pm Eastern)
B101 FIXING BARRIERS: UNLOCKING TREATMENT MODALITIES IN INFLAMMATORY LUNG DISEASES
Poster Board # 1015: Investigation of the Relationship Between Blood Eosinophil Count and Small Airway Dysfunction Identifies Potential Asthma Endotypes in the ATLANTIS Study
• Asthma endotypes may be broadly categorized into high type 2 (T2) asthma and low T2 asthma. Small airway dysfunction (SAD) contributes to the clinical manifestations of asthma. In this study, the researchers aimed to investigate the effect of T2 inflammation and SAD on clinical phenotypes related to asthma severity.
Poster Discussion Session
Participant: Xingnan Li, PhD, Associate Professor of Medicine (Data-Driven and Digital Medicine) at the Icahn School of Medicine at Mount Sinai
Room 3022/3024 (West Building, Level 3), Moscone Center

2:15 – 4:15 pm Pacific (11:15 am – 1:15 pm  Eastern)
B109 THE SLEEPING HEART: OSA-DRIVEN HETEROGENEITY IN BP CONTROL, MACE RISK PREDICTION, AND ACUTE MI MANAGEMENT
Poster Board # 106: Unraveling Heterogeneity of Subclinical Cardiovascular Disease in OSA: Assessment of Vascular Inflammation Before and After CPAP Using Hybrid PET/MRI
• Obstructive sleep apnea (OSA) is associated with atherosclerosis and cardiovascular disease. The researcher’s prior work has demonstrated heterogeneity of treatment effects (HTE) with continuous positive airway pressure (CPAP) on cardiovascular outcomes. Now, they aimed to evaluate HTE in OSA, at the vascular level, to better understand the biologic mechanisms. The researchers employed hybrid positron emission tomography/magnetic resonance imaging (PET/MRI) with 18F-FDG radiotracer to characterize vascular inflammation, and assess HTE in patients with OSA before and after CPAP therapy.
Poster Discussion Session
Presenter: Aaron Gans, MD, Resident at Mount Sinai Hospital
Room 203-204 (South Building, Level 2), Moscone Center

2:15 – 4:15 pm Pacific (11:15 am – 1:15 pm  Eastern)
B110 THE ROAD TO EARLY DETECTION: ADVANCING LUNG CANCER SCREENING THROUGH AI, RISK MODELS, AND REAL-WORLD DATA
Poster Board # 620: Management of Lung Nodules: A Two-year Follow-up Study of an Innovative Lung Nodule Program
• Over 1.5 million new incidental lung nodules (ILNs) are detected annually in the United States, with an estimated 60% of these nodules subsequently lost to follow-up. Given the 5% risk of lung cancer diagnosis associated with ILNs, the researchers designed an Incidental Lung Nodule Program (ILNP) at Mount Sinai as a safety net to systematically manage lung nodules and minimize the proportion lost to follow-up. Since its launch in January 2023, the program has been instrumental in early lung cancer detection and significantly improved ILN follow-up rates.
Poster Discussion Session
Presenter: Junyu Qi, MPH, Clinical Research Coordinator II at Mount Sinai Morningside and Mount Sinai West
Room 2002/2004 (West Building, Level 2), Moscone Center

Tuesday, May 20
9:15 – 11:15 am Pacific (6:15 – 8:15 am Eastern)
C31 BREAKING THROUGH THE FOG: AI, IP AND NOVEL INSIGHTS TO IMPROVE LUNG CANCER DIAGNOSIS AND MANAGEMENT
Poster Board # 518: Provider Bias in Decision Making About Treatment of Early-stage Lung Cancer With Stereotactic Body Radiation Therapy or Sub-lobar Resection
• Stereotactic body radiation therapy and sub-lobar resection are treatment options for patients deemed high-risk for lobectomy for early-stage non-small cell lung cancer (NSCLC). Disparities in surgical management of NSCLC are well documented. The researchers evaluated whether patient race or ethnicity influenced physicians’ therapeutic plans for early-stage NSCLC patients at high risk for lobectomy.
Poster Discussion Session-Abstract Session
Participant: Jeremy Mudd, MD, Pulmonary and Critical Care Research Fellow at Mount Sinai Hospital; and Hamna Zafar, MD, Pulmonary and Critical Care Fellow at Mount Sinai Hospital
Room 3010/3012 (West Building, Level 3), Moscone Center

11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
C49 WHAT'S NEW IN COPD PHENOTYPING AND MANAGEMENT
Poster Board # P886: Machine Learning Driven Prediction of Chronic Respiratory Failure in COPD Using Multiple Biomarkers: A Bioprognostic Index
• Despite significant heterogeneity in pathophysiology and clinical trajectory among patients with chronic obstructive pulmonary disease (COPD), personalized prognostication remains elusive. Multiple large cohort studies have investigated plasma biomarkers; however, single biomarkers have not reliably demonstrated additional predictive power over traditional clinical predictors. In this study, researchers examine how Machine Learning (ML) techniques provide an opportunity to leverage multiple biomarkers to predict patient centered outcomes in COPD.
Thematic Poster Session
Participant: Pranai Tandon, MD, Assistant Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai
Area G, Hall F (North Building, Exhibition Level), Moscone Center

11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
C55 EXPOSED: INJURY AND CANCER FROM VAPING, MARIJUANA, SMOKE, AND WORKPLACE HAZARDS
Poster Board # P1045: Macklin Effect: A Rare Complication of Asthma Exacerbation in Heavy Marijuana Users
• Macklin effect is a three-step process that starts with alveolar rupture, followed by dissection of air along bronchovascular sheaths, and ultimately air spreading into the mediastinum. It is associated with thoracic/cervical trauma and barotrauma in patients receiving invasive mechanical ventilation. It is rarely associated with other non-traumatic causes like asthma, heavy marijuana smoking involving breath holding, vomiting, and esophageal ruptures. The researchers review a case who presented with this rare radiological sign associated with asthma exacerbation and heavy marijuana use.
Thematic Poster Session
Participant: Aishwarya Puri, MD, Pulmonary and Critical Care Fellow at Mount Sinai Morningside and Mount Sinai West; and Avinash Singh, MBBS, Assistant Professor of Medicine (Pulmonary Disease) at the Icahn School of Medicine at Mount Sinai
Area H, Hall F (North Building, Exhibition Level), Moscone Center

11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
C56 MARINA: FROM DIAGNOSIS TO INTERVENTION: SHAPING PULMONARY EMBOLISM OUTCOMES
Poster Board # P1361: Causes of Re-admissions Among Patients With Acute Pulmonary Embolism: A Retrospective Analysis
• Pulmonary embolism (PE) has an annual incidence of 39 to 115 per 100,000 population and is associated with significant morbidity, mortality and healthcare costs. Identifying key predictors of PE readmission may reduce associated morbidity and costs. The researchers retrospectively reviewed causes of readmission within 30 days among patients hospitalized for acute PE at a tertiary care facility managed by the PE Response Team (PERT).
Thematic Poster Session
Participant: Aesha Patel, DO, Resident at Mount Sinai Morningside and Mount Sinai West
Area L, Hall F (North Building, Exhibition Level), Moscone Center

11:30 am – 1:15 pm Pacific (8:30 – 10:15 am Eastern)
C77 BREATHLESS BIOMARKERS AND PHENOMENAL PHENOTYPES: UNLOCKING SLEEP APNEA’S HIDDEN PHYSIOLOGY, ONE MECHANISM AT A TIME
Poster Board # P1070: Characterizing Imaging-based Cardiometabolic Markers Using Hybrid 18F-FDG Positron Emission Tomography/Magnetic Resonance Imaging in Patients With Actigraphy-derived Sleep Patterns
• There is mounting evidence that short sleep and irregular sleep patterns are associated with impaired cardiovascular health. However, few studies have explored this link independent of obstructive sleep apnea (OSA), an important confounder in this relationship. Here, researchers investigate the link between short sleep and imaging-based surrogate measures of cardiovascular health in a cohort of patients with mild to no OSA.
Thematic Poster Session
Participant: Bolong Xu, MD, Resident at Mount Sinai Hospital
Area H, Hall F (North Building, Exhibition Level), Moscone Center

C94 BREATHING EASY: UNRAVELING THE MYSTERIES OF ASTHMA THROUGH TRANSLATIONAL STUDIES
3:51 – 4:03 pm Pacific (12:51 – 1:03 pm Eastern)
A Computational Approach for Detection of Novel Circular RNAs (circRNA) From the ATLANTIS Study
• Asthma is a highly heterogeneous disease where its complexity, in part, is demonstrated in Differentially Expressed Genes (DEGs) from RNA-seq analysis. The Assessment of Small Airways Involvement in Asthma (ATLANTIS) study performed bulk transcriptomics using nasal epithelium from more than 300 participants well characterized with asthma, across severities and non-asthmatic controls. The researchers hypothesize that comparing non-asthmatic to asthmatics DEGs will reveal modulation in circRNA expression and predict novel circRNAs that could mediate the disease pathway.
Mini Symposium-Scientific Abstract
Participant: Mustafa M. Siddiq, PhD, Assistant Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) at the Icahn School of Medicine at Mount Sinai
Room 3014/3016/3018 (West Building, Level 3), Moscone Center

Wednesday, May 21
8:15 – 10:15 am Pacific (5:15 – 7:15 am Eastern)
D30 GOING WITH THE FLOW: ABNORMALITIES IN RESPIRATORY MECHANICS
Poster Board # 615: Artificial Intelligence- Based Deep Learning Model for Detecting Central and Upper Airway Obstruction on Flow-Volume Loops
• Intrathoracic and extrathoracic airway obstructions often manifest as respiratory symptoms, such as dyspnea, which commonly prompt pulmonary function testing (PFT). However, current diagnostic criteria, both quantitative and visual, lack sensitivity for reliably identifying upper airway obstructions using flow-volume loop patterns, with individual criteria often showing sensitivities below 50%. While current guidelines suggest expert review of flow-volume loops to detect characteristic plateau patterns during forced inspiratory and/or expiratory phases, no standardized method exists for identifying these obstructions from PFT results. This study aims to address this gap by developing an Artificial Intelligence (AI) deep learning model capable of automatically detecting repeatable plateau patterns in flow-volume loops, indicative of intrathoracic and extrathoracic airway obstruction.
Poster Discussion Session-Scientific Abstract
Participant: Jennifer Prevot, MD, Pulmonary and Critical Care Medicine Fellow at Mount Sinai Hospital
Room 2002/2004 (West Building, Level 2), Moscone Center

11:00 am – 1:00 pm Pacific (8:00 – 10:00 am Eastern)
D109 THE NEW NORMAL? EARLY SIGNS OF CHRONIC LUNG DISEASE
Poster Board # 423: E-cigarette and Vaping Practices and Patterns Among U.S. Millennial Adults: A Preliminary Report From the American Lung Association Lung Health Cohort Study
• Vaping is common, with recent trends towards more frequent use. While its chronic effects on respiratory health remains an area of active research, early work has demonstrated associations with adverse outcomes. Vaping practices and patterns have been described amongst adolescents but remain incompletely characterized in millennial adults who may be at peak lung health.
Poster Discussion Session-Late Breaking Abstract
Participant: Sonali Bose, MD, Associate Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) and Pediatrics at the Icahn School of Medicine at Mount Sinai
Room 301-302 (South Building, Level 3), Moscone Center

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 48,000 employees working across seven hospitals, more than 400 outpatient practices, more than 600 research and clinical labs, a school of nursing, and a leading school 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 solutions from birth 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 approximately 9,000 primary and specialty care physicians and 11 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 Best Hospitals and Best Specialty Hospitals” and by U.S. News & World Report’s® “Best Hospitals” and “Best Children’s Hospitals.” The Mount Sinai Hospital is on the U.S. News & World Report® “Best Hospitals” Honor Roll for 2024-2025.
For more information, visit https://www.mountsinai.org or find Mount Sinai on Facebook, Twitter and YouTube.

END