(Press-News.org) Paper Title: Automated diagnosis of chronic obstructive pulmonary disease using deep learning applied to electrocardiograms
Journal: eBioMedicine, Volume 123, January 2026
Authors: Monica Kraft, MD, Health System Chair of the Department of Medicine; Girish N. Nadkarni, MD, MPH, CPH, Chief AI Officer and Chair of the Department of Artificial Intelligence and Human Health; Akhil Vaid, MD, Assistant Professor of Medicine (Data Driven Digital Medicine) at the Icahn School of Medicine at Mount Sinai and the Mount Sinai Health System; and other coauthors.
Bottom Line: Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality globally. Effective management hinges on early diagnosis, which is often impeded by non-specific symptoms and resource-intensive diagnostic methods. This study assesses the effectiveness of electrocardiograms (ECGs) analyzed via deep learning as a tool for early COPD detection.
How: Mount Sinai researchers utilized a Convolutional Neural Network model to analyze ECGs, or medical tests that record the heart's electrical activity, and can detect COPD. The primary outcome was the accuracy of a new clinical COPD diagnosis, as determined by International Classification of Disease codes. They performed an evaluation using Area-Under-the-Curve (AUC) metrics, derived by testing against ECGs from patients at five hospitals within the Mount Sinai Health System who represented a demographically diverse patient population in New York City. They examined data from 2006 to 2023 within the GE MUSE system that exports electrocardiograms as individual XML files containing raw waveforms. The experts also used ECGs from patients at another hospital and ECGs of patients with COPD within the UK BioBank to expand the cohort and validate the analysis.
Findings: Mount Sinai researchers analyzed more than 208,000 ECGs from over 18,000 COPD cases, matched to more than 49,000 controls by age, sex, and race. The model exhibited robust performance across diverse populations with an AUC of 0⋅80 (0⋅80–0⋅80) in internal testing, 0⋅82 (0⋅81–0⋅82) in external validation, and 0⋅75 (0⋅71–0⋅78) in the UK cohort. Subsequent analyses linked ECG-derived model predictions with spirometry data, and model explainability highlighted P-wave changes, an indication of COPD.
Why the Research Is Interesting: Experts at Mount Sinai found that AI-powered ECG analysis offers a promising path for early COPD detection, potentially facilitating earlier and more effective management of the condition. Implementing such machine learning tools in clinical settings could significantly enhance COPD screenings and diagnostic accuracy, thereby improving patient outcomes and addressing global health burdens of the disease.
Said Mount Sinai's Dr. Monica Kraft of the research:
“Our study is the first to demonstrate that deep learning models applied to standard 10-second, 12-lead ECGs can accurately detect Chronic Obstructive Pulmonary Disease (COPD) across large, real-world patient cohorts. Using the model known as a convolutional neural network, we show that ECGs—a low-cost and widely available tool—can capture COPD-related physiological changes, including those that precede formal clinical diagnosis.
Unlike previous exploratory work, our analysis includes external validation across distinct cohorts over various times and locations, as well as analysis in the subgroup categories of irregular heartbeat and smoking exposure.”
Said Mount Sinai's Dr. Girish Nadkarni of the research:
“By demonstrating that AI can enhance the diagnostic utility of ECGs for COPD, a pathway is opened for earlier intervention and management of this disease, potentially reducing the severity of its progression and associated financial cost burdens. The use of such AI-enhanced diagnostic tools can be expanded to remote or under-resourced areas where access to specialized diagnostic facilities might be limited.
Additionally, this study lays the groundwork for future research into the integration of AI technologies with other routine diagnostic tools—possibly improving the diagnostic accuracy and timeliness for a range of chronic conditions and ultimately enhancing prevention and early intervention.”
This study was supported by the Scientific Computing and Data at the Icahn School of Medicine at Mount Sinai; the Clinical and Translational Science Awards (UL1TR004419) from the National Center for Advancing Translational Sciences; and the National Heart, Lung, and Blood Institute (R01HL167050-02).
For more Mount Sinai artificial intelligence news, visit: https://icahn.mssm.edu/about/artificial-intelligence.
###
View the full paper here. To schedule an interview with the researchers, contact the Mount Sinai Press Office at stacy.anderson@mountsinai.org or 347-346-3390.
END
A study led by Maria Carmo-Fonseca at GIMM has helped clarify one of the main limitations of lab-grown heart cells, which are widely used around the world to study heart disease and test new drugs. Although these cells make it possible to investigate the human heart without invasive procedures or animal models, they still fail to fully reproduce the characteristics of real heart cells, which can compromise the accuracy of certain studies.
“These cells are extraordinarily useful, but they still behave like very immature cells”, explains ...
A groundbreaking new study from Bar-Ilan University shows that one of sleep’s core functions originated hundreds of millions of years ago in jellyfish and sea anemones, among the earliest creatures with nervous systems. By tracing this mechanism back to these ancient animals, the research demonstrates that protecting neurons from DNA damage and cellular stress is a basic, ancient function of sleep that began long before complex brains evolved.
Although sleep is universal among animals with nervous systems, it poses clear survival risks: during ...
CHAMPAIGN, Ill. — Simple pharmaceutical interventions could help older brains cope with memory impairment and recovery after surgery, new studies in mice suggest.
In two studies, researchers at the University of Illinois Urbana-Champaign investigated different aspects of cognitive impairment: postoperative impairment — a relatively common phenomenon among older adults — and age-related memory decline, as well as noninvasive methods of restoring function.
“These studies provide a blueprint for further basic science studies that can identify compounds in preclinical tests that may eventually also be testable in humans,” ...
UNIVERSITY PARK, Pa. — About half of older men suffer from sleep problems, back pain or both, according to Soomi Lee, associate professor of human development and family studies at Penn State. Lee recently led a study to investigate whether one precedes the other and found that back problems can predict sleep problems years later in men over 65 years old.
“We know that back pain and sleep are serious issues for older adults,” Lee said. “We studied data collected over several years to understand whether poor sleep could predict back pain or if back pain ...
PHILADELPHIA – On Jan. 5, the Centers for Disease Control and Prevention (CDC) dramatically reduced the number of recommended childhood vaccinations from 17 to 11, citing practices in other wealthy nations, including Denmark, Germany, and Japan. The CDC said that parents could choose to have their children receive some previously recommended vaccines, including those for flu, rotavirus, Covid-19, meningitis, and hepatitis A and B, after “shared clinical decision-making.”
The CDC’s announcement followed other similar moves by federal health officials. In December, the CDC’s ...
BALTIMORE, Jan. 6, 2026—A new study published in the INFORMS journal Marketing Science has found that some of the most widely considered online advertising safety and fairness policies may actually boost ad platform revenues while improving fairness outcomes. The policies at the center of the study are around ads that are designed to help ensure that women, minorities and other protected classes are not disproportionately excluded from job, education and financial opportunities.
The study, “Is Fair Advertising Good for Platforms?,” by Di Yuan of Auburn University, ...
Researchers at CU Boulder have created tiny, microorganism-inspired particles that can change their shape and self-propel, much like living things, in response to electrical fields.
One day, these shape-shifting “active particles” could be used as microrobots that deliver medications inside the human body, particularly in areas that are hard for drugs to reach on their own, or for building large-scale dynamic materials that are responsive and self-healing.
The findings are described ...
Johns Hopkins University geneticists and a small army of researchers across the country, including students, are working to catalog the vast and largely unknown soil microbiome of the United States.
The project, one of the biggest microbiome studies ever attempted, that’s tapping the latest DNA-analysis technology, has already resulted in the discovery of more than 1,000 new strains of bacteria and never-before-seen microbes—still just a tiny fraction of the microbial dark matter.
“This scientific void we’re trying to fill on microbial diversity could only be accomplished by having this network of scientists and students across the United States,” ...
ST. LOUIS, MO, January 6, 2026 — A collaborative team of researchers from the Donald Danforth Plant Science Center, the University of Florida, Gainesville and University of Iowa have developed groundbreaking tools that allow grasses—including major grain crops like corn—to act as living biosensors capable of detecting minute amounts of chemicals in the field.
Principal Investigators Dmitri Nusinow, PhD, and Malia Gehan, PhD, led the effort to engineer grasses that produce a visible purple pigment, anthocyanin, ...
Overdose prevention sites and supervised consumption sites in Toronto are not associated with long-term increases in local crime, McGill University researchers have found.
Over 10 years, crime reports remained stable or declined in neighbourhoods where sites opened, the researchers said. Their findings land amid debates across Canada about how harm reduction services intersect with public health and safety.
“Opposition from the public and policymakers has often centred on neighbourhood safety and decline. We wanted to find out whether the data supported those claims,” said Dimitra Panagiotoglou, an associate professor in McGill’s ...
