aceA protocol for validation of novel artificial intelligence-based framework for dyspnoea investigation with cardiopulmonary exercise testing
Abstract: Background Exertional dyspnoea largely represents the sensory translation of an ever-growing dynamic mismatch between ventilatory demand and capacity as exercise intensifies. This fundamental tenet, however, has not been formally incorporated into data display and clinical interpretation of incremental cardiopulmonary exercise testing (CPET). The objectives of the present study were to validate a novel framework (Dynamic Assessment of Dyspnoea and Ventilation on Exercise (DyVe-X)) to quantify the severity of exe…
"Multiomic proteomic analysis of blood from long COVID patients using invasive cardiopulmonary exercise testing" by Authors of the study: Inderjit Singh, Brooks P. Leitner, Yiwei Wang, Hanming Zhang, Phillip Joseph, Denyse D. Lutchmansingh, Mridu Gulati, Jennifer D. Possick, William Damsky, John Hwa, Paul M. Heerdt, Hyung J. Chun is licensed under CC BY 4.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/.
Published 2026-09-07 as a peer-reviewed protocol, the study outlines validation of Dynamic Assessment of Dyspnoea and Ventilation on Exercise (DyVe-X), an AI-based software that continuously assesses dyspnoea intensity and mechanical-ventilatory reserve depletion during incremental cardiopulmonary exercise testing in 1161 tobacco-exposed subjects.
If validated, the framework could shift CPET interpretation from a single peak breathing reserve threshold to a dynamic, symptom-linked assessment of why breathlessness occurs, but as of the publication date no validation results are reported and performance remains an anticipated outcome limited to smokers and ex-smokers at risk for or with COPD.
- Study uses incremental CPET data from three large cohorts of tobacco-exposed subjects: smokers and ex-smokers at risk for, or at different stages of, COPD (n=1161).
- DyVe-X 1.0.0 software categorizes breathing abnormalities as excessive breathing (low submaximal ventilatory reserve) and constrained breathing (reduced inspiratory reserve) based on dyspnoea-work rate and dyspnoea-ventilation relationships.
- Comparator for validation is current key criterion of ventilatory limitation defined as peak breathing reserve 2415%.
Protocol proposes AI-based DyVe-X software to continuously quantify exertional dyspnoea against work rate and ventilation and to identify excessive and constrained breathing patterns during incremental CPET, with anticipated superior performance over peak breathing reserve criterion.
The rundown
The protocol describes DyVe-X 1.0.0 (Kingston, ON, Canada) which applies AI techniques to normative data to map dyspnoea intensity against work rate and ventilation across exercise, rather than relying only on peak values.
Authors define two mechanistic phenotypes to be tested: excessive breathing with low submaximal ventilatory reserve but preserved dyspnoea-ventilation, and constrained breathing with reduced inspiratory reserve and high dyspnoea-work rate and dyspnoea-ventilation.
Sources
- Peer-reviewedERJ Open Research2026-09-07
How should this claim be treated?
The debate