Automated Quality Assessment of Spirometry Data
Powered by deep learning mimicking human visual assessment of spirometry quality. Scalable, immediate and reliable assessment of spirometry data in clinical studies.
Make timely and informed decisions on spirometry quality. Unleash the potential of spirometry AI to deliver reliable outcomes.
ArtiQ.QC offers a cloud-based, scalable solution that can be tailored to the study setup and choice between centralised or decentralized data collection.
ArtiQ.QC analysis can be exchanged throughout the study. This allows for timely decisions on spirometry quality. The ArtiQ technology is compatible with your tools through a generic API, independent of your choice of study platform, vendor software or other IT systems.
Faster turn-around time to complete quality control (QC) and evaluation of spirometry endpoints.
Immediate results with reduced subject burden as another effort can be done while subjects are still at the site.
Reduction in Time
High-quality data collection with potential reduction in sample size or study duration.
Reduced inter- and intra-rater variability when assessing spirometry quality.
The deep learning algorithm of ArtiQ.QC showed superior accuracy over a rule-based approach for both the acceptability and usability 2005 criteria of spirometry maneuvers (ERJ 2020). In the test set (n = 3738), the ArtiQ.QC algortihm demonstrated, next to the higher accuracy, a high sensitivity (92%) and specificity (96%).