Feasibility of using an automated quality control algorithm for spirometry
Bibliographic record
Abstract
RATIONALE Spirometry tests that meet quality control criteria are essential for accurate interpretation; however, reviewing individual maneuvers for quality in large population-based studies introduces barriers to achieving this goal.OBJECTIVE The objective of this study was to explore the use of a novel automated artificial intelligence software (ArtiQ.QC) to apply the 2019 American Thoracic Society/European Respiratory Society spirometry quality control criteria to data collected as part of the Canadian Longitudinal Study on Aging (CLSA).METHODS Individual spirometry maneuvers (ie, flow-volume and time data) from the CLSA were imported into ArtiQ.QC. Each maneuver was evaluated for technical acceptability according to the ATS/ERS 2019 standard. Quality grades were compared between those provided by the spirometer software and the ArtiQ.QC grade.MEASUREMENTS AND MAIN RESULTS Of the 21,795 spirometry test sessions, 15,079 (69.2%) were technically acceptable and repeatable (Grade A, B or C) for both forced expiratory volume in 1 s (FEV1) and forced vital capacity (FVC). Of 67,908 maneuvers, 25,598 were deemed technically unacceptable, with 87.8% of these failing to meet end of forced expiration criteria. The proportion of individuals below the lower limit of normal for FEV1 and FVC was lower when ArtiQ.QC evaluation was applied compared with those provided by the software.CONCLUSION AI-based quality control algorithms are a feasible and efficient way to ensure high quality spirometry data in research studies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.028 | 0.080 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".