Development and application of an AI-empowered acoustic monitoring system for misuse detection in dry powder inhalers
Bibliographic record
Abstract
Misuse and poor inhalation techniques remain persistent issues in pulmonary drug delivery via dry powder inhalation. While acoustic-based monitoring has been a feasible strategy, existing approaches often depend on smartphones for signal collection, or wired connections for data transmission, limiting their scalability and practicality in real-world settings. More importantly, few studies have specifically focused on the detection of incorrect DPI usage via digital monitoring systems, and current methods still face limitations in accuracy. Therefore, in this study, an AI-empowered acoustic monitoring system was developed, combining edge sensing and cloud analytics to support continuous signal acquisition and misuse detection. Comprehensive featuring engineering and machine learning analysis have been performed to investigate their influence on inhalation activity recognition. The results suggested that feature fusion could significantly enhance classification performance, with the Support Vector Classifier (SVC) showing 99.5 % overall accuracy during cross-validation and 100% accuracy on the test set, along with rapid training and high stability. This proposed digital system achieves a near-perfect categorization on the inhalation-related events, and effectively detects unexpected exhalation into inhalers, showing strong potential in real-life applications for improved respiratory disease management.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".