Development of an AI-Empowered Novel Digital Monitoring System for Inhalation Flow Profiles
Bibliographic record
Abstract
The use of dry powder inhalers (DPIs) represents a cornerstone in the treatment of chronic pulmonary diseases. However, suboptimal inhalation techniques, including inadequate airflow rates, have been a persistent concern for achieving effective therapeutic outcomes, as many patients remain unaware of their insufficient inhalation performance. As an effective strategy, a digital monitoring system, coupled with dry powder inhalers (DPIs), has emerged to estimate flow profiles and provide inhalation information. The estimation could be further facilitated by the application of artificial intelligence (AI). In this work, a novel digital system to primarily monitor pressure during DPI usage was successfully designed, and advanced machine learning (ML) techniques were then employed to estimate inhalation flow profiles based on the captured data. Four optimal machine learning models were selected for subsequent inhalation parameter prediction, given their superior generalization ability. By using these models, inhalation flow profiles could be successfully estimated, with an excellent accuracy of 97.7% for Peak Inspiratory Flow Rate (PIFR) and 95.2% for inspiratory capacity (IC). In summary, the pressure-based digital monitoring system empowered by AI techniques could be successfully applied to assess inhalation flow profiles with excellent accuracy.
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) | 0.000 | 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 | 0.001 |
| 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".