MétaCan
Menu
Back to cohort
Record W2979277565 · doi:10.2196/15173

A Predictive Model for Clinical Asthma Exacerbations Using Albuterol eMDPI (ProAir Digihaler): A Twelve-Week, Open-Label Study

2019· article· en· W2979277565 on OpenAlex
Guilherme Safioti, Lena Granovsky, Thomas Li, Michael Reich, Shahar Cohen, Yonatan Hadar, Roy A. Pleasants, Henry Chrystyn, Tanisha Hill, Michael DePietro

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueIproceedings · 2019
Typearticle
Languageen
FieldMedicine
TopicInhalation and Respiratory Drug Delivery
Canadian institutionsnot available
Fundersnot available
KeywordsInhalerMedicineAsthmaInhalationExacerbationPeak flow meterAsthma exacerbationsReceiver operating characteristicDry-powder inhalerAnesthesiaInternal medicine

Abstract

fetched live from OpenAlex

Background The ability to identify an impending clinical asthma exacerbation (CAE) would improve asthma action plans and provide opportunities for pre-emptive treatment. Increased use of inhaled rescue medications, such as albuterol, has been observed in the days prior to a CAE, but other potential predictive factors are poorly understood. Approved by the US Food and Drug Administration (FDA) in late 2018, ProAir Digihaler with built-in sensors registers when patients use the inhaler and has been shown previously to accurately measure both peak inspiratory flow and inhalation volume, confirming the device’s ability to reliably record objective information on inhaler usage and technique. Objective Data collected from the ProAir Digihaler provides, for the first time, a more complete picture of patients’ use of inhaled medication, and thereby offers an opportunity to develop a predictive model of an impending CAE, and the potential to better implement asthma action plans and facilitate early treatment. Methods Patients (≥18 years old) with exacerbation-prone asthma were recruited to a 12-week, open-label study. Patients used the ProAir Digihaler (albuterol 90 µg 1–2 inhalations q4 hours) as needed. The electronic component of Digihaler recorded each use and inhalation variables (peak inspiratory flow, volume inhaled, time to peak flow, and inhalation duration). Data were downloaded from the inhalers and, together with clinical data, subjected to a machine-learning algorithm to develop models predictive of an impending CAE as defined by the need for oral corticosteroids. The generated model was evaluated by receiver operating characteristic (ROC) curve analysis. Results Three hundred and sixty patients made ≥1 valid inhalation from the Digihaler and were included in the analysis. Of these, 64 patients experienced a total of 78 CAEs. The strongest predictive factor during the 5 days before a CAE was the average number of albuterol inhalations per day. The predictive model was strengthened by supplementing these data with other inhalation features collected by Digihaler, including peak inhalation flow, inhalation volume, night-time usage, and trends of these parameters over time. This model predicted an impending exacerbation over the 5 days with a ROC AUC value of 0.75. Conclusions This study represents, to our knowledge, the first successful attempt to develop a model to predict CAE derived from the use of a rescue medication inhaler device equipped with an integrated sensor and capable of measuring inhalation parameters. The predictive power of the model would benefit from further development with larger populations of asthma patients.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.955
Threshold uncertainty score0.992

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.220
GPT teacher head0.432
Teacher spread0.212 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it