Advances in Audio-Based Systems to Monitor Patient Adherence and Inhaler Drug Delivery

Taylor, Terence E.; Zigel, Yaniv; Looze, Céline De; Costello, Richard W.; Reilly, Richard B.

doi:10.1016/j.chest.2017.08.1162

Cited by 40 publications

(29 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these studies mostly recruited either small patient cohorts or small cohorts of healthy participants and did not objectively detect the presence of critical user technique errors such as poor actuation coordination and inhaling too fast during pMDI use. There may be challenges, however, in accurately estimating the inhalation flow rate from pMDIs using audio-methods due to the limited acoustic energy generated in pMDIs during inhalation 36 , 37 .…”

Section: Introductionmentioning

confidence: 99%

Objective Assessment of Patient Inhaler User Technique Using an Audio-Based Classification Approach

Taylor

Zigel

Egan

et al. 2018

Sci Rep

Self Cite

View full text Add to dashboard Cite

Many patients make critical user technique errors when using pressurised metered dose inhalers (pMDIs) which reduce the clinical efficacy of respiratory medication. Such critical errors include poor actuation coordination (poor timing of medication release during inhalation) and inhaling too fast (peak inspiratory flow rate over 90 L/min). Here, we present a novel audio-based method that objectively assesses patient pMDI user technique. The Inhaler Compliance Assessment device was employed to record inhaler audio signals from 62 respiratory patients as they used a pMDI with an In-Check Flo-Tone device attached to the inhaler mouthpiece. Using a quadratic discriminant analysis approach, the audio-based method generated a total frame-by-frame accuracy of 88.2% in classifying sound events (actuation, inhalation and exhalation). The audio-based method estimated the peak inspiratory flow rate and volume of inhalations with an accuracy of 88.2% and 83.94% respectively. It was detected that 89% of patients made at least one critical user technique error even after tuition from an expert clinical reviewer. This method provides a more clinically accurate assessment of patient inhaler user technique than standard checklist methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Objective Assessment of Patient Inhaler User Technique Using an Audio-Based Classification Approach

Taylor

Zigel

Egan

et al. 2018

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“… 28 Digital technologies are also being used to measure adherence in real time for other diseases, such as COPD. 29 The question remains, however, whether prescribers in the real world would act on information about patient non-adherence and appropriately adjust patterns of treatment.…”

Section: Introductionmentioning

confidence: 99%

Does knowledge of patient non-compliance change prescribing behavior in the real world? A claims-based analysis of patients with serious mental illness

Shafrin¹,

Bognar²,

Everson³

et al. 2018

CEOR

View full text Add to dashboard Cite

BackgroundNew digital technologies offer providers the promise of more accurately tracking patients’ medication adherence. It is unclear, however, whether access to such information will affect provider treatment decisions in the real world.MethodsUsing prescriber-reported information on patient non-compliance from health insurance claims data between 2008 and 2014, we examined whether prescribers’ knowledge of non-compliance was associated with different prescribing patterns for patients with serious mental illness (SMI). We examined patients who initiated an oral atypical antipsychotic, but were later objectively non-adherent to this treatment, defined as proportion of days covered (PDC) <0.8. We examined how a physician’s awareness of patient non-compliance (ICD-9 diagnosis code: V15.81) was correlated with the physician’s real-world treatment decisions for that patient. Treatment decisions studied included the share of patients who increased antipsychotic dose, augmented treatment, switched their antipsychotic, or used a long-acting injectable (LAI).ResultsAmong the 286,249 patients with SMI who initiated an antipsychotic and had PDC <0.8, 4,033 (1.4%) had documented non-compliance. When prescribers documented non-compliance, patients were more likely to be switched to another antipsychotic (32.8% vs 24.7%, P<0.001), have their dose increased (24.4% vs 22.1%, P=0.004), or receive an LAI (0.09% vs 0.04%, P=0.008), but were less likely to have augmented therapy with another antipsychotic (1.1% vs 1.3%, P=0.035) than patients without documented non-compliance.ConclusionAmong SMI patients with documented non-compliance, the frequency of dose, medication switches, and LAI use were higher and augmentation was lower compared to patients without documented non-compliance. Access to adherence information may help prescribers more rapidly switch ineffective medications as well as avoid unnecessary medication augmentation.

show abstract

“…As a step forward data-driven approaches learn by example from features and distributions found in the data. Taylor et al [26] compared Quadratic Discriminant Analysis (QDA) and Artificial Neural Network (ANN) based classifiers using MFCC, Linear Predictive Coding, ZCR and CWT features.…”

Section: Related Workmentioning

confidence: 99%

“…A year later, Holmes et al [18,19], also, developed an algorithm that recognizes blister events and breath events (with an accuracy of 92.1%) and separates inhalations from exhalations (with an accuracy of more than 90%). Later, Taylor et al developed two main algorithms for blister detection [26,37] based on Quadratic Discriminant Analysis and ANN, and achieved an accuracy of 88.2% and 65.6%, respectively. Nousias et al in Reference [13] presented a comparative study between Random Forest, ADABoost, Support Vector Machines and Gaussian Mixture Models, reaching the conclusion that RF and GMM yield a 97% to 98% classification accuracy on the examined dataset, when utilizing MFCC, Spectrogram and Cepstrogram features.…”

Section: Comparison With Relevant Previous Workmentioning

confidence: 99%

Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification

Ntalianis

Fakotakis

Nousias

et al. 2020

Sensors

View full text Add to dashboard Cite

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration of medication. As a series of studies indicates, medication adherence can effectively be monitored by successfully identifying actions performed by patients during inhaler usage. This study focuses on the recognition of inhaler audio events during usage of pressurized metered dose inhalers (pMDI). Aiming at real-time performance, we investigate deep sparse coding techniques including convolutional filter pruning, scalar pruning and vector quantization, for different convolutional neural network (CNN) architectures. The recognition performance has been assessed on three healthy subjects following both within and across subjects modeling strategies. The selected CNN architecture classified drug actuation, inhalation and exhalation events, with 100%, 92.6% and 97.9% accuracy, respectively, when assessed in a leave-one-subject-out cross-validation setting. Moreover, sparse coding of the same architecture with an increasing compression rate from 1 to 7 resulted in only a small decrease in classification accuracy (from 95.7% to 94.5%), obtained by random (subject-agnostic) cross-validation. A more thorough assessment on a larger dataset, including recordings of subjects with multiple respiratory disease manifestations, is still required in order to better evaluate the method's generalization ability and robustness.

show abstract

Advances in Audio-Based Systems to Monitor Patient Adherence and Inhaler Drug Delivery

Cited by 40 publications

References 79 publications

Objective Assessment of Patient Inhaler User Technique Using an Audio-Based Classification Approach

Objective Assessment of Patient Inhaler User Technique Using an Audio-Based Classification Approach

Does knowledge of patient non-compliance change prescribing behavior in the real world? A claims-based analysis of patients with serious mental illness

Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification

Contact Info

Product

Resources

About