An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers
Critical technique errors are very often performed by patients in the use of Dry Powder Inhalers (DPIs) resulting in a reduction of the clinical efficiency of such medication. Those critical errors include: pure inhalation, non-arming of the device, no exhalation before or after inhalation, and non-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/19/6677 |
| _version_ | 1827705576440725504 |
|---|---|
| author | Athina-Chara Eleftheriadou Anastasios Vafeiadis Antonios Lalas Konstantinos Votis Dimitrios Tzovaras |
| author_facet | Athina-Chara Eleftheriadou Anastasios Vafeiadis Antonios Lalas Konstantinos Votis Dimitrios Tzovaras |
| author_sort | Athina-Chara Eleftheriadou |
| collection | DOAJ |
| description | Critical technique errors are very often performed by patients in the use of Dry Powder Inhalers (DPIs) resulting in a reduction of the clinical efficiency of such medication. Those critical errors include: pure inhalation, non-arming of the device, no exhalation before or after inhalation, and non-holding of breath for 5–10 s between inhalation and exhalation. In this work, an audio-based classification method that assesses patient DPI user technique is presented by extracting the the non-silent audio segments and categorizing them into respiratory sounds. Twenty healthy and non-healthy volunteers used the same placebo inhaler (Bretaris Genuair Inhaler) in order to evaluate the performance of the algorithm. The audio-based method achieved an F1-score of 89.87% in classifying sound events (<i>Actuation</i>, <i>Inhale</i>, <i>Button Press</i>, and <i>Exhale</i>). The significance of the algorithm lies not just on automatic classification but on a post-processing step of peak detection that resulted in an improvement of 5.58% on the F1-score, reaching 94.85%. This method can provide a clinically accurate assessment of the patient’s inhaler use without the supervision of a doctor. |
| first_indexed | 2024-03-10T16:05:54Z |
| format | Article |
| id | doaj.art-a70b3488c9c540289b5f8bf249b5195b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T16:05:54Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a70b3488c9c540289b5f8bf249b5195b2023-11-20T14:56:05ZengMDPI AGApplied Sciences2076-34172020-09-011019667710.3390/app10196677An Audio-Based Method for Assessing Proper Usage of Dry Powder InhalersAthina-Chara Eleftheriadou0Anastasios Vafeiadis1Antonios Lalas2Konstantinos Votis3Dimitrios Tzovaras4Centre for Research and Technology Hellas, Information Technologies Institute, 6th km Charilaou-Thermi, 57001 Thermi, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 6th km Charilaou-Thermi, 57001 Thermi, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 6th km Charilaou-Thermi, 57001 Thermi, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 6th km Charilaou-Thermi, 57001 Thermi, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 6th km Charilaou-Thermi, 57001 Thermi, GreeceCritical technique errors are very often performed by patients in the use of Dry Powder Inhalers (DPIs) resulting in a reduction of the clinical efficiency of such medication. Those critical errors include: pure inhalation, non-arming of the device, no exhalation before or after inhalation, and non-holding of breath for 5–10 s between inhalation and exhalation. In this work, an audio-based classification method that assesses patient DPI user technique is presented by extracting the the non-silent audio segments and categorizing them into respiratory sounds. Twenty healthy and non-healthy volunteers used the same placebo inhaler (Bretaris Genuair Inhaler) in order to evaluate the performance of the algorithm. The audio-based method achieved an F1-score of 89.87% in classifying sound events (<i>Actuation</i>, <i>Inhale</i>, <i>Button Press</i>, and <i>Exhale</i>). The significance of the algorithm lies not just on automatic classification but on a post-processing step of peak detection that resulted in an improvement of 5.58% on the F1-score, reaching 94.85%. This method can provide a clinically accurate assessment of the patient’s inhaler use without the supervision of a doctor.https://www.mdpi.com/2076-3417/10/19/6677audio classificationmachine learningfeature extractionMFCCsasthmaCOPD |
| spellingShingle | Athina-Chara Eleftheriadou Anastasios Vafeiadis Antonios Lalas Konstantinos Votis Dimitrios Tzovaras An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers Applied Sciences audio classification machine learning feature extraction MFCCs asthma COPD |
| title | An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers |
| title_full | An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers |
| title_fullStr | An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers |
| title_full_unstemmed | An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers |
| title_short | An Audio-Based Method for Assessing Proper Usage of Dry Powder Inhalers |
| title_sort | audio based method for assessing proper usage of dry powder inhalers |
| topic | audio classification machine learning feature extraction MFCCs asthma COPD |
| url | https://www.mdpi.com/2076-3417/10/19/6677 |
| work_keys_str_mv | AT athinacharaeleftheriadou anaudiobasedmethodforassessingproperusageofdrypowderinhalers AT anastasiosvafeiadis anaudiobasedmethodforassessingproperusageofdrypowderinhalers AT antonioslalas anaudiobasedmethodforassessingproperusageofdrypowderinhalers AT konstantinosvotis anaudiobasedmethodforassessingproperusageofdrypowderinhalers AT dimitriostzovaras anaudiobasedmethodforassessingproperusageofdrypowderinhalers AT athinacharaeleftheriadou audiobasedmethodforassessingproperusageofdrypowderinhalers AT anastasiosvafeiadis audiobasedmethodforassessingproperusageofdrypowderinhalers AT antonioslalas audiobasedmethodforassessingproperusageofdrypowderinhalers AT konstantinosvotis audiobasedmethodforassessingproperusageofdrypowderinhalers AT dimitriostzovaras audiobasedmethodforassessingproperusageofdrypowderinhalers |