Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function
<b>Background:</b> Chronic obstructive pulmonary disease (COPD) is projected to be the third-leading cause of death by 2030. Traditional spirometry for the monitoring of the forced expiratory volume in one second (FEV1) can provoke discomfort and anxiety. This study aimed to validate AI...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | BioMedInformatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-7426/5/2/31 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156661037072384 |
|---|---|
| author | Nicki Lentz-Nielsen Lars Maaløe Pascal Madeleine Stig Nikolaj Blomberg |
| author_facet | Nicki Lentz-Nielsen Lars Maaløe Pascal Madeleine Stig Nikolaj Blomberg |
| author_sort | Nicki Lentz-Nielsen |
| collection | DOAJ |
| description | <b>Background:</b> Chronic obstructive pulmonary disease (COPD) is projected to be the third-leading cause of death by 2030. Traditional spirometry for the monitoring of the forced expiratory volume in one second (FEV1) can provoke discomfort and anxiety. This study aimed to validate AI models using daily audio recordings as an alternative for FEV1 estimation in home settings. <b>Methods</b>: Twenty-three participants with moderate to severe COPD recorded daily audio readings of standardized texts and measured their FEV1 using spirometry over nine months. Participants also recorded biomarkers (heart rate, temperature, oxygen saturation) via tablet application. Various machine learning models were trained using acoustic features extracted from 2053 recordings, with K-nearest neighbor, random forest, XGBoost, and linear models evaluated using 10-fold cross-validation. <b>Results:</b> The K-nearest neighbors model achieved a root mean square error of 174 mL/s on the validation data. The limit of agreement (LoA) ranged from −333.21 to 347.26 mL/s. Despite an error range of −1252 to 1435 mL/s, most predictions fell within the LoA, indicating good performance in estimating the FEV1. <b>Conclusions</b>: The predictive model showed promising results, with a narrower LoA compared to traditional unsupervised spirometry methods. The AI models effectively used audio to predict the FEV1, suggesting a viable non-invasive approach for COPD monitoring that could enhance patient comfort and accessibility in home settings. |
| format | Article |
| id | doaj-art-00f5a7b52f4f49a88827de0725e91a41 |
| institution | OA Journals |
| issn | 2673-7426 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | BioMedInformatics |
| spelling | doaj-art-00f5a7b52f4f49a88827de0725e91a412025-08-20T02:24:26ZengMDPI AGBioMedInformatics2673-74262025-06-01523110.3390/biomedinformatics5020031Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory FunctionNicki Lentz-Nielsen0Lars Maaløe1Pascal Madeleine2Stig Nikolaj Blomberg3Koncern Digitalisering, Region Zealand, 4100 Ringsted, DenmarkCorti and Department of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Lyngby, DenmarkExerciseTech, Department of Health Science and Technology, Faculty of Medicine, Aalborg University, 9260 Klarup, DenmarkKoncern Digitalisering, Region Zealand, 4100 Ringsted, Denmark<b>Background:</b> Chronic obstructive pulmonary disease (COPD) is projected to be the third-leading cause of death by 2030. Traditional spirometry for the monitoring of the forced expiratory volume in one second (FEV1) can provoke discomfort and anxiety. This study aimed to validate AI models using daily audio recordings as an alternative for FEV1 estimation in home settings. <b>Methods</b>: Twenty-three participants with moderate to severe COPD recorded daily audio readings of standardized texts and measured their FEV1 using spirometry over nine months. Participants also recorded biomarkers (heart rate, temperature, oxygen saturation) via tablet application. Various machine learning models were trained using acoustic features extracted from 2053 recordings, with K-nearest neighbor, random forest, XGBoost, and linear models evaluated using 10-fold cross-validation. <b>Results:</b> The K-nearest neighbors model achieved a root mean square error of 174 mL/s on the validation data. The limit of agreement (LoA) ranged from −333.21 to 347.26 mL/s. Despite an error range of −1252 to 1435 mL/s, most predictions fell within the LoA, indicating good performance in estimating the FEV1. <b>Conclusions</b>: The predictive model showed promising results, with a narrower LoA compared to traditional unsupervised spirometry methods. The AI models effectively used audio to predict the FEV1, suggesting a viable non-invasive approach for COPD monitoring that could enhance patient comfort and accessibility in home settings.https://www.mdpi.com/2673-7426/5/2/31artificial intelligencemachine learningaudio analysisCOPD monitoringdigital biomarkersrespiratory health |
| spellingShingle | Nicki Lentz-Nielsen Lars Maaløe Pascal Madeleine Stig Nikolaj Blomberg Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function BioMedInformatics artificial intelligence machine learning audio analysis COPD monitoring digital biomarkers respiratory health |
| title | Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function |
| title_full | Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function |
| title_fullStr | Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function |
| title_full_unstemmed | Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function |
| title_short | Voice as a Health Indicator: The Use of Sound Analysis and AI for Monitoring Respiratory Function |
| title_sort | voice as a health indicator the use of sound analysis and ai for monitoring respiratory function |
| topic | artificial intelligence machine learning audio analysis COPD monitoring digital biomarkers respiratory health |
| url | https://www.mdpi.com/2673-7426/5/2/31 |
| work_keys_str_mv | AT nickilentznielsen voiceasahealthindicatortheuseofsoundanalysisandaiformonitoringrespiratoryfunction AT larsmaaløe voiceasahealthindicatortheuseofsoundanalysisandaiformonitoringrespiratoryfunction AT pascalmadeleine voiceasahealthindicatortheuseofsoundanalysisandaiformonitoringrespiratoryfunction AT stignikolajblomberg voiceasahealthindicatortheuseofsoundanalysisandaiformonitoringrespiratoryfunction |