Acoustic Cough Monitoring for the Management of Patients With Known Respiratory Disease

NCT05042063 | Completed

• 1 other identifier: PI_2021/72
• Study Type: observational
• Target: 616
• Locations: 1 country
• Sites: 1

Brief Summary

This study pretends to evaluate the potential use of Hyfe Cough Tracker (Hyfe) to screen for, diagnose, and support the clinical management of patients with respiratory diseases, while enriching a dataset of disease-specific annotated coughs, for further refinement of similar systems.

Conditions

Cough; COPD; GERD; Asthma; Tuberculosis; Non-Tuberculous Mycobacterial Pneumonia; COVID-19 Pneumonia

Outcome Measures

Primary Outcomes (1)

• Correlation between subjective perception of cough and objective frequency

  The daily VAS score of participants will be compared to the cough frequency registered by the cough surveillance system. These data will be used to fit a linear regression model to compare self-reported VAS scores to daily cough frequency and calculate a correlation coefficient (r).

  6 months.

Secondary Outcomes (7)

• Sensitivity of the system discriminating coughs

  6 months.

• Specificity of the system discriminating coughs

  6 months.

• Positive predictive value (PPV) of the system discriminating coughs

  6 months.

• Negative predictive value (NPV) of the system discriminating coughs

  6 months.

• Construction of an annotated cough dataset

  5 years.

Study Arms (3)

Participants with cough as a symptom

This group will be composed of patients at the Clínica Universidad de Navarra that complain of having cough as a remarkable symptom.

Device: Hyfe Cough Tracker

Validation subgroup 1

This subgroup will be composed by both, patients belonging to the main study group, as well as voluntaries, who will be asked to provide a series of elicited cough and non-cough sounds for validation purposes.

Device: Hyfe Cough Tracker

Validation subgroup 2

This subgroup will be composed by inpatients admitted to the Clínica Universidad de Navarra with a diagnosis of respiratory disease, or presenting cough as a symptom, as well as healthy individuals. This group will be monitored with Hyfe Cough Tracker and Hyfe Air for a variable period of 6-24 hours, while they are recorded with a MP3 recorder connected to a lapel microphone.

Device: Hyfe Cough Tracker; Device: Hyfe Air

Interventions

Hyfe Cough Tracker DEVICE

Hyfe Cough Tracker is a digital acoustic surveillance system that uses an artificial intelligence system to discriminate cough from non-cough sounds. Hyfe is an AI-enabled mobile app that records short snippets (\<0.5 seconds) of putative cough explosive sounds and then classifies them as cough or non-cough using a convolutional neural network (CNN) model. Briefly, the acoustic characteristics of recorded sounds are converted into an image file, which is then processed by an algorithm trained to identify graphical differences in images. This creates an adjustable prediction score, with values above it, resulting in a sound being classified as "cough", and those below being classified as "non-cough.

Participants with cough as a symptom; Validation subgroup 1; Validation subgroup 2

Hyfe Air DEVICE

Hyfe Air is a wearable device with an incorporated wireless lapel microphone. The device´s recordings can be run through the same cough-detection algorithm used by Hyfe Cough Tracker, while its results are directly stored in a remote database and are not displayed to participants.

Validation subgroup 2

Eligibility Criteria

• Age: 5 Years - 100 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

For the main study group, the population are patients with respiratory disease treated in the Clínica Universidad de Navarra (Pamplona and Madrid campuses). Since the validation sub-study 1 only requires elicited sounds, a group of participants from a previous study will be directly invited to participate. For the validation sub-study 2, participants will include both, inpatients admitted to the Clínica Universidad de Navarra and presenting cough, and healthy individuals directly invited to participate by the study team.

You may qualify if:

• For participants in the main study group
• Outpatient or inpatients at the Clinical Universidad de Navarra with a complaint of cough.
• The patient or his/her legal representative, have given consent to participate in the study.
• For participants in the sub-study groups:
• Being 18 years or older.
• Providing consent for the sub-study

You may not qualify if:

• Inability to accept the privacy policy and terms of use of Hyfe.
• Lack of access to a Wi-Fi network at the site of residence (for the main study group).
• Unwillingness to regularly use the cough-surveillance system throughout the monitoring period

Sponsors & Collaborators

• Clinica Universidad de Navarra, Universidad de Navarra: lead
• Centre de Recherche du Centre Hospitalier de l'Université de Montréal: collaborator
• Hyfe Inc: collaborator

Study Sites (1)

Clinica Universidad de Navarra

Pamplona, Navarre, 31008, Spain

Location

Related Publications (14)

• Barton A, Gaydecki P, Holt K, Smith JA. Data reduction for cough studies using distribution of audio frequency content. Cough. 2012 Dec 12;8(1):12. doi: 10.1186/1745-9974-8-12.

  PMID: 23231789 BACKGROUND

• Boulet LP, Coeytaux RR, McCrory DC, French CT, Chang AB, Birring SS, Smith J, Diekemper RL, Rubin B, Irwin RS; CHEST Expert Cough Panel. Tools for assessing outcomes in studies of chronic cough: CHEST guideline and expert panel report. Chest. 2015 Mar;147(3):804-814. doi: 10.1378/chest.14-2506.

  PMID: 25522203 BACKGROUND

• Bujang MA, Adnan TH. Requirements for Minimum Sample Size for Sensitivity and Specificity Analysis. J Clin Diagn Res. 2016 Oct;10(10):YE01-YE06. doi: 10.7860/JCDR/2016/18129.8744. Epub 2016 Oct 1.

  PMID: 27891446 BACKGROUND

• Decalmer SC, Webster D, Kelsall AA, McGuinness K, Woodcock AA, Smith JA. Chronic cough: how do cough reflex sensitivity and subjective assessments correlate with objective cough counts during ambulatory monitoring? Thorax. 2007 Apr;62(4):329-34. doi: 10.1136/thx.2006.067413. Epub 2006 Nov 13.

  PMID: 17101736 BACKGROUND

• Gabaldon-Figueira JC, Brew J, Dore DH, Umashankar N, Chaccour J, Orrillo V, Tsang LY, Blavia I, Fernandez-Montero A, Bartolome J, Grandjean Lapierre S, Chaccour C. Digital acoustic surveillance for early detection of respiratory disease outbreaks in Spain: a protocol for an observational study. BMJ Open. 2021 Jul 2;11(7):e051278. doi: 10.1136/bmjopen-2021-051278.

  PMID: 34215614 BACKGROUND

• Hall JI, Lozano M, Estrada-Petrocelli L, Birring S, Turner R. The present and future of cough counting tools. J Thorac Dis. 2020 Sep;12(9):5207-5223. doi: 10.21037/jtd-2020-icc-003.

  PMID: 33145097 BACKGROUND

• Matos S, Birring SS, Pavord ID, Evans DH. An automated system for 24-h monitoring of cough frequency: the leicester cough monitor. IEEE Trans Biomed Eng. 2007 Aug;54(8):1472-9. doi: 10.1109/TBME.2007.900811.

  PMID: 17694868 BACKGROUND

• Park SC, Kang MJ, Han CH, Lee SM, Kim CJ, Lee JM, Kang YA. Prevalence, incidence, and mortality of nontuberculous mycobacterial infection in Korea: a nationwide population-based study. BMC Pulm Med. 2019 Aug 1;19(1):140. doi: 10.1186/s12890-019-0901-z.

  PMID: 31370826 BACKGROUND

• Porter P, Abeyratne U, Swarnkar V, Tan J, Ng TW, Brisbane JM, Speldewinde D, Choveaux J, Sharan R, Kosasih K, Della P. A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children. Respir Res. 2019 Jun 6;20(1):81. doi: 10.1186/s12931-019-1046-6.

  PMID: 31167662 BACKGROUND

• Ragonnet R, Trauer JM, Geard N, Scott N, McBryde ES. Profiling Mycobacterium tuberculosis transmission and the resulting disease burden in the five highest tuberculosis burden countries. BMC Med. 2019 Nov 22;17(1):208. doi: 10.1186/s12916-019-1452-0.

  PMID: 31752895 BACKGROUND

• Sharan RV, Abeyratne UR, Swarnkar VR, Claxton S, Hukins C, Porter P. Predicting spirometry readings using cough sound features and regression. Physiol Meas. 2018 Sep 5;39(9):095001. doi: 10.1088/1361-6579/aad948.

  PMID: 30091716 BACKGROUND

• Song WJ, Chang YS, Faruqi S, Kang MK, Kim JY, Kang MG, Kim S, Jo EJ, Lee SE, Kim MH, Plevkova J, Park HW, Cho SH, Morice AH. Defining Chronic Cough: A Systematic Review of the Epidemiological Literature. Allergy Asthma Immunol Res. 2016 Mar;8(2):146-55. doi: 10.4168/aair.2016.8.2.146. Epub 2015 Sep 18.

  PMID: 26739408 BACKGROUND

• Turner RD. Cough in pulmonary tuberculosis: Existing knowledge and general insights. Pulm Pharmacol Ther. 2019 Apr;55:89-94. doi: 10.1016/j.pupt.2019.01.008. Epub 2019 Feb 1.

  PMID: 30716411 BACKGROUND

• Sanchez-Olivieri I, Rudd M, Gabaldon-Figueira JC, Carmona-Torre F, Del Pozo JL, Moorsmith R, Jover L, Galvosas M, Small P, Grandjean Lapierre S, Chaccour C. Performance evaluation of human cough annotators: optimal metrics and sex differences. BMJ Open Respir Res. 2023 Nov;10(1):e001942. doi: 10.1136/bmjresp-2023-001942.

  PMID: 37945314 DERIVED

Biospecimen

Retention: SAMPLES WITHOUT DNA

Voice records of participants taking part in the validation sub-studies.

MeSH Terms

Conditions

Cough; Pulmonary Disease, Chronic Obstructive; Gastroesophageal Reflux; Asthma; Tuberculosis

Condition Hierarchy (Ancestors)

Respiration Disorders; Respiratory Tract Diseases; Signs and Symptoms, Respiratory; Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Lung Diseases, Obstructive; Lung Diseases; Chronic Disease; Disease Attributes; Pathologic Processes; Esophageal Motility Disorders; Deglutition Disorders; Esophageal Diseases; Gastrointestinal Diseases; Digestive System Diseases; Bronchial Diseases; Respiratory Hypersensitivity; Hypersensitivity, Immediate; Hypersensitivity; Immune System Diseases; Mycobacterium Infections; Actinomycetales Infections; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Infections

Study Officials

• Carlos Chaccour, MD, PhD

  Clinica Universidad de Navarra

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 2, 2021
• First Posted: September 13, 2021
• Study Start: September 15, 2021
• Primary Completion: September 15, 2022
• Study Completion: September 15, 2022
• Last Updated: November 20, 2025

Record last verified: 2025-10

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, ICF, CSR
• Time Frame: Data will become available at the completion of the study (2026) and will remain available from that moment onward.
• Access Criteria: Upon request to researchers

Locations

ES (1)