Authors:
João Dinis
;
Guilherme Campos
;
João Rodrigues
and
Alda Marques
Affiliation:
University of Aveiro, Portugal
Keyword(s):
Adventitious lung sounds, Respiratory cycles, Crackles, Wheezes, Diagnosis, Respiratory diseases, COPD, Asthma, Cystic fibrosis, Pneumonia.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Cardiovascular Technologies
;
Computing and Telecommunications in Cardiology
;
Data Engineering
;
Data Management and Quality
;
Data Manipulation
;
Data Visualization
;
Electronic Health Records and Standards
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Medical and Nursing Informatics
;
Sensor Networks
;
Software Systems in Medicine
Abstract:
Significant research efforts have been dedicated to the automatic detection of adventitious lung sounds, using, for this purpose, different algorithms. The validation of these algorithms is based on the comparison of their results with reference annotations and therefore requires the development of user-friendly annotation software. This paper presents an application, developed in Matlab®, for the annotation of respiratory sounds. The user can identify respiratory cycles and adventitious sounds – crackles and wheezes – directly on the waveforms displayed on the screen, which may be simultaneously played back. The audio playback speed is user-adjustable and synchronised with the cursor display. Specific annotation file storage formats were defined. Preliminary usability tests performed by three health professionals using twenty respiratory sound files from six patients (with pneumonia and cystic fibrosis) indicate that the software is user-friendly and effective, allowing simple and q
uick annotations.
(More)