TBscreen: A passive cough classifier for tuberculosis screening with a controlled dataset.
Sci Adv
; 10(1): eadi0282, 2024 Jan 05.
Article
en En
| MEDLINE
| ID: mdl-38170773
ABSTRACT
Recent respiratory disease screening studies suggest promising performance of cough classifiers, but potential biases in model training and dataset quality preclude robust conclusions. To examine tuberculosis (TB) cough diagnostic features, we enrolled subjects with pulmonary TB (N = 149) and controls with other respiratory illnesses (N = 46) in Nairobi. We collected a dataset with 33,000 passive coughs and 1600 forced coughs in a controlled setting with similar demographics. We trained a ResNet18-based cough classifier using images of passive cough scalogram as input and obtained a fivefold cross-validation sensitivity of 0.70 (±0.11 SD). The smartphone-based model had better performance in subjects with higher bacterial load {receiver operating characteristic-area under the curve (ROC-AUC) 0.87 [95% confidence interval (CI) 0.87 to 0.88], P < 0.001} or lung cavities [ROC-AUC 0.89 (95% CI 0.88 to 0.89), P < 0.001]. Overall, our data suggest that passive cough features distinguish TB from non-TB subjects and are associated with bacterial burden and disease severity.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Tuberculosis
/
Tuberculosis Pulmonar
Tipo de estudio:
Diagnostic_studies
/
Etiology_studies
/
Prognostic_studies
/
Screening_studies
Límite:
Humans
País/Región como asunto:
Africa
Idioma:
En
Revista:
Sci Adv
Año:
2024
Tipo del documento:
Article
País de afiliación:
Estados Unidos