This study aims to establish a standardized, synchronized data collection system for pediatric symptom questionnaires, cough sounds, and breath sounds, and to construct a multimodal database of pediatric respiratory diseases including both disease cases and healthy controls. Using the final research labels determined by clinicians' diagnoses, health status assessments, and research team review as the reference standard, this study will develop and validate a multimodal assisted diagnostic model for common pediatric respiratory diseases based on symptom questionnaires, cough sounds, and breath sounds. The study will primarily evaluate the diagnostic performance of the model in distinguishing healthy children from children with respiratory diseases, screening for asthma and asthma-related cough, and identifying pneumonia, tracheitis/bronchitis, upper airway-related diseases, and common causes of chronic cough. It will also assess the incremental value of cough sounds and breath sounds beyond symptom questionnaire information.
None
None
The target population will include children aged 28 days to 18 years, including children presenting to the outpatient department, emergency department, or inpatient wards of Shanghai Children's Medical Center with cough, wheezing, fever with respiratory symptoms, nasal congestion, rhinorrhea, sore throat, or other respiratory complaints, as well as healthy children recruited during routine health examinations or children without respiratory complaints. The study population will cover common pediatric respiratory diseases and healthy controls, providing a representative disease spectrum.
Cohort
Prospective
Multimodal respiratory data collection
Diagnostic testParticipants will complete a structured symptom questionnaire, cough sound recording using a smartphone application, and breath sound recording using an electronic stethoscope. These data will be used to develop and evaluate a multimodal assisted diagnostic model and will not guide real-time clinical decision-making.
Area under the receiver operating characteristic curve of the multimodal assisted diagnostic model
The area under the receiver operating characteristic curve will be used to evaluate the diagnostic performance of the multimodal assisted diagnostic model integrating symptom questionnaire, cough sound, and breath sound data. The model will be assessed against the final clinical research label for distinguishing children with respiratory diseases from healthy controls and for identifying major pediatric respiratory disease categories.
Area under the precision-recall curve of the multimodal assisted diagnostic model
The area under the precision-recall curve will be used to evaluate the diagnostic performance of the multimodal assisted diagnostic model, particularly in settings with imbalanced disease categories. The model will be assessed against the final clinical research label.
Sensitivity of the multimodal assisted diagnostic model
Specificity of the multimodal assisted diagnostic model
Positive predictive value of the multimodal assisted diagnostic model
Negative predictive value of the multimodal assisted diagnostic model
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
