Abdominal Disease, Bronchopneumonia, Congenital Heart Disease
Conditions
Brief summary
The purpose of this research is to develop a body voice artificial intelligence (AI) recognition device, also referred to as an AI-assisted body sound identification device, by utilizing a deep learning-based novel AI algorithm in conjunction with a big body voice model. It could identify normal and abnormal heart, breath, and bowel sounds, and to provide early screening and auxiliary diagnosis of congenital heart disease (CHD), respiratory infections, diarrhea and other common multi-occurring diseases.
Detailed description
The study employed a multicenter cross-sectional design. The real-world data collected for this study included normal and definitively diagnosed heart sounds in children with congenital heart disease, normal and definitively diagnosed respiratory tract infections in children with breath sounds, specific cough sounds, and normal and definitively diagnosed children's bowel sounds with diarrhea. The specialist team will carry out data governance, annotation, and feature sound extraction on the gathered normal and aberrant sounds, in order to generate a superior multimodal training dataset. Large model artificial intelligence algorithms (deep learning, machine learning, etc.) are used to model and train the algorithm model of the body voice AI recognition device, so that it can distinguish between normal and abnormal sound signals by AI. The results of body sound AI identification will be compared with diagnostic reports from echocardiograms, chest X-rays, and belly X-rays in terms of AUC (Area Under Curve) score, sensitivity, specificity, and accuracy to evaluate the impact of AI recognition devices on illness screening and supplementary diagnosis. External validation will be conducted using homogeneous data from other sites. This project aims to develop a new generation of intelligent sound auscultation instruments that could be used for early screening and auxiliary diagnosis of congenital heart disease , respiratory infections, diarrhea and other common multi-occurring diseases by utilizing large model artificial intelligence technologies.
Interventions
DIAGNOSTIC_TESTHeart Auscultation and Echocardiography
Heart auscultation will be done by pediatrician and echocardiography by echocardiologist
DIAGNOSTIC_TESTChest Auscultation and Chest imaging examinations
Chest auscultation will be done by pediatrician and chest imaging examinations by radiologist
DIAGNOSTIC_TESTAbdominal Auscultation and Abdominal imaging examinations
Abdominal auscultation will be done by pediatrician and chest imaging examinations by radiologist
Sponsors
Xinhua Hospital, Shanghai Jiao Tong University School of Medicine
Study design
Observational model
COHORT
Time perspective
CROSS_SECTIONAL
Eligibility
Sex/Gender
ALL
Age
No minimum to 18 Years
Healthy volunteers
Yes
Inclusion criteria
1. Age 0\~18 years old, gender is not limited 2. Children who have been diagnosed with congenital heart disease by cardiac ultrasound or who do not have congenital heart disease 3. Children diagnosed with bronchopneumonia or without bronchopneumonia 4. Children who are clinically diagnosed with intestinal diseases or who do not suffer from intestinal diseases 5. Informed consent
Exclusion criteria
1. ≥ 18 years old 2. Children who are unable to undergo cardiac ultrasound, chest imaging or other related examinations 3. Subjects who are unable to obtain informed consent, or who are unwilling to cooperate with the provision of diagnosis and treatment related data for further analysis and research as required by the study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity | 1 month | Sensitivity in CHD, lung disease and abdominal screening by different artificial intelligence algorithm and auscultation |
| Specificity | 1 month | Specificity in CHD, lung disease and abdominal screening by different artificial intelligence algorithm and auscultation |
| AUC | 1 month | AUC in CHD, lung disease and abdominal screening by different artificial intelligence algorithm and auscultation |
Countries
China
Contacts
CONTACTXin Sun, MD
PRINCIPAL_INVESTIGATORXin Sun, MD
Xinhua Hospital, Shanghai J iao Tong University School of Medicine
Outcome results
None listed