Artificial Intelligence (AI), Auscultation for Clinical Evaluation, Cluster Randomized Trial, Congenital Heart Disease (CHD), Screening Tool
Conditions
Brief summary
This study plans to conduct clinical validation of the model in real clinical settings, comparing it with primary care physicians and specialist physicians to ensure the model's practicality. Through continuous optimization and practice, the study aims to use AI-assisted heart sound auscultation to empower the auscultation capabilities of primary care obstetricians, pediatricians, and non-cardiovascular specialists nationwide. This will not only reduce the missed diagnosis rate and improve the detection rate of existing CHD screenings, but also expand the coverage of current CHD screening networks, incorporating newborns, infants, preschool children, children, and adolescents aged 0-18 years into the screening scope. The study aims to establish a new benchmark in child health management by providing feasible and cost-effective child health management solutions for other developing countries, contributing to global efforts for the health of children.
Interventions
DIAGNOSTIC_TESTPrimary care physicians
For participants in Group A, a nonblinded independent staff member will first collect medical history, followed by sequential auscultation and CHD assessment by a specialist physician and a primary care physician, with an echocardiogram performed last.
DIAGNOSTIC_TESTAI + Primary care physicians
For participants in Group B, after medical history collection, both a specialist physician and a primary care physician will perform auscultation and CHD assessment. Subsequently, the primary care physician will use an electronic stethoscope to collect heart sound data according to the protocol and upload the recordings to a cloud platform. The AI model will analyze the data on the cloud platform and provide a diagnostic result within 5-10 seconds for the primary care physician's reference. The primary care physician may reassess the findings based on the AI model's feedback, and the participant will then undergo an echocardiogram.
Sponsors
Kun Sun
Bill and Melinda Gates Foundation
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
SCREENING
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
No minimum to 18 Years
Healthy volunteers
Yes
Inclusion criteria
(Schools): * The school is of the type: kindergarten, primary school, junior high school, or senior high school. * The school has medical screening facilities and conditions that can support AI-assisted screening. * The area where the school is located has at least one primary healthcare institution willing to participate in this trial. * The school's management and teaching staff are willing to participate in the study and can cooperate to complete the related screening and data collection work.
Exclusion criteria
(Schools): * More than half of the students in the school refuse to participate in the trial. * Schools that are unable to complete the study due to severe limitations in geographical location and transportation conditions. * Schools lacking medical screening facilities and conditions necessary for the implementation of screening. * Areas where there are no primary healthcare institutions willing to participate in this trial. * Schools whose management and teaching staff refuse to participate in the study or are unable to cooperate in completing the related screening and data collection work. Inclusion Criteria (Individuals): * Children aged between 0 and 18 years, regardless of gender. * Children who agree to undergo echocardiography to determine the presence of congenital heart disease. * Individuals who voluntarily participate in this study and sign the informed consent form.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Sensitivity of auscultation in identifying CHD between independent auscultation by primary care physicians and AI-assisted auscultation by primary care physicians | From enrollment to the end of treatment at 6 months |
Secondary
| Measure | Time frame |
|---|---|
| Sensitivity of Auscultation in CHD Detection: AI model & Experienced Cardiologists' Independent Auscultatio | From enrollment to the end of treatment at 6 months |
| Specificity of Auscultation in CHD Detection: Primary Care Physicians' Independent Auscultation & AI-assisted Primary Healthcare Physicians' Auscultation & AI model & Experienced Cardiologists' Independent Auscultation | From enrollment to the end of treatment at 6 months |
| Accuracy of Auscultation in CHD Detection: Primary Care Physicians' Independent Auscultation & AI-assisted Primary Care Physicians' Auscultation & AI model & Experienced Cardiologists' Independent Auscultation | From enrollment to the end of treatment at 6 months |
| The rate of diagnostic revisions by physicians, the proportions of correct and incorrect changes | From enrollment to the end of treatment at 6 months |
Countries
China
Outcome results
None listed