The purpose of this study is to implement and externally validate an inpatient ML algorithm that combines pulse oximetry features for critical congenital heart disease (CCHD) screening.
Age < 22 days
Fetuses suspected to have congenital heart disease
Newborns with suspected/confirmed critical congenital heart disease
Asymptomatic newborn undergoing SpO2 screening for CCHD
Echocardiogram completed prior to enrollment as the newborn would then no longer be considered "asymptomatic undergoing SpO2 screening for CCHD"
For Newborns with confirmed/suspected congenital heart disease (CHD): a) Patent ductus arteriosus and/or atrial septal defect/patent foramen ovale without other defects, b) Corrective cardiac surgical or catheter intervention performed before enrollment or c) Current infusions of vasoactive medications other than prostaglandin therapy.
Single group
SpO2/PIx Measurement and ML Algorithm
Diagnostic testRight upper and any lower extremity oxygen saturation (SpO2) and perfusion index (PIx) will be measured and an online ML inference model will be used to classify a newborn as healthy versus CCHD as new pulse oximetry data is collected.
Area under the curve for receiver operating characteristics for critical congenital heart disease using ML inpatient algorithm.
Receiver operating characteristics reflect a combination of sensitivity and specificity of a test. The investigators will identify the true positive and true negative rates for CCHD by confirming health status to a minimum of 2 months of age. The investigators will also utilize birth defect and death registries for missing infants.
Sensitivity for critical congenital heart disease using ML inpatient algorithm (0-24 hours and 24-48 hours)
The investigators will identify the true positive rate for CCHD by confirming health status to a minimum of 2 months of age. CCHD will be defined based on echocardiogram or parent report if echocardiogram not present. The investigators will also utilize birth defect and death registries for missing infants.
Specificity for critical congenital heart disease using ML inpatient algorithm (0-24 hours and 24-48 hours)
The investigators will identify the true negative rate by confirming health status to a minimum of 2 months of age. CCHD will be defined based on echocardiogram or parent report if echocardiogram not present. The investigators will also utilize birth defect and death registries for missing infants.
Area under the curve for receiver operating characteristics for critical congenital heart disease using dynamic ML algorithm
Receiver operating characteristics reflect a combination of sensitivity and specificity of a test. The investigators will identify the true positive and true negative rates for CCHD by confirming health status to a minimum of 2 months of age. The investigators will also utilize birth defect and death registries for missing infants.
Sensitivity for critical congenital heart disease using dynamic ML algorithm
The investigators will identify the true positive rate for CCHD by confirming health status to a minimum of 2 months of age. CCHD will be defined based on echocardiogram or parent report if echocardiogram not present. The investigators will also utilize birth defect and death registries for missing infants.
Frequency of repeated inpatient ML measurements
If a newborn has an initial "fail" during the inpatient ML screening algorithm, then 1 repeated measurement will occur within 3 hours after waiting at least 30 minutes. If the next repeated measurement is a "fail" then the final classification assigned will be a "fail." If the repeat measurement is a "pass" the final classification will be a "pass." To gauge impact on nursing time for repeated measurements, The investigators will quantify how often these repeated measurements occur.
Feasibility: Number of minutes needed to obtain simultaneous artifact free hand and foot measurements such that all pulse oximetry features can be included.
In order to incorporate the radiofemoral delay component of the pulse oximetry features, the hand and foot waveforms need to be artifact free simultaneously. The pulse oximetry device will give a result every minute to give the investigators an idea on how long it may take to reach simultaneously artifact free waveforms.
Feasibility: Number of outpatient pulse oximetry measurements obtained
Pulse oximetry measurements are not currently conducted in the outpatient setting. Thus, the investigators will assess feasibility for future trials based on how many outpatient measurements are obtained versus missed in the study protocol.
Click on the lead sponsor to view all of their trials.
University of California, Davis
Lead sponsor
National Institutes of Health (NIH)
Collaborator
