Related Experiment Video
Updated: Jul 14, 2025
Invasive Hemodynamic Monitoring of Aortic and Pulmonary Artery Hemodynamics in a Large Animal Model of ARDS
Published on: November 26, 2018
Automated prediction of cardiorespiratory deterioration in patients with single-ventricle parallel circulation:
Craig G Rusin1, Sebastian I Acosta1, Kennith M Brady2
1Department of Pediatrics-Cardiology, Baylor College of Medicine, Texas Children's Hospital, Houston, Tex.
Insights
A new algorithm can predict cardiorespiratory deterioration in single-ventricle patients 1-2 hours in advance. This early detection in single-ventricle (SV) physiology may improve outcomes by enabling timely interventions.
Area of Science:
- Pediatric Cardiology
- Critical Care Medicine
- Biomedical Informatics
Background:
- Patients with single-ventricle (SV) physiology face high risks of cardiorespiratory deterioration between surgical palliation stages.
- Early detection of deterioration is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To evaluate a previously validated predictive algorithm for its ability to detect cardiorespiratory deterioration in pediatric patients with SV physiology.
- To assess the algorithm's performance in a prospective, multi-center cohort during the interstage period.
Main Methods:
- A prospective study collected high-resolution physiologic data from 58 SV patients using the Sickbay software platform.
- Data were analyzed using a pre-existing predictive algorithm without retraining.
- Performance was assessed using standard metrics including receiver operating curve (ROC) area, likelihood ratios, and alert rates.
Main Results:
- The algorithm demonstrated high sensitivity and specificity in detecting impending cardiorespiratory deterioration events (ROC = 0.927).
- The risk index metric provided a 1- to 2-hour advance warning before overt extremis.
- A total of 30 deterioration events were observed within approximately 28,991 hours of monitored data.
Conclusions:
- The algorithm can provide a 1- to 2-hour warning for 53.6% of cardiorespiratory deterioration events in SV patients.
- The system generated a low rate of 2.5 alarms per patient per day, indicating clinical feasibility.
- This predictive tool holds promise for improving management of SV patients during critical post-operative and interstage periods.
Objectives:
Patients with single-ventricle physiology have a significant risk of cardiorespiratory deterioration between their first- and second-stage palliation surgeries. Detection of deterioration episodes may allow for early intervention and improved outcomes.
Methods:
A prospective study was executed at Nationwide Children's Hospital, Children's Hospital of Philadelphia, and Children's Hospital Colorado to collect physiologic data of subjects with single ventricle physiology during all hospitalizations between neonatal palliation and II surgeries using the Sickbay software platform (Medical Informatics Corp). Timing of cardiorespiratory deterioration events was captured via chart review. The predictive algorithm previously developed and validated at Texas Children's Hospital was applied to these data without retraining. Standard metrics such as receiver operating curve area, positive and negative likelihood ratio, and alert rates were calculated to establish clinical performance of the predictive algorithm.
Results:
Our cohort consisted of 58 subjects admitted to the cardiac intensive care unit and stepdown units of participating centers over 14 months. Approximately 28,991 hours of high-resolution physiologic waveform and vital sign data were collected using the Sickbay. A total of 30 cardiorespiratory deterioration events were observed. the risk index metric generated by our algorithm was found to be both sensitive and specific for detecting impending events one to two hours in advance of overt extremis (receiver operating curve = 0.927).
Conclusions:
Our algorithm can provide a 1- to 2-hour advanced warning for 53.6% of all cardiorespiratory deterioration events in children with single ventricle physiology during their initial postop course as well as interstage hospitalizations after stage I palliation with only 2.5 alarms being generated per patient per day.
