Related Experiment Video
Updated: Jan 26, 2026
How to Administer Near-Infrared Spectroscopy in Critically ill Neonates, Infants, and Children
Published on: August 19, 2020
Early prediction of critical events for infants with single-ventricle physiology in critical care using routinely
Victor M Ruiz1, Lucas Saenz2, Alejandro Lopez-Magallon3
1Department of Anesthesiology and Critical Care Medicine, Department of Biomedical and Health Informatics, and Tsui Laboratory, Children's Hospital of Philadelphia, Philadelphia, Pa; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pa.
Insights
Predicting critical events in infants with single-ventricle physiology is challenging. The Cardiac-intensive-care Warning INdex (C-WIN) system uses machine learning to accurately predict these events, enabling timely interventions.
Area of Science:
- Pediatric critical care medicine
- Biomedical informatics
- Machine learning in healthcare
Background:
- Critical events in infants with congenital heart disease are frequent and difficult to predict, leading to adverse outcomes.
- Early prediction of critical events like cardiopulmonary resuscitation or intubation is crucial for infants with single-ventricle physiology before surgery.
Purpose of the Study:
- To develop and evaluate a machine learning system for early prediction of critical events in infants with single-ventricle physiology.
- To hypothesize that naïve Bayesian models can accurately predict critical events using expert knowledge and clinical data.
Main Methods:
- Collected data from 93 infants with single-ventricle physiology in a pediatric intensive care unit.
- Developed the Cardiac-intensive-care Warning INdex (C-WIN) system using naïve Bayesian models and expert clinical knowledge.
- Evaluated predictive performance at 1, 2, 4, 6, and 8-hour prediction horizons using area under the receiver operating characteristic curve, sensitivity, and specificity.
Main Results:
- The C-WIN system demonstrated strong predictive performance, with area under the receiver operating characteristic curves ranging from 0.73 to 0.88.
- At a 1-hour prediction horizon, C-WIN achieved an area under the curve of 0.88, with 84% sensitivity and 81% specificity.
- The models successfully leveraged routinely collected clinical data for prediction.
Conclusions:
- Predictive models like C-WIN can significantly improve clinicians' ability to identify high-risk infants.
- Early prediction of critical events allows for timely interventions, potentially reducing morbidity, mortality, and healthcare costs.
- Machine learning models integrating expert knowledge show promise for critical event prediction in pediatric cardiac intensive care.
Objective:
Critical events are common and difficult to predict among infants with congenital heart disease and are associated with mortality and long-term sequelae. We aimed to achieve early prediction of critical events, that is, cardiopulmonary resuscitation, emergency endotracheal intubation, and extracorporeal membrane oxygenation in infants with single-ventricle physiology before second-stage surgery. We hypothesized that naïve Bayesian models learned from expert knowledge and clinical data can predict critical events early and accurately.
Methods:
We collected 93 patients with single-ventricle physiology admitted to intensive care units in a single tertiary pediatric hospital between 2014 and 2017. Using knowledge elicited from experienced cardiac-intensive-care-unit providers and machine-learning techniques, we developed and evaluated the Cardiac-intensive-care Warning INdex (C-WIN) system, consisting of a set of naïve Bayesian models that leverage routinely collected data. We evaluated predictive performance using the area under the receiver operating characteristic curve, sensitivity, and specificity. We performed the evaluation at 5 different prediction horizons: 1, 2, 4, 6, and 8 hours before the onset of critical events.
Results:
The area under the receiver operating characteristic curves of the C-WIN models ranged between 0.73 and 0.88 at different prediction horizons. At 1 hour before critical events, C-WIN was able to detect events with an area under the receiver operating characteristic curve of 0.88 (95% confidence interval, 0.84-0.92) and a sensitivity of 84% at the 81% specificity level.
Conclusions:
Predictive models may enhance clinicians' ability to identify infants with single-ventricle physiology at high risk of critical events. Early prediction of critical events may indicate the need to perform timely interventions, potentially reducing morbidity, mortality, and health care costs.
More Related Videos
05:01A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients
Published on: October 17, 2017
10:38Observational Study Protocol for Repeated Clinical Examination and Critical Care Ultrasonography Within the Simple Intensive Care Studies
Published on: January 16, 2019
Related Concept Videos
01:16Critical Region, Critical Values and Significance Level
In hypothesis testing, a sample statistic is converted to a test statistic using z, t, or chi-square distribution. A critical region is an area under the curve in probability distributions demarcated by the critical value. When the test statistic falls in this region, it suggests that the null hypothesis must be rejected. As this region contains all those values of the...
01:31Critical Values
01:19Critical Thinking
Colleges and universities are...
01:24Critical Thinking I
01:25Critical Thinking II
01:23Criticisms of the Evolutionary Perspective
Evolutionary psychology provides one explanation for these findings, suggesting...