Age-Adjusted Hemodynamic Risk Scoring for Pediatric Patients
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting hemodynamic instability in pediatric patients are inadequate due to the variability of clinical features like heart rate and blood pressure with age, making early detection difficult and requiring significant clinical expertise.
Innovation Solution
A system and method using hardware processors to determine a hemodynamic instability risk score by obtaining age and physiological feature values, applying bivariate classifiers with age-adjusted thresholds to calculate feature contribution scores, and aggregating these scores to provide a risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If normal vital signs and laboratory values are used to detect hemodynamic instability, then the detection method is simple, but the accuracy deteriorates due to age-related variability in clinical features
Solution Approach 1:
The patent applies parameter changes by transforming fixed vital sign thresholds into age-dependent dynamic thresholds. Instead of using static cutoff values for heart rate, blood pressure, and respiratory rate, the system calculates age-adjusted thresholds using established pediatric reference data, allowing accurate detection across different age groups while maintaining operational simplicity through automated computation
2Measurement precision
If age-adjusted thresholds are applied to improve detection accuracy, then measurement precision improves, but device complexity increases due to multiple feature thresholds and classification logic
Solution Approach 1:
The patent segments the complex detection task into independent univariate classifiers for each physiological feature (heart rate, blood pressure, respiratory rate, shock index). Each classifier independently determines age-adjusted thresholds and calculates individual feature scores, which are then aggregated to produce the final hemodynamic instability risk score. This modular segmentation reduces overall system complexity while maintaining high detection accuracy
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure pertains to a system configured to determine a hemodynamic instability risk score for a pediatric subject. The system is configured to: obtain an age of the subject; obtain feature values for one or more features associated with physiological characteristics of the subject; determine one or more feature value thresholds for individual features that indicate risk of hemodynamic instability in the subject, the feature value thresholds determined based on the age of the subject; determine feature contribution prediction scores for the individual features based on whether the obtained feature values breach one or more of the determined feature value thresholds for the individual features; and aggregate the feature contribution prediction scores to determine the hemodynamic instability risk score for the subject.