Related Experiment Video
Updated: Aug 1, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Clinical Instability Is a Sign of Severity of Illness: A Cohort Study
Murray M Pollack1, Eduardo Trujillo Rivera2, Hiroki Morizono3
1Department of Pediatrics, Division of Critical Care Medicine, Children's National Hospital and The George Washington University School of Medicine and Health Sciences, Washington, DC.
Insights
Clinical instability, measured by changes in mortality risk, indicates illness severity in pediatric intensive care units. Greater instability in deaths compared to survivors confirms this clinical teaching.
Area of Science:
- Pediatric critical care medicine
- Clinical informatics
- Machine learning in healthcare
Background:
- Clinical instability is a recognized indicator of illness severity in critically ill patients.
- Quantifying within-patient clinical instability and its association with mortality risk is crucial for improving patient outcomes.
Purpose of the Study:
- To test the hypothesis that within-patient clinical instability, measured by changes in mortality risk over time, is indicative of increasing illness severity.
- To compare clinical instability between survivors and non-survivors in pediatric intensive care units.
Main Methods:
- Analysis of electronic health data from 8,399 admissions in pediatric and cardiac intensive care units (ICUs) between January 1, 2018, and February 29, 2020.
- Utilized the Criticality Index-Mortality, a machine learning algorithm, to assess mortality risk every three hours.
- Compared within-patient changes in mortality risk between survivors and deaths, employing effect size measures like rank-biserial correlation.
Main Results:
- Deaths exhibited substantially greater maximum risk increases (11.1%–16.1%) and decreases (-7.3%–-10.0%) compared to survivors (median < ±0.1%).
- Within-patient volatility was over 4.5-fold greater in deaths than survivors during the first ICU day, plateauing at 2.5-fold greater by ICU days 4-5.
- While statistical significance (p < 0.001) was observed, effect sizes indicated non-clinically important differences in overall instability, but moderate to high clinical importance for maximum risk changes.
Conclusions:
- Episodic clinical instability, quantified by mortality risk fluctuations, reliably indicates increasing illness severity in pediatric ICU patients.
- Greater maximum and within-patient clinical instability in non-survivors supports the established clinical principle that instability signifies severity of illness.
Objectives:
Test the hypothesis that within patient clinical instability measured by deterioration and improvement in mortality risk over 3-, 6-, 9-, and 12-hour time intervals is indicative of increasing severity of illness.
Design:
Analysis of electronic health data from January 1, 2018, to February 29, 2020.
Setting:
PICU and cardiac ICU at an academic children's hospital.
Patients:
All PICU patients. Data included descriptive information, outcome, and independent variables used in the Criticality Index-Mortality.
Interventions:
None.
Measurements And Main Results:
There were 8,399 admissions with 312 deaths (3.7%). Mortality risk determined every three hours using the Criticality Index-Mortality, a machine learning algorithm calibrated to this hospital. Since the sample sizes were sufficiently large to expect statical differences, we also used two measures of effect size, the proportion of time deaths had greater instability than survivors, and the rank-biserial correlation, to assess the magnitude of the effect and complement our hypothesis tests. Within patient changes were compared for survivors and deaths. All comparisons of survivors versus deaths were less than 0.001. For all time intervals, two measures of effect size indicated that the differences between deaths and survivors were not clinically important. However, the within-patient maximum risk increase (clinical deterioration) and maximum risk decrease (clinical improvement) were both substantially greater in deaths than survivors for all time intervals. For deaths, the maximum risk increase ranged from 11.1% to 16.1% and the maximum decrease ranged from -7.3% to -10.0%, while the median maximum increases and decreases for survivors were all less than ± 0.1%. Both measures of effect size indicated moderate to high clinical importance. The within-patient volatility was greater than 4.5-fold greater in deaths than survivors during the first ICU day, plateauing at ICU days 4-5 at 2.5 greater volatility.
Conclusions:
Episodic clinical instability measured with mortality risk is a reliable sign of increasing severity of illness. Mortality risk changes during four time intervals demonstrated deaths have greater maximum and within-patient clinical instability than survivors. This observation confirms the clinical teaching that clinical instability is a sign of severity of illness.
Related Concept Videos
01:29Bias in Epidemiological Studies
01:27Confounding in Epidemiological Studies
01:18Factors Affecting Illness
For instance, risk factors are connected to illness,...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
01:25Interpreting Run Charts