Related Experiment Video
Updated: Jan 11, 2026
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Exploring Novel Data-Driven Clustering Methods for Uncovering Patterns in Longitudinal Neonatal Postoperative
Stephanie M Helman1, Nathan T Riek2, Susan M Sereika3
1School of Medicine, Department of Medicine, Division of General Internal Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania.
Objective:
To identify distinct postoperative temperature trajectories in neonates with congenital heart defects after cardiopulmonary bypass (CPB), using advanced unsupervised machine learning clustering methods, corroborate findings, and evaluate their prognostic value on outcomes.
Patients And Methods:
A secondary cohort analysis of prospective data collected from a single pediatric referral center's CardioAccess data registry, consistent of neonates who underwent CPB between January 1, 2015, and January 1, 2019, was performed. Postoperative temperatures were extracted from medical records (48 hours). Group-based trajectory modeling (GBTM) performance was compared with self-organizing maps (SOM) and k-means clustering. Cluster membership and model fit were optimized for 3 temperature clusters per method. The primary outcome was a composite of postoperative complications. Clustering techniques were compared and associated with outcomes using adjusted multivariable binary logistic regression.
Results:
Neonates of ≥34 weeks' gestation underwent CPB (N=450). GBTM, SOM, and k-means identified membership for 3 groups: (1) persistent hypothermia (n=38 [9%]; n=49 [11%]; and n=40 [9%], respectively); (2) resolving hypothermia (n=233 [51%]; n=227 [50%]; and n=147 [33%], respectively); and (3) normothermia (n=179 [40%]; n=174 [39%]; and n=263 [58%], respectively). Concordance between techniques found strong agreement between GBTM and SOM (κ=0.92) and weak agreement between GBTM and k-means (κ=0.41). After adjustment, persistently hypothermic neonates compared with normothermic neonates were associated with higher odds of the complication composite outcome in the GBTM (odds ratio [OR], 2.8; 95% CI, 1.0-7.3; P=.04) and SOM (OR, 2.3; 95% CI, 1.0-5.4; P=.04) models, but not in the k-means model (OR, 1.4; 95% CI, 0.7-3.1; P=.38).
Conclusion:
Exploring concordance between different machine learning techniques shows that temperature in neonates after CPB follows unique trajectories. Those exhibiting persistent hypothermia trends are at higher risk of adverse outcomes.
Related Concept Videos
01:14Temperature Measurement Sites
Oral: When assessing oral temperature, the thermometer tip should be placed under the tongue in the posterior sublingual pocket. It offers accurate readings and can be...
01:19Assessing Body Temperature - Temporal Artery
Step 1: Perform hand hygiene and don a fresh pair of gloves to prevent cross-infection and ensure patient safety.
Step 2: Explain the procedure to the patient to establish trust. Clear communication establishes trust with the patient, ensures they understand what to expect, promotes cooperation, and enhances comfort during the procedure.
Step 3: Assess the patient's...
01:13Equipments Used to Measure Body Temperature
Glass-bulb Thermometer:
Glass-bulb thermometers are hollow glass tubes with a bulb tip containing liquid such as ethanol or mercury. Historically, glass bulb mercury thermometers were the standard device to measure body temperature. Today, mercury thermometers are prohibited in many countries due to the hazardous effects of mercury and the risk of exposure if the glass bulb breaks. In general,...
01:26Patterns of Fever
01:27Assessing Body Temperature - Rectal
Follow these steps for rectal temperature assessment:
Step 1: Perform hand hygiene and don clean gloves to prevent cross-infection.
Step 2: Position the patient in a side-lying position to better visualize the rectal...
01:52Regression Toward the Mean