Related Experiment Video
Updated: Oct 5, 2025
Experimental Model to Evaluate Resolution of Pneumonia
Published on: February 17, 2023
Evaluation of the Need for Intensive Care in Children With Pneumonia: Machine Learning Approach
Yun-Chung Liu1,2, Hao-Yuan Cheng1,3, Tu-Hsuan Chang4
1Department of Pediatrics, National Taiwan University Hospital, College of Medicine, National Taiwan University, Taipei City, Taiwan.
Insights
Machine learning accurately predicts intensive care unit (ICU) admission for pediatric pneumonia patients. This tool identifies key clinical factors, aiding timely decisions for better patient outcomes.
Area of Science:
- Pediatric critical care medicine
- Machine learning applications in healthcare
- Clinical decision support systems
Background:
- Accurate prediction of intensive care unit (ICU) admission for pediatric pneumonia is vital for improving patient prognosis.
- Existing clinical guidelines for ICU admission in pediatric pneumonia lack practical applicability.
- A need exists for a reliable system to guide ICU admission decisions for children with pneumonia.
Purpose of the Study:
- To develop and evaluate machine learning (ML) algorithms for predicting ICU admission in pediatric pneumonia patients within 24 hours.
- To identify key clinical indicators that inform ICU admission decisions for pediatric pneumonia.
- To assess the performance of ML models in predicting the need for intensive care.
Main Methods:
- Retrospective analysis of 8464 pediatric pneumonia hospitalizations (2010-2019) at National Taiwan University Hospital.
- Collection of patient data including underlying diseases, clinical signs, and laboratory results at admission.
- Development and validation of ML algorithms (e.g., Random Forest) to predict ICU transfer, evaluating performance metrics like AUC and average precision.
Main Results:
- 13.8% of pediatric pneumonia patients required ICU transfer within 24 hours.
- Early ICU transfer patients were younger, had more underlying diseases, and presented with abnormal vital signs and lab data.
- The Random Forest algorithm demonstrated high predictive performance (AUC 0.99), with low systolic blood pressure and specific comorbidities being key predictors.
Conclusions:
- Machine learning offers a clinically applicable approach for developing triage algorithms in pediatric pneumonia.
- Key predictors for ICU admission include age, underlying conditions, vital signs, and laboratory results.
- This ML-driven tool can assist clinicians in making timely and informed decisions regarding intensive care for children with pneumonia.
Background:
Timely decision-making regarding intensive care unit (ICU) admission for children with pneumonia is crucial for a better prognosis. Despite attempts to establish a guideline or triage system for evaluating ICU care needs, no clinically applicable paradigm is available.
Objective:
The aim of this study was to develop machine learning (ML) algorithms to predict ICU care needs for pediatric pneumonia patients within 24 hours of admission, evaluate their performance, and identify clinical indices for making decisions for pediatric pneumonia patients.
Methods:
Pneumonia patients admitted to National Taiwan University Hospital from January 2010 to December 2019 aged under 18 years were enrolled. Their underlying diseases, clinical manifestations, and laboratory data at admission were collected. The outcome of interest was ICU transfer within 24 hours of hospitalization. We compared clinically relevant features between early ICU transfer patients and patients without ICU care. ML algorithms were developed to predict ICU admission. The performance of the algorithms was evaluated using sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and average precision. The relative feature importance of the best-performing algorithm was compared with physician-rated feature importance for explainability.
Results:
A total of 8464 pediatric hospitalizations due to pneumonia were recorded, and 1166 (1166/8464, 13.8%) hospitalized patients were transferred to the ICU within 24 hours. Early ICU transfer patients were younger (P<.001), had higher rates of underlying diseases (eg, cardiovascular, neuropsychological, and congenital anomaly/genetic disorders; P<.001), had abnormal laboratory data, had higher pulse rates (P<.001), had higher breath rates (P<.001), had lower oxygen saturation (P<.001), and had lower peak body temperature (P<.001) at admission than patients without ICU transfer. The random forest (RF) algorithm achieved the best performance (sensitivity 0.94, 95% CI 0.92-0.95; specificity 0.94, 95% CI 0.92-0.95; AUC 0.99, 95% CI 0.98-0.99; and average precision 0.93, 95% CI 0.90-0.96). The lowest systolic blood pressure and presence of cardiovascular and neuropsychological diseases ranked in the top 10 in both RF relative feature importance and clinician judgment.
Conclusions:
The ML approach could provide a clinically applicable triage algorithm and identify important clinical indices, such as age, underlying diseases, abnormal vital signs, and laboratory data for evaluating the need for intensive care in children with pneumonia.
Related Concept Videos
01:28Pneumonia IV: Management
Bacterial Pneumonia Treatment
For bacterial pneumonia, antibiotics serve as the cornerstone of therapy. Initial treatment often begins with empirical antibiotics, tailored to the anticipated causative organism and adjusted based on culture results. Key antibiotic choices include:
01:30Pneumonia III: Complications and Assessment
01:30Pneumonia I: Introduction
Risk Factors
Various factors influence the likelihood of developing pneumonia. Age plays a crucial role, with infants, children under two, and individuals over 65 at increased risk due to their...
01:30Pneumonia V: Nursing management and Prevention
The nurse must practice strict medical asepsis and adhere to infection control guidelines to minimize healthcare-associated infections.
Enhance airway patency
Position the patient correctly to facilitate drainage of the affected lung segments. Manual or mechanical percussion and vibration can also be employed....
01:29Pneumonia II: Pathophysiology
01:21Acute Respiratory Failure-II
The underlying physiological abnormalities that contribute to hypoxemic respiratory failure include: