Related Experiment Video
Updated: Jun 13, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Pediatric septic shock estimation using deep learning and electronic medical records
Ji Weon Lee1, Bongjin Lee2,3, June Dong Park2
1Integrated and Respite Care Center for Children, Seoul National University, Seoul, Korea.
Insights
A new deep learning model simplifies early diagnosis of pediatric septic shock using Systemic Inflammatory Response Syndrome (SIRS) data. This AI approach improves diagnostic efficiency and accuracy for timely treatment in children.
Area of Science:
- Pediatric critical care medicine
- Artificial intelligence in healthcare
- Machine learning for diagnostics
Background:
- Diagnosing pediatric septic shock is challenging due to complex traditional criteria like Systemic Inflammatory Response Syndrome (SIRS), leading to diagnostic delays and increased risks.
- Existing diagnostic methods for pediatric septic shock often prove impractical, necessitating more efficient and accurate approaches.
Purpose of the Study:
- To develop and validate a deep learning model for the early diagnosis of pediatric septic shock.
- To leverage Systemic Inflammatory Response Syndrome (SIRS) data for improved diagnostic accuracy in pediatric septic shock cases.
Main Methods:
- A deep learning model was trained and evaluated using a large dataset of pediatric patients (<18 years) from a tertiary hospital (January 2010 - July 2023).
- Data included vital signs, lab tests, and clinical information; septic shock cases were identified using SIRS criteria and inotrope use.
- Model performance was assessed using AUROC and AUPRC, with variable importance analyzed via Shapley additive explanation.
Main Results:
- The analysis included over 9.6 million measurements, identifying 34,696 septic shock cases (0.4%).
- The deep learning model achieved high performance with an AUROC of 0.927 and AUPRC of 0.879.
- Key predictive variables included age, oxygen supply, sex, and partial pressure of carbon dioxide; body temperature had minimal impact.
Conclusions:
- The developed deep learning model offers a simplified and accurate method for early pediatric septic shock diagnosis, reducing workload.
- High diagnostic accuracy facilitates timely treatment initiation for pediatric septic shock.
- External validation via prospective studies is recommended to confirm the model's generalizability.
Background:
Diagnosing pediatric septic shock is difficult due to the complex and often impractical traditional criteria, such as systemic inflammatory response syndrome (SIRS), which result in delays and higher risks. This study aims to develop a deep learning-based model using SIRS data for early diagnosis in pediatric septic shock cases.
Methods:
The study analyzed data from pediatric patients (<18 years old) admitted to a tertiary hospital from January 2010 to July 2023. Vital signs, lab tests, and clinical information were collected. Septic shock cases were identified using SIRS criteria and inotrope use. A deep learning model was trained and evaluated using the area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). Variable contributions were analyzed using the Shapley additive explanation value.
Results:
The analysis, involving 9,616,115 measurements, identified 34,696 septic shock cases (0.4%). Oxygen supply was crucial for 41.5% of the control group and 20.8% of the septic shock group. The final model showed strong performance, with an AUROC of 0.927 and AUPRC of 0.879. Key influencers were age, oxygen supply, sex, and partial pressure of carbon dioxide, while body temperature had minimal impact on estimation.
Conclusions:
The proposed deep learning model simplifies early septic shock diagnosis in pediatric patients, reducing the diagnostic workload. Its high accuracy allows timely treatment, but external validation through prospective studies is needed.
