Machine-learning-enabled prognostic models for sepsis

• Published in: Intelligence-based medicine 2024, Vol.10, p.100167, Article 100167
• Main Authors: Li, Chunyan, Wang, Lu, Li, Kexun, Deng, Hongfei, Wang, Yu, Chang, Li, Zhou, Ping, Zeng, Jun, Sun, Mingwei, Jiang, Hua, Wang, Qi
• Format: Article
• Language: English
• Subjects: Class-imbalance data; Classifiers; Dimension reduction; Sampling strategies; Sepsis; Small dataset
• ISSN: 2666-5212; 2666-5212
• DOI: 10.1016/j.ibmed.2024.100167

Sepsis is a leading cause of mortality in intensive care units (ICUs). The development of a robust prognostic model utilizing patients’ clinical data could significantly enhance clinicians’ ability to make informed treatment decisions, potentially improving outcomes for septic patients. This study aims to create a novel machine-learning framework for constructing prognostic tools capable of predicting patient survival or mortality outcome. A novel dataset is created using concatenated triples of static data, temporal data, and clinical outcomes to expand data size. This structured input trains five machine learning classifiers (KNN, Logistic Regression, SVM, RF, and XGBoost) with advanced feature engineering. Models are evaluated on an independent cohort using AUROC and a new metric, γ, which incorporates the F1 score, to assess discriminative power and generalizability. We developed five prognostic models using the concatenated triple dataset with 10 dynamic features from patient medical records. Our analysis shows that the Extreme Gradient Boosting (XGBoost) model (AUROC = 0.777, F1 score = 0.694) and the Random Forest (RF) model (AUROC = 0.769, F1 score = 0.647), when paired with an ensemble under-sampling strategy, outperform other models. The RF model improves AUROC by 6.66% and reduces overfitting by 54.96%, while the XGBoost model shows a 0.52% increase in AUROC and a 77.72% reduction in overfitting. These results highlight our framework’s ability to enhance predictive accuracy and generalizability, particularly in sepsis prognosis. This study presents a novel modeling framework for predicting treatment outcomes in septic patients, designed for small, imbalanced, and high-dimensional datasets. By using temporal feature encoding, advanced sampling, and dimension reduction techniques, our approach enhances standard classifier performance. The resulting models show improved accuracy with limited data, offering valuable prognostic tools for sepsis management. This framework demonstrates the potential of machine learning in small medical datasets. •Prognostic models for sepsis are developed through a new machine-learning approach.•The temporal feature encoding and feature engineering are innovated.•The approach applies to small-sized, class-imbalanced, & high-dimensional datasets.•Models produce clinically acceptable outcomes despite being built on small datasets.