🤖 AI Summary
Sepsis, a global critical illness, lacks comprehensive understanding of modifiable risk factors amenable to public health policy intervention.
Method: We propose a knowledge-constrained multi-algorithm Bayesian network structure learning framework that integrates clinical prior knowledge with real-world hospital data. The framework synergistically employs score-based, constraint-based, and hybrid structure learning methods, augmented by model averaging to enhance robustness.
Contribution/Results: For the first time, we systematically identify strong causal associations between sepsis and non-traditional high-risk conditions—including COPD, alcohol dependence, and diabetes—and elucidate their policy-actionable pathways. Under data-limited conditions, the model achieves ~70% accuracy, sensitivity, and specificity in causal structure prediction, with an AUC of 80%. These results demonstrate the framework’s reliability and practical utility for causal discovery and sepsis risk prediction.
📝 Abstract
Sepsis is a life-threatening and serious global health issue. This study combines knowledge with available hospital data to investigate the potential causes of Sepsis that can be affected by policy decisions. We investigate the underlying causal structure of this problem by combining clinical expertise with score-based, constraint-based, and hybrid structure learning algorithms. A novel approach to model averaging and knowledge-based constraints was implemented to arrive at a consensus structure for causal inference. The structure learning process highlighted the importance of exploring data-driven approaches alongside clinical expertise. This includes discovering unexpected, although reasonable, relationships from a clinical perspective. Hypothetical interventions on Chronic Obstructive Pulmonary Disease, Alcohol dependence, and Diabetes suggest that the presence of any of these risk factors in patients increases the likelihood of Sepsis. This finding, alongside measuring the effect of these risk factors on Sepsis, has potential policy implications. Recognising the importance of prediction in improving health outcomes related to Sepsis, the model is also assessed in its ability to predict Sepsis by evaluating accuracy, sensitivity, and specificity. These three indicators all had results around 70%, and the AUC was 80%, which means the causal structure of the model is reasonably accurate given that the models were trained on data available for commissioning purposes only.