Qiang Li ¹ Dongchen Li ^1* He Jiao ² Zhenhua Wu ³ Weizhi Nie ^4*

• ¹ School of Microelectronics, Tianjin University, Tianjin, China
• ² School of Pharmaceutical Science and Technology, Tianjin University, Tianjin, China
• ³ Department of Cardiovascular Surgery Intensive Care Unit,Tianjin Chest Hospital, Tianjin, China
• ⁴ School of Electrical and Information Engineering, Tianjin University, Tianjin, China

The early prediction of sepsis based on machine learning or deep learning has achieved good results. Most of the methods use structured data stored in electronic medical records, but the pathological characteristics of sepsis involve complex interactions between multiple physiological systems and signaling pathways, resulting in mixed structured data. Some researchers will introduce unstructured data when also introduce confounders. These confounders mask the direct causality of sepsis, leading the model to learn misleading correlations. Finally, it affects the generalization ability, robustness, and interpretability of the model. To address this challenge, we propose an early sepsis prediction approach based on causal inference which can remove confounding effects and capture causal relationships. First, we analyze the relationship between each type of observation, confounder, and label to create a causal structure diagram. To eliminate the effects of different confounders separately, the methods of back-door adjustment and instrumental variable are used. Specifically, we learn the confounder and an instrumental variable based on mutual information from various observed data and eliminate the influence of the confounder by optimizing mutual information. We use back-door adjustment to eliminate the influence of confounders in clinical notes and static indicators on the true causal effect. Our method is named CISepsis, we validate on the MIMIC-IV dataset, that our method shows better performance, we also demonstrate the effectiveness of our method through ablation experiments.