Sepsis poses a major global health threat, accounting for millions of deaths annually and significant economic costs. Accurate predictions of mortality risk in sepsis patients facilitate the efficient allocation of medical resources, thereby enhancing patient survival and quality of life. Through precise risk assessments, healthcare facilities can effectively distribute intensive care beds, medical equipment, and staff, ensuring high-risk patients receive timely and appropriate care. Early identification and intervention significantly decrease mortality rates and improve patient outcomes. Current methods typically utilize only one type of data--either constant, temporal, or ICD codes. This study introduces the Time-Constant KAN Integrated Network(TCKIN), an innovative model that enhances the accuracy of sepsis mortality risk predictions by integrating both temporal and constant data from electronic health records and ICD codes. Validated against the MIMIC-III and MIMIC-IV datasets, TCKIN surpasses existing machine learning and deep learning methods in accuracy, sensitivity, and specificity. Notably, TCKIN achieved AUCs of 87.76% and 88.07%, demonstrating superior capability in identifying high-risk patients. Additionally, TCKIN effectively combats the prevalent issue of data imbalance in clinical settings, improving the detection of patients at elevated risk of mortality and facilitating timely interventions. These results confirm the model's effectiveness and its potential to transform patient management and treatment optimization in clinical practice. With this advanced risk assessment tool, healthcare providers can devise more tailored treatment plans, optimize resource utilization, and ultimately enhance survival rates and quality of life for sepsis patients.

通过整合临床病历和ICD编码的时间和常数数据，Time-Constant KAN Integrated Network（TCKIN）模型可以提高对败血症死亡风险的准确预测，并在准确性、敏感性和特异性方面超越现有的机器学习和深度学习方法，为高风险患者的识别提供卓越的能力。

TCKIN: 一个新型的整合网络模型用于预测脓毒症患者的死亡风险