Department of Biomedical Engineering, School of Life Science, Beijing Institute of Technology, Beijing, 100081, China.
Institute of Medical Information, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100020, China.
Sci Rep. 2022 Dec 31;12(1):22621. doi: 10.1038/s41598-022-27134-6.
Sepsis-associated encephalopathy (SAE) is a major complication of sepsis and is associated with high mortality and poor long-term prognosis. The purpose of this study is to develop interpretable machine learning models to predict the occurrence of SAE after ICU admission and implement the individual prediction and analysis. Patients with sepsis admitted to ICU were included. SAE was diagnosed as glasgow coma score (GCS) less than 15. Statistical analysis at baseline was performed between SAE and non-SAE. Six machine learning classifiers were employed to predict the occurrence of SAE, and the adjustment of model super parameters was performed by using Bayesian optimization method. Finally, the optimal algorithm was selected according to the prediction efficiency. In addition, professional physicians were invited to evaluate our model prediction results for further quantitative assessment of the model interpretability. The preliminary analysis of variance showed significant differences in the incidence of SAE among patients with pathogen infection. There were significant differences in physical indicators like respiratory rate, temperature, SpO and mean arterial pressure (P < 0.001). In addition, the laboratory results were also significantly different. The optimal classification model (XGBoost) indicated that the best risk factors (cut-off points) were creatinine (1.1 mg/dl), mean respiratory rate (18), pH (7.38), age (72), chlorine (101 mmol/L), sodium (138.5 k/ul), SAPSII score (23), platelet count (160), and phosphorus (2.4 and 5.0 mg/dL). The ranked features derived from the best model (AUC is 0.8837) were mechanical ventilation, duration of mechanical ventilation, phosphorus, SOFA score, and vasopressin usage. The SAE risk prediction model based on XGBoost created here can make very accurate predictions using simple indicators and support the visual explanation. The interpretable model was effectively evaluated by professional physicians and can help them predict the occurrence of SAE more intuitively.
脓毒症相关性脑病（SAE）是脓毒症的主要并发症，与高死亡率和不良预后相关。本研究旨在开发可解释的机器学习模型，以预测 ICU 入院后 SAE 的发生，并进行个体预测和分析。纳入 ICU 收治的脓毒症患者。SAE 诊断为格拉斯哥昏迷评分（GCS）<15。在基线时，对 SAE 和非 SAE 患者进行了统计学分析。采用 6 种机器学习分类器预测 SAE 的发生，并采用贝叶斯优化方法对模型超参数进行调整。最后，根据预测效率选择最优算法。此外，还邀请了专业医生对我们的模型预测结果进行评估，以进一步对模型的可解释性进行定量评估。初步方差分析显示，病原体感染患者的 SAE 发生率存在显著差异。呼吸频率、体温、SpO2 和平均动脉压等生理指标存在显著差异（P<0.001）。此外，实验室结果也存在显著差异。最优分类模型（XGBoost）表明，最佳风险因素（临界值）为肌酐（1.1mg/dl）、平均呼吸频率（18）、pH（7.38）、年龄（72）、氯（101mmol/L）、钠（138.5k/ul）、SAPSII 评分（23）、血小板计数（160）和磷（2.4 和 5.0mg/dL）。最佳模型得出的排名特征（AUC 为 0.8837）包括机械通气、机械通气持续时间、磷、SOFA 评分和血管加压素使用。本研究构建的基于 XGBoost 的 SAE 风险预测模型可以使用简单的指标进行非常准确的预测，并支持可视化解释。专业医生对可解释模型进行了有效评估，可以帮助他们更直观地预测 SAE 的发生。
