Department of Anesthesiology and Pain Medicine, National Health Insurance Service Ilsan Hospital, Ilsandong-gu, Goyang-si, Gyeonggi-do, Republic of Korea.
Department of Radiology, National Health Insurance Service Ilsan Hospital, Ilsandong-gu, Goyang-si, Gyeonggi-do, Republic of Korea.
Clin Nutr ESPEN. 2021 Oct;45:213-219. doi: 10.1016/j.clnesp.2021.08.022. Epub 2021 Sep 10.
BACKGROUND & AIMS: Refeeding syndrome (RFS) is a disease that occurs when feeding is restarted and metabolism changes from catabolic to anabolic status. RFS can manifest variously, ranging from asymptomatic to fatal, therefore it may easily be overlooked. RFS prediction using explainable machine learning can improve diagnosis and treatment. Our study aimed to propose a machine learning model for RFS prediction, specifically refeeding hypophosphatemia, to evaluate its performance compared with conventional regression models, and to explain the machine learning classification through Shapley additive explanations (SHAP) values.
A retrospective study was conducted including 806 patients, with 2 or more days of nothing-by-mouth prescription, and with phosphate (P) level measurements within 5 days of refeeding were selected. We divided the patients into hypophosphatemia (n = 367) and non-hypophosphatemia groups (n = 439) at a P level of 0.8 mmol/L. Among the features examined within 48 h after admission, we reviewed laboratory test results and electronic medical records. Logistic, Lasso, and ridge regressions were used as conventional models, and performances were compared with our extreme gradient boosting (XGBoost) machine learning model using the area under the receiver operating characteristic curve. Our model was explained using the SHAP value.
The areas under the curve were 0.950 (95% confidence interval: 0.924-0.975) for our XGBoost machine learning model and surpassed the performance of conventional regression models; 0.760 (0.707-0.813) for logistic regression, 0.751 (0.694-0.807) for Lasso regression, and 0.758 (0.701-0.809) for ridge regression. According to the SHAP values in the order of importance, low initial P, recent weight loss, high creatinine, diabetes mellitus with insulin use, low haemoglobin A1c, furosemide use, intensive care unit admission, blood urea nitrogen level of 19-65, parenteral nutrition, magnesium below or above the normal range, low potassium, and older age were features to predict refeeding hypophosphatemia.
The machine learning model for predicting RFS has a substantially higher effectiveness than conventional regression methods. Creating an accurate risk assessment tool based on machine learning for early identification of patients at risk for RFS can enable careful nutrition management planning and monitoring in the intensive care unit, towards reducing the incidence of RFS-related morbidity and mortality.
重新喂养综合征（RFS）是一种在开始喂养和代谢从分解代谢转变为合成代谢状态时发生的疾病。RFS 的表现形式多种多样，从无症状到致命不等，因此很容易被忽视。使用可解释的机器学习进行 RFS 预测可以改善诊断和治疗。我们的研究旨在提出一种用于预测 RFS（特别是重新喂养性低磷血症）的机器学习模型，评估其与传统回归模型相比的性能，并通过 Shapley 加法解释（SHAP）值来解释机器学习分类。
我们进行了一项回顾性研究，纳入了 806 名接受了 2 天以上无口服医嘱且在重新喂养后 5 天内进行了磷（P）水平测量的患者。我们将患者分为低磷血症（n=367）和非低磷血症组（n=439），以 P 水平 0.8mmol/L 为界。在入院后 48 小时内检查的特征中，我们回顾了实验室检查结果和电子病历。使用逻辑回归、Lasso 和岭回归作为传统模型，并使用接收者操作特征曲线下的面积比较我们的极端梯度增强（XGBoost）机器学习模型的性能。我们使用 SHAP 值解释模型。
我们的 XGBoost 机器学习模型的曲线下面积为 0.950（95%置信区间：0.924-0.975），优于传统回归模型的性能；逻辑回归为 0.760（0.707-0.813），Lasso 回归为 0.751（0.694-0.807），岭回归为 0.758（0.701-0.809）。根据重要性顺序的 SHAP 值，初始 P 低、近期体重减轻、肌酐高、使用胰岛素的糖尿病、糖化血红蛋白 A1c 低、使用呋塞米、入住重症监护病房、血尿素氮水平 19-65、肠外营养、镁在正常范围以下或以上、低钾和年龄较大是预测重新喂养性低磷血症的特征。
用于预测 RFS 的机器学习模型比传统回归方法具有更高的有效性。基于机器学习为 RFS 风险患者创建准确的风险评估工具，可以在重症监护病房进行精心的营养管理计划和监测，从而降低与 RFS 相关发病率和死亡率。
