Data_Sheet_2_Decoding Wilson disease: a machine learning approach to predict neurological symptoms.docx

ObjectivesWilson disease (WD) is a rare autosomal recessive disorder caused by a mutation in the ATP7B gene. Neurological symptoms are one of the most common symptoms of WD. This study aims to construct a model that can predict the occurrence of neurological symptoms by combining clinical multidimensional indicators with machine learning methods.
MethodsThe study population consisted of WD patients who received treatment at the First Affiliated Hospital of Anhui University of Traditional Chinese Medicine from July 2021 to September 2023 and had a Leipzig score ≥ 4 points. Indicators such as general clinical information, imaging, blood and urine tests, and clinical scale measurements were collected from patients, and machine learning methods were employed to construct a prediction model for neurological symptoms. Additionally, the SHAP method was utilized to analyze clinical information to determine which indicators are associated with neurological symptoms.
ResultsIn this study, 185 patients with WD (of whom 163 had neurological symptoms) were analyzed. It was found that using the eXtreme Gradient Boosting (XGB) to predict achieved good performance, with an MCC value of 0.556, ACC value of 0.929, AUROC value of 0.835, and AUPRC value of 0.975. Brainstem damage, blood creatinine (Cr), age, indirect bilirubin (IBIL), and ceruloplasmin (CP) were the top five important predictors. Meanwhile, the presence of brainstem damage and the higher the values of Cr, Age, and IBIL, the more likely neurological symptoms were to occur, while the lower the CP value, the more likely neurological symptoms were to occur.
ConclusionsTo sum up, the prediction model constructed using machine learning methods to predict WD cirrhosis has high accuracy. The most important indicators in the prediction model were brainstem damage, Cr, age, IBIL, and CP. It provides assistance for clinical decision-making.

研究目的
威尔逊病（Wilson disease, WD）是一种由ATP7B基因突变导致的罕见常染色体隐性遗传病（autosomal recessive disorder）。神经系统症状是威尔逊病最为常见的临床表现之一。本研究旨在结合临床多维度指标与机器学习方法，构建可预测神经系统症状发生风险的模型。

研究方法
本研究的研究对象为2021年7月至2023年9月于安徽中医药大学第一附属医院接受诊疗的威尔逊病患者，且莱比锡评分（Leipzig score）≥4分。研究人员收集了患者的一般临床信息、影像学检查结果、血液与尿液检验指标及临床量表测评数据，采用机器学习方法构建神经系统症状预测模型；同时借助SHAP（SHapley Additive exPlanations）方法分析临床信息，以明确与神经系统症状相关的关键指标。

研究结果
本研究共纳入185例威尔逊病患者（其中163例出现神经系统症状）。研究发现，采用极端梯度提升（eXtreme Gradient Boosting, XGB）构建的预测模型表现优异，其马修斯相关系数（Matthews Correlation Coefficient, MCC）为0.556、准确率（Accuracy, ACC）为0.929、受试者工作特征曲线下面积（Area Under Receiver Operating Characteristic Curve, AUROC）为0.835、精确召回曲线下面积（Area Under Precision-Recall Curve, AUPRC）为0.975。脑干损伤、血肌酐（Cr）、年龄、间接胆红素（IBIL）及铜蓝蛋白（CP）为排名前五的重要预测因子。进一步分析显示，存在脑干损伤、血肌酐水平升高、年龄增长及间接胆红素水平升高均会增加神经系统症状的发生风险，而铜蓝蛋白水平降低则会提升神经系统症状的发生概率。

研究结论
综上，本研究通过机器学习方法构建的威尔逊病肝硬化预测模型具有较高的准确性，其中脑干损伤、血肌酐、年龄、间接胆红素及铜蓝蛋白为模型中最为关键的预测指标，可为临床决策提供辅助支持。