Background: Medical decision-making impacts both individual and public health. Clinical scores are commonly used among a wide variety of decision-making models for determining the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. Its current framework, however, still leaves room for improvement when addressing unbalanced data of rare events. Methods: Using machine intelligence approaches, we developed AutoScore-Imbalance, which comprises three components: training dataset optimization, sample weight optimization, and adjusted AutoScore. All scoring models were evaluated on the basis of their area under the curve (AUC) in the receiver operating characteristic analysis and balanced accuracy (i.e., mean value of sensitivity and specificity). By utilizing a publicly accessible dataset from Beth Israel Deaconess Medical Center, we assessed the proposed model and baseline approaches in the prediction of inpatient mortality. Results: AutoScore-Imbalance outperformed baselines in terms of AUC and balanced accuracy. The nine-variable AutoScore-Imbalance sub-model achieved the highest AUC of 0.786 (0.732-0.839) while the eleven-variable original AutoScore obtained an AUC of 0.723 (0.663-0.783), and the logistic regression with 21 variables obtained an AUC of 0.743 (0.685-0.800). The AutoScore-Imbalance sub-model (using down-sampling algorithm) yielded an AUC of 0. 0.771 (0.718-0.823) with only five variables, demonstrating a good balance between performance and variable sparsity. Conclusions: The AutoScore-Imbalance tool has the potential to be applied to highly unbalanced datasets to gain further insight into rare medical events and to facilitate real-world clinical decision-making.
翻译:医疗决策背景:医疗决策影响个人和公共健康。临床评分通常在确定床头疾病恶化程度的各种决策模型中广泛使用。AutScore是根据机器学习和一般线性模型提出的一个有用的临床评分生成器。然而,目前的框架在处理罕见事件不平衡数据时仍有改进的余地。方法:使用机器情报方法,我们开发了AutScore-Imal平衡,由三个部分组成:培训数据集优化、样本重量优化和调整的AutScore。所有评分模型都是根据接收器操作特征分析和平衡准确性(即敏感度和特殊度的平均值)的曲线(AUC)下方区域(AUC)进行评估。通过使用来自Beth Isa Rea Deaconess医疗中心的公开数据集,我们评估了拟议的模型和基线方法,用于预测住院死亡率。结果:AutScoco-Imal平衡在AUC和平衡性精确精确性(9可变的ACreal-Imal-alal)子模型下,在接收的AUC(0.6-Mex-al-al-al-al-al-al-rational-al-al-al-ral sal sal sessional sessional sessional disal)中,在Axx mal sal sal deal sal sal sal sal sal sal sal sal sal a hisal a hisal a hisal a hismal deal deal deal deal sal deal deal deal deceal deal deal deal decealmentalmentalmentalmental deal deal 11-al 和21-al sal sal deal deal sal sal sal sal sal deal salalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalessalalessalal 6 malalalal 6 malalalalalal 和21-al 和21-al 6 mal 6 mal 和21-alalalalalalalalalalalalalalalalalal 和21-alalalalalal