Predicting the Outcome of Patients With Subarachnoid Hemorrhage Using Machine Learning Techniques
Predicting the Outcome of Patients With Subarachnoid Hemorrhage Using Machine Learning Techniques
复制标题
DOI：
10.1109/titb.2009.2020434
复制
发表时间：
2009-09-01
影响因子：
--
通讯作者：
Lagares, Alfonso
中科院分区：
文献类型：
--
作者：
de Toledo, Paula;Rios, Pablo M.;Lagares, Alfonso
背景：蛛网膜下腔出血（SAH）的预后预测有助于指导治疗和比较全球管理策略。用于结果预测的逻辑回归模型在临床实践中应用可能很麻烦。目的：使用机器学习技术建立一个结果预测模型，使从数据中发现的知识明确并可传达给领域专家。材料和方法：使用不同的分类算法生成决策树和决策规则，对非选择性SAH病例的衍生队列（n = 441）进行分析。使用的算法是C4.5，快速决策树学习器，部分决策树，重复增量修剪，以产生错误减少，最近的邻居与泛化，和涟漪下降规则学习器。结局分为良好[格拉斯哥结局量表（GOS）= I-II]和较差（GOS = III-V）。使用独立队列（n = 193）进行验证。一个探索性的问卷调查，潜在的用户（专科医生），收集他们的意见，分类器及其在临床常规的可用性。结果：采用C4.5算法得到最佳分类器。它只使用两个属性[世界神经外科医生联合会（WFNS）和Fisher's量表]，并导致一个简单的决策树。分类器的准确性[ROC曲线下面积（AUC）= 0.84;置信区间（CI）= 0.80-0.88]与通过从相同数据获得的逻辑回归模型（AUC = 0.86; CI = 0.83-0.89）获得的准确性相似，并且被认为更适合临床使用。
Background: Outcome prediction for subarachnoid hemorrhage (SAH) helps guide care and compare global management strategies. Logistic regression models for outcome prediction may be cumbersome to apply in clinical practice. Objective: To use machine learning techniques to build a model of outcome prediction that makes the knowledge discovered from the data explicit and communicable to domain experts. Material and methods: A derivation cohort (n = 441) of nonselected SAH cases was analyzed using different classification algorithms to generate decision trees and decision rules. Algorithms used were C4.5, fast decision tree learner, partial decision trees, repeated incremental pruning to produce error reduction, nearest neighbor with generalization, and ripple down rule learner. Outcome was dichotomized in favorable [Glasgow outcome scale (GOS) = I-II] and poor (GOS = III-V). An independent cohort (n = 193) was used for validation. An exploratory questionnaire was given to potential users (specialist doctors) to gather their opinion on the classifier and its usability in clinical routine. Results: The best classifier was obtained with the C4.5 algorithm. It uses only two attributes [World Federation of Neurological Surgeons (WFNS) and Fisher's scale] and leads to a simple decision tree. The accuracy of the classifier [area under the ROC curve (AUC) = 0.84; confidence interval (CI) = 0.80-0.88] is similar to that obtained by a logistic regression model (AUC = 0.86; CI = 0.83-0.89) derived from the same data and is considered better fit for clinical use.