Automated extraction of decision rules for predicting lumbar drain outcome by analyzing overnight intracranial pressure.
Automated extraction of decision rules for predicting lumbar drain outcome by analyzing overnight intracranial pressure.
复制标题
DOI：
10.1007/978-3-7091-0956-4_40
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Xiao Hu;R. Hamilton;Kevin M. Baldwin;P. Vespa;M. Bergsneider
中科院分区：
文献类型：
--
作者：
Xiao Hu;R. Hamilton;Kevin M. Baldwin;P. Vespa;M. Bergsneider
背景：延长腰椎引流（ELD）已成为一种流行的分流前检查，以帮助诊断正常压力脑积水（NPH）。不幸的是，这个过程需要家庭和医院投入大量的时间。在这项研究中，我们调查如何准确的预测ELD的结果可以通过使用简单的决策规则自动派生的脉冲形态指标过夜ICP记录。我们的最终目标是测试的假设，夜间ICP监测，授权随后的信号分析，可能是一种替代ELD.Methods：本研究涉及54例ELD和夜间ICP记录; ICP形态分析使用MOCAIP算法进行。此外，使用五个聚合函数（特征）表征来自过夜记录的个体度量的分布。然后，开发了一种算法，自动发现最准确的“如果-那么”的决策规则的五个特征函数。研究结果：基于5个特征函数的决策规则的分类准确率分别为70.4%、72.2%、74.1%、72.2%和79.6%。然而，“OR”组合的两个特征的准确性提高到88.9%。结论：我们提出了一种算法，发现决策规则，可以潜在地预测ELD的结果。
Background: Extended lumbar drain (ELD) has become a popular pre-shunt workup test to help diagnose normal pressure hydrocephalus (NPH). Unfortunately, this procedure requires a substantial time investment for both the family and hospital. In this study, we investigate how accurate the prediction of ELD outcome can be achieved by using simple decision rules automatically derived from pulse morphological metrics of overnight ICP recordings. Our ultimate goal is to test the hypothesis that overnight ICP monitoring, empowered by subsequent signal analysis, could be an alternative to ELD.Methods: The present study involved 54 patients with both ELD and overnight ICP recordings; the ICP morphological analysis was performed using the MOCAIP algorithm. Furthermore, the distribution of individual metric from the overnight recording was characterized using five aggregation functions (features). Then an algorithm was developed to automatically discover the most accurate “if-then” decision rule for each of the five feature functions. In addition, the best combination of two decision rules, either using “AND” or “OR” operator, was obtained.Findings: Rules based on five individual feature functions achieved an accuracy of 70.4%, 72.2%, 74.1%, 72.2%, and 79.6% respectively. However, “OR” combination of two features improved accuracy to 88.9%.Conclusion: We showed an algorithm to discover decision rules that can potentially predict ELD outcome.