Classification of human rotation test results using parametric modeling and multivariate statistics
Classification of human rotation test results using parametric modeling and multivariate statistics
复制标题
DOI：
10.3109/00016489609137880
复制
发表时间：
1996-07-01
影响因子：
1.4
通讯作者：
Oas, JG
中科院分区：
文献类型：
--
作者：
Dimitri, PS;Wall, C;Oas, JG
前庭测试的有用性直接关系到测试解释的准确性。两个因素，即对大量测试数据集的主观分析和未能进行适当的年龄修正，往往会降低测试的准确性。这些问题的纠正可以通过将基于生理的前庭功能模型和多变量分类技术应用于测试数据来完成，从而创建更客观的测试解释程序。在这里，我们报告了使用这一策略分析正弦谐波加速度(SHA)测试解释的结果。对于每个患者，模型将SHA测试变量的大集合减少到三个关键参数：渐近增益、前庭-眼睛反射时间常数和偏差。此外，这项新技术根据患者的年龄客观地调整了这些参数。最后，每个患者的一组参数在统计学上被归类为正常或单侧外周缺陷。基于57名正常人和30名单侧完全性外周神经缺失患者的学习集，该新技术导致正常和完全性单侧缺失类别之间的错分率为3.4%，而目前方法在正常和异常之间的错别率为13.8%。我们还使用与正常和完全单侧学习集相同的分类函数对由可能存在部分单侧缺陷的患者组成的试验组进行了分析和分类。尽管分类器没有针对部分群体进行优化，但结果似乎比人工翻译更好。这些结果验证了生理参数模型和多元统计分类在SHA测试解释中的准确性和实用性。
The usefulness of vestibular testing is directly related to the accuracy of the test interpretations. Two factors, subjective analysis of large test data sets and failure to make appropriate age corrections, tend to reduce test accuracy. Correction of these problems can be accomplished by application of physiologically based models of vestibular function and multivariate classification techniques to the test data, thereby creating a more objective test interpretation procedure. Herein we report Our results on the use of this strategy for analysis of sinusoidal harmonic acceleration (SHA) test interpretation. For each patient, models reduce the large set of SHA test variables to three key parameters: asymptotic gain, vestibule-ocular reflex time constant, and bias. In addition, the new technique objectively adjusts these parameters for the patient's age. Finally, each patient's set of parameters are statistically classified as either normal or as unilateral peripheral deficit. Based on learning sets of 57 normals and 30 patients with a full unilateral peripheral deficit, this new technique resulted in a misclassification rate between the categories of normal and full unilateral loss of 3.4%, comparing favorably to the present method's misclassification rate between normal and abnormal of 13.8%. We also analyzed and classified a test group consisting of patients with possible partial unilateral deficits using the same classification function as the normal and full unilateral learning sets. Even though the classifier was not optimized for the partial group, results seemed favorable relative to the human interpreter. These results validate the accuracy and utility of physiological parametric models and multivariate statistical classification in SHA test interpretation.