Statsenko Yauhen, Habuza Tetiana, Gorkom Klaus Neidl-Van, Zaki Nazar, Almansoori Taleb M
Radiology Department of College of Medicine and Health Sciences, United Arab Emirates University, Al Ain, United Arab Emirates.
Department of Computer Science and Software Engineering of College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates.
Front Aging Neurosci. 2020 Dec 9;12:574401. doi: 10.3389/fnagi.2020.574401. eCollection 2020.
The current study examines the relationship between speed and accuracy of performance in a reaction time setting and explores the informative value of the inverse efficiency score (IES) regarding the possibility to reflect age-related cognitive changes. To study the characteristics of speed and accuracy while performing psychophysiological tests throughout the lifespan; to examine the speed-accuracy ratio in age groups and to apply IES to discriminative visual-motor reaction task; and to figure out the predictive potential of psychophysiological tests to identify IES values. We utilize nonparametric statistical tests, regression analysis, and supervised machine learning methods. The examinees under 20 and over 60 years of age share one tendency regarding the speed-accuracy ratio without speed-accuracy trade-off. Both at the time of active developmental changes in adolescence and during ongoing atrophic changes in elderly there is a tendency toward a rise of the number of mistakes while slowing the reaction. In the age range from 20 to 60 the relationship between the speed and accuracy is opposite and speed-accuracy trade-off is present. In our battery, complex visual-motor reaction is the only test with the significant negative association between reaction time and error rate in the subcohort of young and midlife adults taken together. On average, women perform more slowly and accurately than men in the speed-accuracy task, however most of the gender-related differences are insignificant. Using results of other psychophysiological tests, we predicted IES values for the visual-motor reaction with high accuracy ( = 0.77 ± 0.08; mean absolute error / IES range = 3.37%). The regression model shows the best performance in the cognitively preserved population groups of young and middle-aged adults (20-60 years). Because of the individual rate of neurodevelopment in youth and cognitive decline in the elderly, the regression model for these subcohorts has a low predictive performance. IES accounts for different cognitive subdomains and may reflect their disproportional changes throughout the lifespan. This encourages us to proceed to explore the combination of executive functioning and psychophysiological test results utilizing machine learning models. The latter can be designed as a reliable computer-aided detector of cognitive changes at early stages.
本研究考察了反应时间设定中表现的速度与准确性之间的关系，并探讨了逆效率得分（IES）在反映与年龄相关的认知变化可能性方面的信息价值。旨在研究在整个生命周期中进行心理生理测试时速度和准确性的特征；检查各年龄组的速度-准确性比率，并将IES应用于有区别的视觉运动反应任务；并确定心理生理测试识别IES值的预测潜力。我们采用非参数统计测试、回归分析和监督机器学习方法。20岁以下和60岁以上的受试者在速度-准确性比率方面有一个共同趋势，即不存在速度-准确性权衡。在青春期积极发育变化时期和老年人持续萎缩变化期间，都存在反应变慢时错误数量增加的趋势。在20至60岁的年龄范围内，速度与准确性之间的关系相反，存在速度-准确性权衡。在我们的测试组中，复杂视觉运动反应是年轻和中年成年人亚组中反应时间与错误率之间具有显著负相关的唯一测试。平均而言，在速度-准确性任务中，女性比男性表现得更慢且更准确，然而大多数与性别相关的差异并不显著。利用其他心理生理测试的结果，我们高精度地预测了视觉运动反应的IES值（= 0.77 ± 0.08；平均绝对误差/IES范围 = 3.37%）。回归模型在年轻和中年成年人（20 - 60岁）的认知保存人群组中表现最佳。由于年轻人神经发育的个体速率和老年人的认知衰退，这些亚组的回归模型预测性能较低。IES涵盖不同的认知子领域，并可能反映其在整个生命周期中的不均衡变化。这鼓励我们继续利用机器学习模型探索执行功能与心理生理测试结果的组合。后者可设计为早期认知变化的可靠计算机辅助检测工具。
