Bárczi Gusztáv Faculty of Special Needs Education, Institute for the Psychology of Special Needs, Eötvös Loránd University, Ecseri út 3, 1097 Budapest, Hungary.
Department of Artificial Intelligence, Faculty of Informatics, Eötvös Loránd University, Pázmány P. Sétány 1/A, 1117 Budapest, Hungary.
Sensors (Basel). 2022 Aug 6;22(15):5880. doi: 10.3390/s22155880.
The main objective of the present study is to highlight the role of technological (soft sensor) methodologies in the assessment of the neurocognitive dysfunctions specific to neurodevelopmental disorders (for example, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), and specific learning disorder). In many cases neurocognitive dysfunctions can be detected in neurodevelopmental disorders, some of them having a well-defined syndrome-specific clinical pattern. A number of evidence-based neuropsychological batteries are available for identifying these domain-specific functions. Atypical patterns of cognitive functions such as executive functions are present in almost all developmental disorders. In this paper, we present a novel adaptation of the Tower of London Test, a widely used neuropsychological test for assessing executive functions (in particular planning and problem-solving). Our version, the Tower of London Adaptive Test, is based on computer adaptive test theory (CAT). Adaptive testing using novel algorithms and parameterized task banks allows the immediate evaluation of the participant's response which in turn determines the next task's difficulty level. In this manner, the subsequent item is adjusted to the participant's estimated capability. The adaptive procedure enhances the original test's diagnostic power and sensitivity. By measuring the targeted cognitive capacity and its limitations more precisely, it leads to more accurate diagnoses. In some developmental disorders (e.g., ADHD, ASD) it could be very useful in improving the diagnosis, planning the right interventions, and choosing the most suitable assistive digital technological service.
本研究的主要目的是强调技术（软传感器）方法在评估神经发育障碍特有的神经认知功能障碍方面的作用（例如自闭症谱系障碍 (ASD)、注意力缺陷多动障碍 (ADHD) 和特定学习障碍）。在许多情况下，可以在神经发育障碍中检测到神经认知功能障碍，其中一些具有明确的综合征特异性临床模式。有许多基于证据的神经心理学测试包可用于识别这些特定领域的功能。执行功能等认知功能的异常模式几乎存在于所有发育障碍中。在本文中，我们提出了一种塔伦测试（广泛用于评估执行功能（特别是计划和解决问题）的神经心理学测试）的新颖改编版。我们的版本，塔伦自适应测试，基于计算机自适应测试理论 (CAT)。使用新算法和参数化任务库进行自适应测试允许立即评估参与者的反应，这反过来又决定了下一个任务的难度级别。通过这种方式，后续项目会根据参与者的估计能力进行调整。自适应程序增强了原始测试的诊断能力和灵敏度。通过更精确地测量目标认知能力及其局限性，它可以实现更准确的诊断。在一些发育障碍（例如 ADHD、ASD）中，它可以非常有助于改善诊断、规划正确的干预措施以及选择最合适的辅助数字技术服务。
