TY -的A2 Bangyal Waqas海德尔AU - Suarez-Araujo卡门·巴斯AU -加西亚贝兹,会长Patricio AU - Cabrera-Leon Ylermi AU - Prochazka,爱丽斯盟-罗德里格斯埃斯皮诺萨,诺伯特AU -费尔南德斯Viadero卡洛斯AU -神经影像倡议,为阿尔茨海默病PY - 2021 DA - 2021/06/28 TI -实时临床决策支持系统,对轻度认知障碍检测、基于混合神经结构SP - 5545297六世- 2021 AB -轻度认知障碍(MCI)的临床过程主要是基于临床记录和短的认知测试。然而,低怀疑和困难理解测试的否决使诊断准确性很低,尤其是在初级护理。人工神经网络(ann)是适合的设计计算辅助诊断系统,因为他们的特征生成变量及其学习能力之间的关系。追求,工作的主要目的是探索的能力混合ANN-based系统为了提供一个工具来协助临床决策,促进了一个可靠的MCI估计。模型设计与变量通常在初级保健,包括Minimental状态检查(MMSE)、功能评估问卷(FAQ)、老年抑郁量表(GDS),年的年龄和教育。这将是有用的在任何临床设置。其他重要的目标,我们的研究是比较ANN-based的诊断渲染系统和临床医生。128例MCI和203名对照样本选择的阿尔茨海默病的神经影像学(ADNI)。ANN-based系统发现最优变量组合,AUC,敏感性,特异性和临床效用指数(崔)计算。安的结果进行了比较与医学专家包括两个家庭医生,神经病学家和老年医学专家。 The optimal ANN model reached an AUC of 95.2%, with a sensitivity of 90.0% and a specificity of 84.78% and was based on MMSE, FAQ, and age inputs. As a whole, physician performance achieved a sensitivity of 46.66% and a specificity of 91.3%. CUIs were also better for the ANN model. The proposed ANN system reaches excellent diagnostic accuracy although it is based only on common clinical tests. These results suggest that the system is especially suitable for primary care implementation, aiding physicians work with cognitive impairment suspicions. SN - 1748-670X UR - https://doi.org/10.1155/2021/5545297 DO - 10.1155/2021/5545297 JF - Computational and Mathematical Methods in Medicine PB - Hindawi KW - ER -