‘Fit2Drive’ Transforms Assessing Older Drivers with Cognitive Decline

Older Adult, Driving, Car, Vehicle

结果表明，FAU研究人员开发的Fit2Drive算法具有很强的91.5% predictive accuracy.

By gisele galoustian | 6/24/2024

随着世界人口的老龄化，道路上老年司机的比例也在增加. 安全驾驶需要足够的记忆力、知觉和运动技能以及执行能力. 尽管患有严重阿尔茨海默病和相关痴呆(ADRD)的人不再能够安全驾驶, 驾驶性能的变化可能从阿尔茨海默病的临床前阶段就开始了.

由于认知能力下降而决定停止驾驶对老年人来说是困难和有争议的, their families and clinicians alike. 虽然有许多认知测试和道路评估可用, 临床从业人员报告说，他们接受的培训有限，而且时间有限，无法进行这些测试，以确定患者是否应该停止驾驶. Moreover, objective evidence is difficult to obtain.

在一种名为“Fit2Drive”的循证计算器的帮助下 Florida Atlantic University 是否已使一项预测老年人通过道路驾驶考试概率的在职测试的管理和评估变得容易. Based upon brief, easily administered cognitive tests, Fit2Drive为那些有认知问题的人提供了对驾驶能力的客观评估.

For the study, FAU Christine E. Lynn College of Nursing and Charles E. Schmidt College of Science 研究人员创造了一种算法，可以快速生成对单个患者的预测. 他们结合了来自两个样本的12项认知测试和道路评估数据:来自FAU的患者 Louis and Anne Green Memory and Wellness Center data repository and older drivers from the community.

The cognitive tests included the Mini-Mental State Exam (MMSE), a well-known 30-point dementia screening tool; and Trail Making Tests A, a test of visual tracking; and B, to evaluate cognitive flexibility and measure executive functioning. In total, 412 study participants, ages 59 to 89, completed the cognitive assessments and an on-road driving test.

Results of the study, published in the Journal of the American Medical Directors Association, showed that the Fit2Drive algorithm demonstrated a strong 91.5% predictive accuracy. 一步一步的检查预测能力的结果和一些组合, 结果表明，MMSE最高分和Trails B时间(以秒为单位)在预测模型中占唯一方差的比例最高，而额外测试分数对预测强度的额外增加作用最小.

研究结果还显示，两个样本的道路评价结果在统计学上存在显著差异, 大多数未通过道路驾驶考试的人来自存储库数据集(53).7%) compared with those from the community sample (7.9%).

“The anger, 个别患者的眼泪和沮丧以及缺乏指导临床医生建议的客观数据是我们努力开发高度准确的, 循证预测能力通过道路驾驶考试,” said Ruth Tappen, Ed.D., senior author, the Christine E. Lynn Eminent Scholar and Professor, FAU Christine E. Lynn College of Nursing, and a member of the FAU Stiles-Nicholson Brain Institute. “Fit2Drive的结果旨在为临床医生提供有用的客观证据，可以与关心继续驾驶是否明智的患者和家属分享。, 这种情况对他们来说是一个重大的生活事件，对初级保健提供者来说也是一个挑战.”

找出能够预测一个人通过道路驾驶考试可能性的最小数量的认知测试结果, 研究人员将办公室测试结果以道路测试结果的通过或不通过作为结果，将可能的预测变量回归到逻辑回归(统计模型)中.

与道路评估相比，二元合格-不合格结果允许预测模型评估预测结果的敏感性(真阳性)和特异性(真阴性). From this data, 研究人员根据四种可能的结果(真正)创建了一个列联表, false positive, true negative, false negative). 然后绘制敏感性和特异性的总体组合(称为ROC曲线)。, AUC提供了对其预测器的总体准确性的估计.

打印一张包含MMSE分数和Trails B时间的所有可能组合的表格将产生176页, 对于任何临床医生来说，在病人咨询时使用哪种会很尴尬,” said Tappen. “Therefore, 我们根据我们的数据推导出的方程开发了一个计算器，以方便获取所需的数据. 当输入患者MMSE和Trails B时间分数的结果时, 计算器为临床医生提供了病人通过道路驾驶考试的可能性.”

The Fit2Drive calculator can be accessed at fit2drive.org . Researchers recommend the MMSE be administered first, followed by administration of Trails A and Trails B, which is how the tests were administered in this study. 供应商可以从Fit2Drive网站下载应用程序到Android或iOS移动设备，并使用智能手机输入数据.

“As our ability to administer cognitive tests online increases, 我们也许可以创建一个完全在线版本的Fit2Drive，以进一步简化它的使用,” said Tappen.

Study co-authors are David Newman, Ph.D., professor and statistician, FAU Christine E. Lynn College of Nursing; Monica Roselli, Ph.D., professor and associate chair of psychology, FAU Charles E. Schmidt College of Science; Joshua Conniff, a Ph.D. student working in Roselli’s neuropsychology lab; Consolacion Paulette Sepe, a Ph.D. student, FAU Christine E. Lynn College of Nursing; and Matthew Newman, a systems architect, SolveIT.

-FAU-