Unobtrusive and continuous monitoring of cognitive changes using smartphones

使用智能手机不引人注目且持续监测认知变化

• 批准号: 10250402
• 负责人: Maciej Rafal Kos
• 金额: $ 4.21万
• 依托单位: NORTHEASTERN UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-03-12
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10250402
• 关键词: Accounting; Adult; Aging; Alzheimer' s Disease; Alzheimer' s disease related dementia; Android; Attention; Biological Markers; Brain imaging; Caregivers; Caring; Cellular Phone; Characteristics; Clinical; Clinical Trials; Clinical assessments; Cognition; Cognitive; Cognitive Science; Cognitive deficits; Cross-Sectional Studies; Data; Dementia; Development; Diagnosis; Early Diagnosis; Ecological momentary assessment; Effectiveness; Elderly; Frequencies; Functional disorder; Goals; Health; Healthcare Systems; Impaired cognition; Individual; Informed Consent; Location; Longitudinal Studies; Measures; Methods; Modeling; Monitor; Motor; Names; Nature; Nerve Degeneration; Neurocognitive; Neurodegenerative Disorders; Neurology; Neuropsychology; Participant; Patients; Pattern; Phase; Psychometrics; Psychomotor Performance; Recording of previous events; Reporting; Research; Research Personnel; Research Project Grants; Selection for Treatments; Services; Short-Term Memory; Signal Transduction; Social Interaction; Speed; System; Testing; Training; Transportation; Traumatic Brain Injury; Validation; Visit; accurate diagnosis; base; care providers; cognitive change; cognitive function; cost; digital; health data; improved; instrumental activity of daily living; mHealth; middle age; mild cognitive impairment; mobile application; mobile computing; neurocognitive disorder; novel strategies; open source tool; socioeconomics; software development; time use; touchscreen; walking speed; web site; young adult

Project Summary Acquired cognitive impairment associated with aging, neurocognitive disorders, like Alzheimer’s disease, and traumatic brain injury (TBI) pose major challenges to healthcare systems throughout the world. To facilitate successful aging, effective methods are needed for monitoring cognition in order to detect early signs of impaired cognition and dementia. However, the effectiveness of existing neuropsychological assessments is thwarted by their sporadicity, difficulty in accounting for the context-dependent nature of patients’ health (e.g., having a “good” or a “bad” day), and reliance on frequently inaccurate patient and caregiver reports. Thus, new approaches are needed for objective and ecologically valid assessment of cognitive function and for early detection of impaired cognition associated with neurocognitive disorders like Alzheimer’s disease and TBI. Current mHealth and AI approaches enable continuous context inference from smartphone use and location data. Patient reports of Instrumental Activities of Daily Living (IADLs) can be greatly enhanced with continuous, objective context inferences from passively collected smartphone-based data that can contribute to earlier and more accurate diagnoses of neurocognitive disorder including Alzheimer’s disease and related dementia. Cross-sectional studies involving younger and older adults suggest that characteristics of an individual’s mobile application use and typing speed correlate with working memory, attention, and psychomotor function. Therefore, the proposed augmentation of clinical assessments with continuous and objective estimates of cognitive changes derived computationally and unobtrusively from mobile application use characteristics and motor interactions has the potential to inform both the early detection and diagnosis of impaired cognition associated with neurocognitive disorders, such as Alzheimer’s disease and TBI, and potentially treatment selection for their amelioration. The central hypothesis to be tested in this longitudinal study is that changes in cognition, including impaired cognition associated with Alzheimer’s disease and other neurocognitive disorders, can be inferred from smartphone data. In the F99 phase, Mr. Kos will a) augment existing measures derived from IADLs and lifespace mobility with analogous measures inferred from mobile location-finding systems (e.g., GPS) and application use data, and b) propose a digital biomarker for tracking cognitive changes and impaired cognition based on temporal patterns in application use and motor interactions with smartphones. Validation will be conducted on 80 middle-aged individuals; 20 with subjective cognitive impairment, 20 with diagnosed Mild Cognitive Impairment, 20 with TBI, and 20 cognitively intact controls. In the K00 phase, Mr. Kos will select the subset of these measures determined to be most applicable to tracking cognitive changes and impaired cognition and, thus, prime for detecting early signs of Alzheimer’s disease and other types of neurocognitive disorder in older adults. Their refinement and validation in clinical trials using biomarkers and brain imaging data will enable developing a mechanistic understanding of a) the relationships between impaired cognition, Alzheimer’s disease, and neurocognitive changes including TBI and b) how these relationships are reflected in interactions with mobile technologies.

项目摘要 与衰老相关的获得性认知障碍、神经认知障碍（如阿尔茨海默病）和创伤性脑损伤（TBI）对全世界的医疗保健系统构成了重大挑战。为了促进成功的老龄化，需要有效的方法来监测认知，以检测认知受损和痴呆的早期迹象。然而，现有神经心理学评估的有效性受到其偶发性、难以解释患者健康的背景依赖性（例如，具有“好”或“坏”的一天），以及依赖于经常不准确的患者和护理者报告。因此，需要新的方法来对认知功能进行客观和生态有效的评估，并早期检测与阿尔茨海默病和TBI等神经认知障碍相关的认知受损。 目前的mHealth和AI方法可以从智能手机使用和位置数据中进行持续的上下文推断。通过从被动收集的基于智能手机的数据中进行连续、客观的上下文推断，可以大大增强患者的工具性日常生活活动（IADL）报告，这有助于更早、更准确地诊断神经认知障碍，包括阿尔茨海默病和相关痴呆症。涉及年轻人和老年人的横断面研究表明，个人使用移动的应用程序和打字速度的特征与工作记忆、注意力和心理功能相关。因此，通过对认知变化进行连续和客观的估计来增强临床评估，这些认知变化是通过计算和不显眼的方式从移动的应用程序使用特征和运动交互中得出的，这有可能为与神经认知障碍（如阿尔茨海默病和TBI）相关的认知受损的早期检测和诊断提供信息，并可能为改善这些认知障碍提供治疗选择。 在这项纵向研究中要检验的中心假设是，认知的变化，包括与阿尔茨海默病和其他神经认知障碍相关的认知受损，可以从智能手机数据中推断出来。 在F99阶段，科斯先生将a）用从移动的定位系统推断出的类似度量（例如，GPS）和应用程序使用数据，以及B）基于应用程序使用中的时间模式和与智能手机的运动交互，提出用于跟踪认知变化和受损认知的数字生物标志物。将对80名中年人进行验证; 20名主观认知障碍，20名诊断为轻度认知障碍，20名TBI，20名认知完整的对照。 在K 00阶段，科斯先生将选择这些措施的子集，确定其最适用于跟踪认知变化和认知受损，因此，主要用于检测老年人阿尔茨海默病和其他类型的神经认知障碍的早期迹象。使用生物标志物和脑成像数据在临床试验中对它们进行改进和验证，将能够对以下内容进行机械理解：a）认知受损、阿尔茨海默病和神经认知变化（包括TBI）之间的关系，以及B）这些关系如何反映在与移动的技术的交互中。