A deep learning algorithm to detect signs of cognitive impairment in electronic health records

用于检测电子健康记录中认知障碍迹象的深度学习算法

• 批准号: 10900991
• 负责人: Sudeshna Das
• 金额: $ 84.34万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-15 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10900991
• 关键词: Accountability; Active Learning; Address; Algorithms; Alzheimer' s disease diagnosis; Alzheimer' s disease related dementia; Appointment; Artificial Intelligence; Behavioral; Caring; Characteristics; Classification; Clinical; Code; Cognitive; Cohort Studies; Communities; Complex; Computer software; Computerized Medical Record; Computers; Data; Data Element; Data Set; Databases; Dementia; Detection; Diagnosis; Elderly; Electronic Health Record; Electronics; Emergency department visit; Ensure; Entropy; Epidemiologist; Evaluation; Functional disorder; Future; Geography; Guidelines; Health; Health Care Costs; Health Professional; Health Sciences; Health system; Healthcare; Impaired cognition; Individual; Institution; Intervention; Knowledge; Label; Learning; Measures; Medical Records; Methods; Modeling; Natural Language Processing; Online Systems; Outcome; Outcome Study; Patient Care Management; Patients; Pattern; Performance; Pharmaceutical Preparations; Provider; Recording of previous events; Reference Standards; Research; Research Personnel; Research Priority; Resources; Sample Size; Sampling; Scientist; Site; Source; Specialist; Specific qualifier value; Structure; Symptoms; Technology; Testing; Texas; Text; Training; Universities; Validation; Wisconsin; Work; adjudication; algorithmic bias; annotation system; burden of illness; clinical care; clinical phenotype; deep learning; deep learning algorithm; deep learning model; demographics; drug repurposing; epidemiology study; health care service utilization; health care settings; improved; innovation; learning strategy; mild cognitive impairment; multidisciplinary; pragmatic trial; research study; screening; source localization; structured data; tool; unstructured data

Alzheimer’s Disease and Related Dementias (AD/ADRD) outcomes from real-world data, such as electronic health records (EHR), offer the possibility of examining a wide variety of research questions that cannot be answered efficiently—or at all—in other settings. A key challenge is that AD/ADRD is under-recognized in the community, under-diagnosed by healthcare professionals, and under-coded in claims data—and can be mislabeled in any setting. Thus, approaches relying on dementia diagnosis codes or medications suffer from inaccuracies in these data. EHR has a wealth of information in clinical notes, patient health history, and health system interactions that often contain signs of cognitive decline. Deep learning algorithms can leverage and learn from these complex text and data patterns in EHR. In this proposal, we aim to develop and evaluate a deep learning algorithm to improve the detection of cognitive impairment due to underlying AD/ADRD pathophysiology (including cognitive concerns, mild cognitive impairment, and dementia) using the EHR of three large healthcare institutions. For training and evaluation of the algorithm, we will use a “seed” reference standard set with detailed chart review and adjudication of cognitive diagnosis by an expert clinician (n=1,000), and then apply active learning strategies with diversity sampling to better reflect the characteristics of US older adults and iteratively increase sample size to n=20,000. We will rigorously evaluate the algorithm using EHR from all three institutions, and develop openly available guidelines and resources for the research community. Our specific aims are: 1) To develop and evaluate a deep learning NLP tool to identify patients with cognitive impairment using EHR at one institution; 2) To refine and evaluate the performance of our EHR deep learning algorithm at two other healthcare institutions; and 3) To develop open guidelines, resources, and tools for EHR data use in dementia research. We will measure the marginal improvement in accuracy of our deep learning- based classification relative to models based on diagnosis codes and medications alone, and characterize the predictors of poor model performance, both to improve the model and to understand potential biases. As such, our tool will provide a better understanding of the limitations of using diagnosis codes and/or medications in dementia research. Cutting-edge deep learning algorithms have been applied to many real-world tasks but in a limited manner to AD/ADRD. We anticipate that our state-of-the-art deep learning algorithm, which will be rigorously developed and validated with large representative datasets at multiple institutions, will more efficiently and accurately detect signs of cognitive impairment and can be readily deployed by practitioners. Improved screening of cognitive impairment in EHR will enhance dementia research studies and enable large- scale pragmatic trails. In the future, we hope, the proposed tool will also be useful in clinical settings to flag patients with cognitive impairment who could benefit from an evaluation or be referred to specialist care.

阿尔茨海默病和相关痴呆(AD/ADRD)结果来自真实世界的数据，如电子数据 健康记录(EHR)提供了检查各种研究问题的可能性，这些问题不能 在其他环境中高效地--或者根本不--回答。一个关键的挑战是AD/ADRD在 社区，被医疗保健专业人员诊断不足，在索赔数据中编码不足-并且可以 在任何环境中都贴错了标签。因此，依赖痴呆症诊断代码或药物的方法会受到 这些数据的不准确之处。EHR拥有丰富的临床记录、患者健康记录和健康信息 通常包含认知衰退迹象的系统交互作用。深度学习算法可以利用和 从电子病历中这些复杂的文本和数据模式中学习。在这项提案中，我们的目标是开发和评估一个 改进AD/ADRD认知损害检测的深度学习算法 病理生理学(包括认知问题、轻度认知障碍和痴呆症) 三家大型医疗机构。为了对算法进行训练和评估，我们将使用“SEED”引用 由专家临床医生对认知诊断进行详细图表审查和判定的标准集(n=1,000)， 然后运用多样性抽样的主动学习策略，更好地反映美国老年人的特点 并迭代地将样本大小增加到n=20,000。我们将使用EHR对算法进行严格的评估 来自所有三个机构，并为研究界制定公开可用的指导方针和资源。 我们的具体目标是：1)开发和评估深度学习NLP工具，以识别认知障碍患者 在一家机构使用EHR进行减值；2)改进和评估我们EHR深度学习的表现 算法在另外两个医疗保健机构；以及3)为EHR开发开放式指南、资源和工具 数据在痴呆症研究中的使用。我们将衡量深度学习的精确度的边际改善- 基于相对于仅基于诊断代码和药物的模型的分类，并表征 预测糟糕的模型性能，这既是为了改进模型，也是为了了解潜在的偏差。因此， 我们的工具将更好地了解使用诊断代码和/或药物的局限性 痴呆症研究。尖端的深度学习算法已被应用于许多现实世界的任务，但在 对AD/ADRD的态度有限。我们预计我们最先进的深度学习算法将是 经过严格开发并使用多个机构的大型代表性数据集进行验证，将有更多 有效和准确地检测认知障碍的迹象，并可以很容易地被从业者部署。 改善EHR中认知障碍的筛查将加强痴呆症研究，并使大型 扩大务实之路。我们希望，在未来，建议的工具也将在临床环境中有用，以标记 可以从评估中受益或被转介到专家护理的认知障碍患者。