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

基本信息

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
项目类别：
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&apos s disease diagnosis Alzheimer&apos 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

项目摘要

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症 (AD/ADRD) 来自真实世界数据（例如电子数据）的结果健康记录 (EHR)，提供了检查各种无法通过研究解决的研究问题的可能性在其他环境中能否得到有效回答（或根本没有回答），一个关键的挑战是 AD/ADRD 在该领域未被充分认识。社区、医疗保健专业人员的诊断不足以及索赔数据的编码不足，并且可以因此，依赖痴呆症诊断代码或服用药物的方法可能会被错误标记。这些数据中的不准确之处 EHR 在临床记录、患者健康史和健康方面拥有丰富的信息。通常包含认知衰退迹象的系统交互可以利用深度学习算法。从 EHR 中的这些复杂文本和数据模式中学习。在本提案中，我们的目标是开发和评估一个深度学习算法可改善对潜在 AD/ADRD 所致认知障碍的检测使用 EHR 进行病理生理学（包括认知问题、轻度认知障碍和痴呆）对于算法的训练和评估，我们将使用“种子”参考。由临床专家 (n=1,000) 进行的包含详细图表审查和认知诊断判定的标准集，然后应用具有多样性抽样的主动学习策略，以更好地反映美国老年人的特征成人并迭代地将样本量增加到 n=20,000 我们将使用 EHR 严格评估该算法。来自所有三个机构，并为研究界制定公开可用的指南和资源。我们的具体目标是： 1) 开发和评估深度学习 NLP 工具来识别患有认知障碍的患者在一个机构使用 EHR 进行损伤；2) 完善和评估我们的 EHR 深度学习的性能其他两家医疗机构的算法；以及 3) 开发 EHR 的开放指南、资源和工具我们将衡量深度学习准确性的边际改进。相对于仅基于诊断代码和药物的模型的分类，并表征模型性能不佳的预测因子，既可以改进模型，也可以理解潜在的偏差。我们的工具将帮助您更好地了解使用诊断代码和/或药物的局限性尖端的深度学习算法已应用于许多现实世界的任务，但仅限于痴呆症研究。我们预计我们最先进的深度学习算法将是有限的。通过多个机构的大型代表性数据集进行严格开发和验证，将更多有效、准确地检测认知障碍的迹象，并且可以由从业者轻松部署。改进电子病历中认知障碍的筛查将加强痴呆症研究，并使大规模我们希望，将来所提出的工具也能在临床环境中发挥作用，以进行标记。患有认知障碍的患者可以从评估中受益或被转诊至专科护理。