Human-AI Collaborations to Improve Accuracy and Mitigate Bias in Acute Dyspnea Diagnosis

人机协作提高急性呼吸困难诊断的准确性并减少偏差

• 批准号: 10491373
• 负责人: Michael William Sjoding
• 金额: $ 69.91万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-20 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10491373
• 关键词: Acute; Algorithms; Artificial Intelligence; Back; Caring; Chronic Obstructive Pulmonary Disease; Clinical; Clinical Medicine; Clinical/Radiologic; Collaborations; Complex; Computer Vision Systems; Congestive Heart Failure; Controlled Environment; Data; Decision Making; Development; Diagnosis; Diagnostic; Diagnostic Errors; Disadvantaged minority; Disease; Dyspnea; Electronic Health Record; Emergency department visit; Ensure; Environment; Etiology; Evaluation; Feedback; Female; Healthcare; Heart failure; Hospitalization; Human; Hybrids; Image; Institution; Intelligence; Knowledge; Laboratories; Lead; Learning; Machine Learning; Minority Groups; Modeling; Patient Care; Patient-Focused Outcomes; Patients; Performance; Physicians; Pneumonia; Positioning Attribute; Prevalence; Process; Provider; Retinal blind spot; Shortness of Breath; Symptoms; Techniques; Testing; Training; Trust; Uncertainty; Vision; Work; accurate diagnosis; base; clinical decision support; clinically relevant; comorbidity; computer human interaction; diagnostic accuracy; diagnostic tool; health care settings; improved; male; multidisciplinary; multitask; older patient; patient population; patient subsets; prospective; prospective test; sex; tool

PROJECT SUMMARY Acute dyspnea (shortness of breath) is one of the most common reasons for emergency department visits and hospitalizations each year. Heart failure, pneumonia, and chronic obstructive pulmonary disease are the most common etiologies, representing 2.5 million hospitalizations in the US in 2017. Determining the precise cause of acute dyspnea is critically important but challenging, as presenting symptoms, laboratory testing, and imaging results may be difficult to interpret, particularly in the elderly and patients with comorbid disease or severe illness. Diagnostic errors and inappropriate treatment may occur in up to 30% of patients, which is associated with worse patient outcomes. Artificial Intelligence (AI) tools have been proposed to augment providers in the diagnostic process and are well-positioned to support the diagnostic evaluation of acute dyspnea. However, inaccurate AI tools can also worsen clinician performance. Therefore, simply keeping clinicians “in-the-loop” is not a guaranteed back-stop against a poorly performing model. This proposal seeks to enable effective Clinician-AI collaborations to improve diagnostic accuracy in acute dyspnea. We propose to: 1) evaluate computational strategies to improve the robustness of an AI tool used to support clinicians in the diagnosis of acute dyspnea, 2) test strategies to enhance collaborations between clinicians and AI tools, 3) prospectively evaluate an acute dyspnea AI tool in a clinical environment while evaluating strategies to collect clinician feedback to enable ongoing model improvement. Our multidisciplinary team consisting of experts in clinical medicine, computer vision, machine learning, and human-computer interaction are well positioned to tackle these important challenges. Successful completion of this proposal will result in a robust, generalizable acute dyspnea AI tool to augment physicians in the diagnostic evaluation of acute dyspnea. More broadly, the proposal will lead to generalizable knowledge to support safer development and integration of AI tools across healthcare settings.

项目摘要 急性呼吸困难（呼吸急促）是急诊就诊和 每年住院。心力衰竭，肺炎和慢性阻塞性肺疾病是最大的 常见病因，代表2017年美国250万个住院。确定精度原因 急性呼吸困难至关重要，但受到挑战，作为符号，实验室测试和 成像结果可能很难解释，尤其是在古老的和合并症的患者中 严重疾病。多达30％的患者可能会发生诊断错误和不适当的治疗 与较差的患者结局有关。已经提出了人工智能（AI）工具来增加 诊断过程中的提供者，并具有良好的位置，以支持急性的诊断评估 呼吸困难。但是，不准确的AI工具也会恶化临床性能。因此，仅保留 临床医生“在线”并不能保证表现不佳的模型的后台。该建议寻求 使有效的临床医生合作能够提高急性呼吸困难的诊断准确性。我们建议： 1）评估计算策略，以提高用于支持临床医生的AI工具的鲁棒性 诊断急性呼吸困难，2）增强临床医生与AI工具之间合作的测试策略，3） 前瞻性评估临床环境中的急性呼吸困难AI工具，同时评估收集的策略 临床反馈以实现正在进行的模型改进。我们的多学科团队由专家组成 临床医学，计算机视觉，机器学习和人类计算机的互动良好 应对这些重要的挑战。成功完成此提案将导致坚固，可推广的 急性呼吸困难AI工具可在急性呼吸困难的诊断评估中增加医生。更广泛的是 提案将导致可推广的知识，以支持安全开发和整合AI工具 医疗保健设置。