SCH: AI-DOCTOR COLLABORATIVE MEDICAL DIAGNOSIS

SCH：AI-医生协同医疗诊断

• 批准号: 10592801
• 负责人: Hien Van Nguyen
• 金额: $ 26.91万
• 依托单位: UNIVERSITY OF HOUSTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-22 至 2026-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10592801
• 关键词: Address; Algorithms; Artificial Intelligence; Cardiovascular system; Cessation of life; Classification; Clinical; Cognitive; Computer-Assisted Diagnosis; Detection; Diagnosis; Diagnostic; Diagnostic Errors; Diagnostic radiologic examination; Error Sources; Evaluation; Expert Systems; Fatigue; Goals; Hospitals; Human; Institution; Instruction; Intention; Joints; Knowledge; Learning; Light; Lung nodule; Machine Learning; Malignant Neoplasms; Malignant neoplasm of lung; Measures; Medical; Methodology; Methods; Mission; Modeling; Monitor; Outcome; Pathologic; Performance; Principal Investigator; Problem Solving; Process; Psychological reinforcement; Public Health; Pulmonary Embolism; Radiology Specialty; Research Design; Retrospective Studies; Reverse engineering; Scanning; Software Design; System; Thinking; Thoracic Radiography; Time; User-Computer Interface; Visual; Work; Workload; artificial intelligence algorithm; base; cancer diagnosis; computer framework; design; diagnostic accuracy; distraction; gaze; imaging modality; improved; innovation; iterative design; multidisciplinary; multimodality; neglect; next generation; novel; radiologist; success; theories; usability; user-friendly; visual information

Recent retrospective studies show that radiology's diagnostic error rates did not decrease significantly over the years. For example, missed lung cancer rates remain at 20-60% on chest radiography dependent on study design. This error contributes to 40,000-80,000 deaths annually in U.S. hospitals. This project aims to develop a computational framework for Al to collaborate with human radiologists on medical diagnosis tasks. To achieve this goal, we divide the project into three Aims, where the first two focus on fundamental theories, and the last one evaluates the proposed approaches on targeted applications. Aim 1: Develop computational principles for optimal Al-radiologist interaction. This Aim will develop a computational framework for guiding the interaction between radiologists and Al to achieve the best possible diagnostic performance while minimizing the time burden. Our framework consists of the first method for reverse-engineering radiologists' intention from the joint gaze and visual information based on reinforcement learning. This Aim is the first to provide an integrated system with gaze sensing, deep networks, and human radiologists. The knowledge from this Aim will fundamentally transform how one would build collaborative medical diagnosis systems. Aim 2: Design a user-friendly and minimally-interfering interface for radiologist-Al interaction. This Aim addresses an essential question of designing a minimally interfering interface that allows human radiologists to interact with Al models efficiently. Our proposed system combines an innovative "multimodal thinking with audio and gaze" (MTAG) methodology with user-centered iterative design. The process will result in a novel radiologist-Al collaborative interface that maximizes time efficiency while minimizing the amount of distraction. The outcome of this Aim will shed light on design principles for systems involving radiologists. Aim 3: Evaluation Plan. This Aim evaluates the proposed approaches in Aim 1-2 on two clinically important applications: i) Lung nodule detection and ii) pulmonary embolism. Lung cancer is the second most common cancer, and pulmonary embolism is the third most common cause of cardiovascular death. Studying how radiologists collaborate with Al to reduce diagnostic errors will lead to significant clinical impacts. RELEVANCE (See instructions): Diagnostic errors contribute to 40,000-80,000 deaths annually in U.S. hospitals. This project combines novel artificial intelligence (Al) algorithms, gaze monitoring software, and design principles to help doctors minimize diagnostic errors due to cognitive and perceptual biases. The project's success will fundamentally change how we design Al medical systems to increase diagnostic accuracy, save lives, reduce missed cancer diagnoses, improve public health, and advance NCl's mission.

最近的回顾性研究表明，放射学的诊断错误率并没有显着下降， 这些年例如，胸部X线摄影的肺癌漏诊率保持在20-60%， 研究设计.这种错误每年导致美国医院40，000 - 80，000人死亡。该项目旨在 为人工智能开发一个计算框架，与人类放射科医生合作进行医疗诊断 任务为了实现这一目标，我们将该项目分为三个目标，其中前两个目标侧重于基础 理论，最后一个评估所提出的方法有针对性的应用。 目标1：制定最佳铝放射科医师互动的计算原则。这一目标将发展 一个计算框架，用于指导放射科医生和人工智能之间的互动，以实现最佳的 尽可能的诊断性能，同时最大限度地减少时间负担。我们的框架包括第一个 根据联合凝视和视觉信息对放射科医生的意图进行反向工程的方法 强化学习这一目标是第一个提供一个集成系统与凝视传感，深 网络和人类放射科医生。这一目标的知识将从根本上改变一个人如何 将建立协作医疗诊断系统。 目标2：为放射科医生-人工智能交互设计一个用户友好且干扰最小的界面。这 Aim解决了一个基本问题，即设计一个最小干扰的界面， 放射科医生与人工智能模型有效地互动。我们提出的系统结合了创新的“多模式 以用户为中心的迭代设计。该过程将 导致一种新的放射科医生-人工智能协作界面，最大限度地提高时间效率，同时最大限度地减少 分心的程度。这一目标的结果将阐明系统的设计原则， 放射科医生 目标3：评价计划。本目标对目标1-2中提出的两种临床方法进行了评估。 重要应用：i）肺结节检测和ii）肺栓塞。肺癌是第二位 肺栓塞是最常见的癌症，肺栓塞是心血管死亡的第三大常见原因。 研究放射科医生如何与人工智能合作以减少诊断错误将带来重大的临床意义。 影响。 相关性（参见说明）： 在美国，诊断错误每年导致4万至8万人死亡。该项目结合了 新颖的人工智能（AI）算法，凝视监测软件和设计原则，以帮助医生 最大限度地减少由于认知和感知偏差造成的诊断错误。该项目的成功将从根本上 改变我们设计人工智能医疗系统的方式，以提高诊断准确性，挽救生命，减少漏诊， 癌症诊断，改善公众健康，推进NCI的使命。