Video Analysis of Neurosurgical Technical Performance and Adverse Events

神经外科技术表现和不良事件的视频分析

• 批准号: 10707365
• 负责人: Daniel A. Donoho
• 金额: $ 16.54万
• 依托单位: CHILDREN'S RESEARCH INSTITUTE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10707365
• 关键词: Address; Adverse event; Affect; Anatomy; Architecture; Attention; Award; Cadaver; Carotid Artery Injuries; Cerebrospinal Fluid; Cessation of life; Characteristics; Classification; Clinical; Clinical Data; Complex; Computer Vision Systems; Consensus; Data; Data Set; Data Sources; Development Plans; Discipline; Disease; Etiology; Evaluation; Feedback; Foundations; Future; Goals; Hemorrhage; Human; Institution; International; Intervention; Knowledge; Label; Learning; Length; Machine Learning; Measures; Medical Imaging; Memory; Mentors; Mentorship; Methods; Mission; Modeling; Movement; National Institute of Neurological Disorders and Stroke; Nervous System Trauma; Neurologic; Neurosurgeon; Operative Surgical Procedures; Outcome; Pathology; Patient-Focused Outcomes; Patients; Pattern; Performance; Perfusion; Persons; Phase; Pituitary Gland; Pituitary Neoplasms; Postoperative Period; Procedures; Research; Residual Neoplasm; Resources; Scientist; Standardization; Statistical Methods; Stroke; Surgeon; Surgical Error; Techniques; Testing; Time; Tissues; Training; United States; Video Recording; Visual; Visualization; Work; adverse outcome; career; career development; cerebrovascular; deep learning; design; disability; experience; high risk; improved; instrument; large datasets; machine learning algorithm; machine learning method; machine learning model; multimodal data; nervous system disorder; neural network; neural network algorithm; neurosurgery; post stroke; predictive modeling; prevent; prospective; rational design; research and development; simulation; skills; success; surgical research; surgical risk; therapy design; tool; visual learning

PROJECT SUMMARY The proposed research and career development plan aim to provide the candidate with the knowledge, experience, and resources necessary to become an independent neurosurgeon-scientist whose research reduces stroke and neurologic disability after neurosurgery through the design and implementation of machine learning (ML) and computer vision (CV) systems that provide surgeons with feedback to improve surgical performance. After formal training, practicing neurosurgeons receive little feedback and instead learn by experience accrued during procedures. However, most do not accrue sufficient case volume to achieve optimal outcomes in every procedure. Ultimately, >16,000 patients are harmed by preventable neurosurgical errors each year, resulting in stroke and neurologic disability in up to 70% and death in up to 16% of affected patients. Unfortunately, the study of harmful adverse events during surgery is obstructed by a lack of datasets containing surgical actions leading up to adverse events or outcomes. The candidate proposes to overcome this limitation by using advanced CV and ML methods to analyze a previously unstudied, multimodal dataset combining pituitary surgical video and clinical data. Pituitary surgery is performed >10,000 times annually in the U.S., can be recorded for analysis, and its steps, errors, and adverse events were recently standardized in an international consensus statement. Specifically, the candidate will test the central hypothesis that the interaction of visible surgeon skill factors with visualized features, including patient anatomy and disease pathology, produces identifiable step-specific surgical errors that result in postoperative stroke, neurologic disability, and other adverse events. Specific Aims: 1) Use CV to identify step-specific errors (defined by tool usage, step progression, and phase characteristics) preceding adverse events; 2) Train ML models to predict upcoming adverse events from prior metrics of surgeon skill and current visual features of the surgical field. Methods to identify high-risk neurosurgical actions, predict upcoming adverse events from a surgeon’s movements, and retrospectively highlight critical timepoints and visual features associated with adverse events are necessary to rationally design and implement interventions to reduce stroke, neurologic disability, and other adverse events. The feasibility and success of this work will be facilitated by the candidate’s outstanding mentoring team, including a surgeon-scientist with experience conducting CV-based surgical performance assessments from procedural visual data and experts in ML using medical image and clinical data, biomedical applications of deep learning in complex prediction models, and multi-institutional pituitary surgical research. In the final year of the award, the candidate will apply for an R01 award to prospectively implement generalizable predictive models (developed in Aim 2) using a larger dataset of videos from several surgical procedures and to develop methods to collect and act upon data from operative video in real-time.

项目摘要 拟议的研究和职业发展计划旨在为候选人提供知识， 经验和成为独立神经外科科学家所必需的资源 通过设计和实施，神经外科手术后减少了中风和神经性残疾 学习（ML）和计算机视觉（CV）系统，可为外科医生提供反馈以改善手术 表现。经过正规培训后，实用的神经外科医生几乎没有反馈，而是通过 程序期间收到的经验。但是，大多数没有获得足够的病例量以实现最佳 每个过程中的结果。最终，> 16,000名患者受到可预防的神经外科错误的伤害 每年，最多70％的中风和神经性残疾，多达16％的受影响的死亡 患者。不幸的是，缺乏数据集阻碍了手术期间有害不良事件的研究 包含导致不良事件或结果的手术动作。克服的候选提议 通过使用高级简历和ML方法来分析先前未研究的多模式数据集的限制 结合垂体外科视频和临床数据。垂体手术每年进行> 10,000次 美国可以记录用于分析，其步骤，错误和不良事件最近被标准化 国际共识声明。具体而言，候选人将检验中心假设 可见外科医生技能因素与可视化特征的相互作用，包括患者解剖和疾病 病理学，产生可识别的阶梯特异性手术错误，导致术后中风，神经系统 残疾和其他不利事件。具体目的：1）使用简历来识别特定步骤的错误（由工具定义 在不良事件之前的使用，步骤进展和相位特征）； 2）训练ML模型预测 即将发生的不良事件来自外科医生技能的先前指标和手术领域的当前视觉特征。 识别高风险神经外科动作的方法，预测外科医生的广告事件 运动，并追溯强调了与广告事件相关的关键时间点和视觉特征 对于合理设计和实施干预措施以减少中风，神经功能残疾和 其他不利事件。这项工作的可行性和成功将由候选人的杰出 指导团队，包括具有基于简历外科手术表现的经验的外科医生科学家 使用医学图像和临床数据，生物医学的方法和ML的专家评估ML的评估 深度学习在复杂预测模型中的应用以及多机构的垂体外科研究。在 该奖项的最后一年，候选人将申请R01奖励，以实施可推广的前瞻性实施 预测模型（在AIM 2中开发）使用来自多个外科手术程序的较大视频数据集和 开发方法，以实时收集从操作视频的数据进行采取行动。

项目成果

A systematic review of annotation for surgical process model analysis in minimally invasive surgery based on video.

• DOI: 10.1007/s00464-023-10041-w
• 发表时间: 2023-06
• 期刊: Surgical endoscopy

Commentary: Extra-Axial Endoscopic Third Ventriculostomy for the Treatment of Slit Ventricle Syndrome: 2-Dimensional Operative Video.

评论：轴外内窥镜第三脑室造口术治疗裂隙心室综合征：二维手术视频。

• DOI: 10.1227/ons.0000000000000603
• 发表时间: 2023
• 期刊: Operative neurosurgery (Hagerstown, Md.)
• 作者: Duquette,ElizabethR;Donoho,DanielA;Zada,Gabriel
• 通讯作者: Zada,Gabriel

Human visual explanations mitigate bias in AI-based assessment of surgeon skills.

• DOI: 10.1038/s41746-023-00766-2
• 发表时间: 2023-03-30
• 期刊: NPJ digital medicine
• 影响因子: 15.2

"Are we recording this?" Surgeons deserve next-generation analytics.

• DOI: 10.3171/2023.4.jns23640
• 发表时间: 2023-05-26
• 期刊: Journal of neurosurgery
• 影响因子: 4.1

A multi-institutional study using artificial intelligence to provide reliable and fair feedback to surgeons.

• DOI: 10.1038/s43856-023-00263-3
• 发表时间: 2023-03-30
• 期刊: COMMUNICATIONS MEDICINE
• 作者: Kiyasseh, Dani;Laca, Jasper;Haque, Taseen F;Miles, Brian J;Wagner, Christian;Donoho, Daniel A;Anandkumar, Animashree;Hung, Andrew J
• 通讯作者: Hung, Andrew J