Mounting research confirms that surgeon performance is directly associated with patient outcomes.¹ The current criterion standard for evaluating surgeons is peer review, either during surgery or retrospectively via video footage. Expert review is also used to evaluate performance on robotic surgery. Yet systems data captured directly from the robot provide a novel opportunity to more accurately and objectively measure surgeon performance. A method using data from the robot could increase accuracy and decrease reliance on expert evaluators. We used a novel da Vinci Systems recording device (dVLogger; Intuitive Surgical, Inc) to collect automated performance metrics (APMs) (instrument and endoscopic camera motion tracking and events data, such as energy usage) during live robotic surgery.² We used machine learning (ML) algorithms—now commonplace outside of medicine—to process these large volumes of automatically collected data (Figure). Machine learning, a form of artificial intelligence, relies on computer algorithms and large volumes of data to “learn” and recognize broad patterns that are often imperceptible to human reviewers. With this process, we can now objectively measure surgeon performance and anticipate patient outcomes; in the near future, we will be able to personalize surgeon training.

越来越多的研究证实，外科医生的表现与患者的预后直接相关。¹目前评估外科医生的标准是同行评审，无论是在手术期间还是通过录像回顾。专家评审也用于评估机器人手术的性能。然而，直接从机器人捕获的系统数据提供了一个新的机会，可以更准确、更客观地衡量外科医生的表现。使用来自机器人的数据的方法可以提高准确性并减少对专家评估者的依赖。我们使用一种新颖的达芬奇系统记录设备 (dVLogger; Intuitive Surgical, Inc) 来收集实时机器人手术期间的自动化性能指标 (APM)（仪器和内窥镜摄像机运动跟踪和事件数据，例如能源使用情况）。²我们使用机器学习 (ML) 算法（现在在医学之外很常见）来处理这些自动收集的大量数据（图）。机器学习是人工智能的一种形式，它依靠计算机算法和大量数据来“学习”和识别人类审阅者通常无法察觉的广泛模式。通过这个过程，我们现在可以客观地衡量外科医生的表现并预测患者的结果；在不久的将来，我们将能够个性化外科医生培训。