An Intelligent Melanoma Diagnostic Training System

描述(由申请人提供)：该项目将确定模型追踪智能教学系统的描述良好的范例是否可用于创建多媒体的、基于知识的医学培训系统。我们建议开发黑色素瘤诊断培训系统，这是一个基于虚拟幻灯片的病理住院医师辅导系统。该系统旨在为恶性黑色素瘤和其他黑色素细胞皮肤损害的检测、分类和报告提供指导。黑素细胞病变是组织学癌症诊断的难点。黑色素瘤的假阴性和假阳性诊断可导致显著的发病率和死亡率，是最常见的诉讼病理病例类型之一。黑色素瘤治疗的新进展赋予病理学家越来越多的责任来识别和报告一系列组织学预后指标。我们建议使用智能教学系统(ITS)的范例来开发这一领域的诊断培训系统。ITS是基于计算机的系统，通过整合专家表现模型并为每个用户动态建立唯一的学生模型来提供个性化教学。ITS在模拟真实世界任务的系统中非常有效，使学生能够在基于案例的场景中工作，因为ITS提供指导、指出错误并组织课程以满足个别学习者的需求。作为该项目的一部分，我们将开发一个黑素细胞病变和黑色素瘤的全幻灯片数字图像库，每个图片库都有黄金标准的诊断。系统开发将伴随着受控的、随机的实验室评估，在该评估中，我们将使用测试前和测试后的方法检查系统对检测、分类和报告准确性的影响。在项目的最后一年，我们将在宾夕法尼亚州癌症联盟生物信息联盟的多个地点部署该系统，并使用调查、访谈和日志文件分析来评估该系统的接受度和使用情况。

DESCRIPTION (provided by applicant): This project will determine whether the well-described paradigm of the model-tracing Intelligent Tutoring System can be adapted to create a multimedia, knowledge-based, medical training system. We propose to develop the Melanoma Diagnostic Training System, a virtual-slide based tutor for pathology residents. The system is designed to provide instruction in detection, classification, and reporting of Malignant Melanoma and other melanocytic skin lesions. Melanocytic lesions are a difficult area of histologic cancer diagnosis. False negative and false positive diagnoses of Melanoma can result in significant morbidity and mortality, and are among the most commonly litigated pathology case types. New advances in treatment of Melanoma have placed an increasing responsibility on the pathologist to identify and report on a range of histologic prognostic indicators. We propose to develop a diagnostic training system in this domain using the paradigm of the Intelligent Tutoring Systems (ITS). ITS are computer-based systems that provide individualized instruction by incorporating models of expert performance and dynamically building a unique student model for each user. ITS can be highly effective in systems that simulate real-world tasks, enabling students to work through case-based scenarios as the ITS offers guidance, points out errors and organizes the curriculum to address the needs of that individual learner. As part of the project, we will develop a library of whole-slide digital images of melanocytic lesions and melanoma, each with a gold-standard diagnosis. System development will be accompanied by a controlled, randomized laboratory evaluation in which we will examine the effect of the system on accuracy of detection, classification, and reporting using pre-test and post-test methods. In the final year of the project, we will deploy the system across multiple sites in the Pennsylvania Cancer Alliance Bioinformaties Consortium, and evaluate acceptance and use of the system using surveys, interviews, and log-file analysis.