Wentzel A, Floricel C, Canahuate G, Naser M A, Mohamed A S, Fuller C D, van Dijk L, Marai G E
University of Illinois Chicago, Electronic Visualization Lab.
University of Iowa.
Comput Graph Forum. 2023 Jun;42(3):283-295. doi: 10.1111/cgf.14830. Epub 2023 Jun 27.
Developing applicable clinical machine learning models is a difficult task when the data includes spatial information, for example, radiation dose distributions across adjacent organs at risk. We describe the co-design of a modeling system, DASS, to support the hybrid human-machine development and validation of predictive models for estimating long-term toxicities related to radiotherapy doses in head and neck cancer patients. Developed in collaboration with domain experts in oncology and data mining, DASS incorporates human-in-the-loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrate DASS with the development of two practical clinical stratification models and report feedback from domain experts. Finally, we describe the design lessons learned from this collaborative experience.
当数据包含空间信息时，例如头颈部癌患者相邻危及器官的辐射剂量分布，开发适用的临床机器学习模型是一项艰巨的任务。我们描述了一个建模系统DASS的协同设计，以支持混合人机开发和验证用于估计头颈部癌患者放疗剂量相关长期毒性的预测模型。DASS是与肿瘤学和数据挖掘领域的专家合作开发的，它结合了人在回路视觉引导、空间数据和可解释人工智能，通过自动数据挖掘来增强领域知识。我们通过开发两个实用的临床分层模型展示了DASS，并报告了领域专家的反馈。最后，我们描述了从这次合作经验中学到的设计经验教训。
