Development of a Machine Learning Model for Prostate Cancer Treatment Planning

开发前列腺癌治疗计划的机器学习模型

• 批准号: 10027488
• 负责人: ROBERTO NICOLALDE
• 金额: $ 30万
• 依托单位: NICOLALDE R AND D, LLC
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-16 至 2020-06-15
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10027488
• 关键词: Achievement; Anatomy; Artificial Intelligence; Clinical; Clinical Trials; Computer software; Consensus; Contracts; Data; Development; Dose; Expert Systems; Fostering; Goals; Gold; Human; Individual; Institution; Investments; Knowledge; Learning; Machine Learning; Malignant neoplasm of prostate; Methodology; Modeling; Normal tissue morphology; Outcome; Patient imaging; Patients; Process; Prostate Cancer therapy; Quality of Care; Quality of life; Radiation therapy; Structure; System; Technology; Testing; Time; Training; X-Ray Computed Tomography; base; cost; economic cost; experience; human capital; improved; meetings; preference; prostate cancer model; tool; treatment planning

This project’s goal is to develop and test an application that uses Artificial Intelligence (AI) to improve consistency and quality of RT treatment plans for prostate cancer. By understanding expert planner preferences in structure contouring and treatment planning, and combining this rationale with data amassed in NRG clinical trials, AI models will be trained to produce contours and treatment plans achieving consensus amongst experts and optimal quality of life outcomes based on more clinical evidence than any one expert’s input. Overall, this project will meet a need for improved treatment planning for prostate cancer at reduced economic cost. This AI system will generate treatment plans that will provide a standard which may be compared against those generated by human planners; in time, as teams at individual institutions who employ the product develop greater experience with the system, their engagement will foster the achievement of plans at higher quality with lower investment of human capital, thereby improving quality of care while reducing costs.

该项目的目标是开发和测试一个应用程序，该应用程序使用人工智能（AI）来提高前列腺癌RT治疗计划的一致性和质量。通过了解专家规划者在结构轮廓和治疗计划方面的偏好，并将此原理与NRG临床试验中积累的数据相结合，人工智能模型将被训练以生成轮廓和治疗计划，从而在专家之间达成共识，并基于比任何一个专家的输入更多的临床证据来获得最佳生活质量结果。 总的来说，该项目将满足改善前列腺癌治疗计划的需求，降低经济成本。 该人工智能系统将生成治疗计划，该计划将提供一个标准，可以与人类规划者生成的计划进行比较;随着使用该产品的各个机构的团队对该系统的经验增加，他们的参与将促进以更低的人力资本投资实现更高质量的计划，从而提高护理质量，同时降低成本。