Cancer Prevention and Control (CAPAC) Research Training Program

摘要 癌症是美国最大的种族/少数民族拉美裔美国人的主要死因 在各州，癌症健康差距的影响不成比例。尽管存在这种差异，癌症数据集， 特别是西班牙裔人口，不像其他种族那样可用。考虑到癌症的需要 关注西班牙裔健康的健康差异研究，有必要应用人工智能 智能/机器学习(AI/ML)在这一领域的方法，以及使拉美裔人癌症的紧迫性 数据集可查找、可访问、可互操作、可重用(FAIR)和AI/ML就绪。癌症预防 波多黎各大学综合癌症与控制研究(CAPAC)培训项目 中心(UPRCCC)，招募研究生和卫生专业学生进行暑期实践研究 有公关经验。本附录旨在扩大上级CAPAC培训计划的范围，并为 1)操作和预处理拉美裔癌症的技术和方法的研究人员 数据集，以使它们公平并准备好AI/ML，以及2)开发基于ML的模型的可用方法 分析这些数据并创建以西班牙裔为重点的癌症诊断和治疗预测模型 数据集。我们将开发一个基于数据科学项目生命周期的在线课程，其中包括四个 阶段：1)数据理解/数据预处理；2)数据辩论；3)模型规划；4)模型 大楼。这门24小时的在线异步课程将按两个部分的模块进行组织。 构成部分1将包括以下主题：癌症数据类型的基础、识别和理解 癌症数据集、数据科学概念和项目生命周期；基本编程概念；编程 Python；探索、预处理和调节癌症数据集；执行提取、转换、加载 (ETL)在AI/ML建模之前。组件2将增加如下主题：AI/ML的原理；变量相关性 和关联；确定用于训练和测试的数据集；监督和非监督最大似然方法； 分类、回归和集成ML算法；熟悉ML工具。为了发展我们的课程， 例子和项目，我们将使用来自美国和PR的拉美裔癌症数据集。该课程将 对有兴趣的参与者(40名受训人员)，包括亚太亚太区域委员会的参与者(校友)，自愿和免费 以及申请者、CAPAC导师以及来自合作赠款/机构的受训人员和研究人员。 学生获得的技能将通过测验和期末实践项目进行评估，而课程将 在上级赠款评价部分的支持下进行评价。这一副刊将影响 开发来自美国和波多黎各的人力资源(如学生、研究人员、临床医生) 具备制作公平的拉美裔癌症数据集和应用AI/ML所需的能力和技能 创建基于ML的癌症预测模型的方法。

Summary Cancer is the leading cause of death among Hispanics, the largest racial/ethnic minority group in the United States and disproportionately affected by cancer health disparities. Despite this disparity, cancer datasets, specifically for Hispanic populations, are not as available as for other ethnicities. Given the need for cancer health disparities research with a focus on Hispanic health, there is a need for applying Artificial Intelligence/Machine Learning (AI/ML) approaches in this field, and an urgency on making Hispanics cancer datasets Findable, Accessible, Interoperable, and Reusable (FAIR) and AI/ML -ready. The Cancer Prevention and Control Research (CAPAC) Training Program of the University of Puerto Rico Comprehensive Cancer Center (UPRCCC), recruits graduate and health professions students for a hands-on summer research experience in PR. This supplement aims to expand the scope of the parent CAPAC training Program and prepare research workforce on 1) the techniques and approaches to manipulate and pre-process Hispanics cancer datasets to make them FAIR and AI/ML ready, and on 2) the available methods for developing ML-based models to analyze these data and create predictive models for cancer diagnosis and treatments with a focus on Hispanic datasets. We will develop an online course based on the data science project lifecycle, which includes four phases: 1) Data Understanding/ Data Pre-processing; 2) Data Wrangling; 3) Model Planning; and 4) Model Building. This 24-hour online asynchronous course will be organized in modules within two components. Component 1 will include the following topics: fundamentals of cancer data types, identifying and understanding cancer datasets, data science concepts and project lifecycles; basic programming concepts; programming with Python; exploring, pre-processing, and conditioning the cancer datasets; performing Extract, Transform, Load (ETL) prior to AI/ML modelling. Component 2 will add topics such as: principles of AI/ML; variable correlations and associations; determining datasets for training and testing; supervised and unsupervised ML approaches; classification, regression and ensembles ML-algorithms; familiarizing with ML tools. To develop our course, examples and projects, we will use Hispanics cancer datasets from the US and PR. The course would be voluntary and free for interested participants (capacity of 40 trainees), including CAPAC participants (alumni) and applicants, CAPAC mentors, as well as trainees and research staff from collaborating grants/institutions. Student’s gained skills will be evaluated with quizzes and a final practical project, while the course will be evaluated with the support of the evaluation component of the parent grant. This supplement will impact the development of human resources (e.g. students, researchers, clinicians) from the United States and Puerto Rico with the competencies and skills needed to make FAIR Hispanics cancer datasets and to apply AI/ML approaches for creating ML-based predictive models for cancer.