CAREER: Aequitas: A comprehensive machine learning framework to decode health disparities

职业：Aequitas：解码健康差异的综合机器学习框架

• 批准号: 2145411
• 负责人: Joyce Ho
• 金额: $ 50万
• 依托单位: Emory University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-15 至 2027-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2145411&HistoricalAwards=false
• 关键词: CAREER; Aequitas; comprehensive; machine; learning

Reducing health disparities is important to improve the health and well-being of every person. Social determinants of health, such as socioeconomic status, education, and neighborhood, are primary drivers of health disparities. Unfortunately, rigorous scientific approaches capable of modeling health disparities are challenged by many issues related to data collection, including data privacy, insufficient sample size, heterogeneous data, missing data, multimodal data, and varying data quality along the various modalities. This project aims to develop a machine learning platform that can integrate a variety of data sources without requiring extensive annotation efforts. The platform will also enable modeling of health disparities across multiple data sites while protecting patient privacy. The project will ultimately make it easier for health disparities researchers to identify relevant social determinants of health using existing public health surveillance data in concert with modern data sources to inform the next steps for achieving health equity. The project also proposes educational activities centered around raising awareness of disparities research and broadening participation in computing.The project will advance health disparities research by taking a comprehensive and holistic approach to unpacking the impact of social determinants of health factors on patient outcomes. The project will address three fundamental and interrelated research challenges: (1) automated schema integration methods to enable collaborative standardization of data across multiple agencies; (2) broadening of the landscape of federated learning to encompass multimodal and multi-level models to incorporate factors derived from non-traditional data sources, and (3) new human-guided summarization models that leverage existing expert knowledge to reduce the annotation burden. The three research aims will be complemented by an extensive evaluation plan that includes collaboration with public health experts and physicians focused on advancing health equity. The project will demonstrate the utility and feasibility of the machine learning platform on diabetes, cardiovascular disease, and COVID-19 outcomes. This research effort will fill a critical computational gap in decoding health disparities by harnessing data across multiple data sites and diverse data sources.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

减少健康差距对于改善每个人的健康和福祉至关重要。健康的社会决定因素，如社会经济地位、教育和邻里关系，是健康差距的主要驱动因素。不幸的是，能够对健康差异进行建模的严格的科学方法受到与数据收集相关的许多问题的挑战，包括数据隐私、样本量不足、异构数据、缺失数据、多模态数据以及各种模态的数据质量沿着变化。该项目旨在开发一个机器学习平台，可以集成各种数据源，而无需进行大量的注释工作。该平台还将支持跨多个数据站点的健康差异建模，同时保护患者隐私。该项目最终将使健康差距研究人员更容易利用现有的公共卫生监测数据和现代数据来源确定健康的相关社会决定因素，为实现健康公平的下一步提供信息。该项目还提出了以提高对差异研究的认识和扩大对计算的参与为中心的教育活动。该项目将采取全面和整体的方法来揭示健康因素的社会决定因素对患者结果的影响，从而推进健康差异研究。该项目将解决三个基本的和相互关联的研究挑战：（1）自动化模式集成方法，使跨多个机构的数据协作标准化;（2）扩大联邦学习的范围，以包括多模式和多层次模型，以纳入来自非传统数据源的因素，以及（3）新的人工引导的摘要模型，其利用现有的专家知识来减少注释负担。这三个研究目标将得到一个广泛的评估计划的补充，其中包括与公共卫生专家和医生合作，重点是促进健康公平。该项目将展示机器学习平台在糖尿病、心血管疾病和COVID-19结果方面的实用性和可行性。这项研究工作将通过利用多个数据站点和不同数据源的数据，填补解码健康差异的关键计算空白。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR

• 发表时间: 2022-11
• 期刊: Proceedings of machine learning research
• 作者: Ran Xu;Yue Yu;Chao Zhang;Carl Yang;C. Yang;Xu Zhang;Ali Ho Yang

SR-CoMbEr: Heterogeneous Network Embedding Using Community Multi-view Enhanced Graph Convolutional Network for Automating Systematic Reviews

SR-CoMbEr：使用社区多视图增强图卷积网络进行异构网络嵌入，以实现自动系统审查

• 发表时间: 2023
• 期刊: Advances in Information Retrieval: 45th European Conference on Information Retrieval
• 作者: Lee, Eric W.;Ho, Joyce C.
• 通讯作者: Ho, Joyce C.

PubMed-OA-Extraction-dataset

PubMed-OA-提取数据集

• DOI: 10.5281/zenodo.6330817
• 发表时间: 2022
• 期刊: Zenodo
• 作者: Sheng, Jiasheng

Neighborhood-Regularized Self-Training for Learning with Few Labels

• DOI: 10.48550/arxiv.2301.03726
• 发表时间: 2023-01
• 期刊: Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
• 作者: Ran Xu;Yue Yu;Hejie Cui;Xuan Kan;Yanqiao Zhu;Joyce Ho;Chao Zhang;Carl Yang

Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training

• DOI: 10.1145/3539618.3592085
• 发表时间: 2023-06
• 期刊: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
• 作者: Ran Xu;Yue Yu;Joyce Ho;Carl Yang