CRII: SCH: III: Novel Data-Driven Methods to Analyze Heterogeneous Healthcare Data

CRII：SCH：III：分析异构医疗数据的新型数据驱动方法

• 批准号: 1948399
• 负责人: Sanjay Purushotham
• 金额: $ 17.49万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1948399&HistoricalAwards=false
• 关键词: CRII; SCH; III; Novel; Data

The long term goal of this project is to improve the standard-of-care of patients and build clinicians’ trust in utilizing advanced machine learning and artificial intelligence tools for computational healthcare. The national push for Electronic Health Records through the 2009 Health Information Technology for Economic and Clinical Health (HITECH) Act and the recent advances of wearable sensor technologies has resulted in an exponential surge in volume, detail, and availability of digital health data. This provides an exciting opportunity for researchers, healthcare professionals, and the patients alike to infer richer, data-driven understanding of health and illness. However, unlike other data types, healthcare data is inherently noisy, has missing values, and comes from multiple heterogeneous sources such as lab tests, doctor notes, medical images, and monitor readings. These data properties make it very challenging for most existing machine learning approaches and statistical models to discover meaningful patterns of diseases or to make robust predictions. To address these challenges, this project will develop and validate novel data-driven methods based on powerful deep learning techniques to model the complex correlations and patterns present in the healthcare data. In particular, the proposed data-driven methods will learn disease-specific and patient-specific feature patterns from heterogeneous and limited healthcare data. The effectiveness of the proposed data-driven methods will be showcased on challenging and important healthcare prediction tasks such as early prediction of sepsis and predicting the outcome of Intensive Care Units patients. This project will advocate a model-based data-driven paradigm shift for computational healthcare, and it will focus on addressing the main challenges of analyzing healthcare data, i.e., heterogeneity and limited dataset size, by developing novel data-driven methods. The proposed data-driven methods will accelerate medical discovery and aid in clinical decision making in several ways: (a) connect and learn from the disconnected heterogeneous piles of healthcare data; (b) yield new representations of illness/diseases, and (c) build clinicians’ trust in the data-driven models. The technical aims of the project are divided into three thrusts. The first thrust will focus on developing a novel deep learning framework to learn shared feature representations from heterogeneous healthcare data. Specifically, the researchers will employ machine learning approaches, such as multi-view learning and correlation analysis, to exploit the correlation structures present within and across different healthcare data sources. In addition, adversarial training based domain adaptation techniques will be used to learn joint feature representations from multi-cohort patient populations. The second thrust will focus on feature learning from limited healthcare data by utilizing patient or task similarity networks and a few-shot learning framework. In particular, multi-task learning and embedding techniques will be used to learn feature representations from limited data available for a specific patient cohort or healthcare task. In the third thrust, model uncertainty of the proposed data-driven methods will be studied using ensembles and regularization techniques. The adequacy of the proposed data-driven solutions will be validated on real-world healthcare datasets for multiple clinically relevant prediction tasks.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.

该项目的长期目标是提高患者的护理标准，并建立临床医生对利用先进的机器学习和人工智能工具进行计算医疗保健的信任。通过2009年《经济和临床健康健康信息技术法案》（HITECH）和可穿戴传感器技术的最新进展，国家推动电子健康记录，导致数字健康数据的数量、细节和可用性呈指数级增长。这为研究人员，医疗保健专业人员和患者提供了一个令人兴奋的机会，可以推断出更丰富的，数据驱动的健康和疾病理解。然而，与其他数据类型不同，医疗保健数据本质上是嘈杂的，具有缺失值，并且来自多个异构源，例如实验室测试，医生笔记，医学图像和监视器读数。这些数据属性使得大多数现有的机器学习方法和统计模型在发现有意义的疾病模式或做出稳健的预测方面非常具有挑战性。为了应对这些挑战，该项目将开发和验证基于强大的深度学习技术的新型数据驱动方法，以模拟医疗保健数据中存在的复杂相关性和模式。特别是，所提出的数据驱动方法将从异构和有限的医疗保健数据中学习疾病特异性和患者特异性特征模式。所提出的数据驱动方法的有效性将在具有挑战性和重要的医疗预测任务中展示，例如败血症的早期预测和重症监护病房患者的预后预测。 该项目将倡导基于模型的数据驱动的计算医疗模式转变，并将重点解决分析医疗数据的主要挑战，即，异质性和有限的数据集大小，通过开发新的数据驱动的方法。所提出的数据驱动方法将加速医学发现并以几种方式帮助临床决策：（a）连接并从断开的异构医疗数据堆中学习;（B）产生疾病/疾病的新表示，以及（c）建立临床医生对数据驱动模型的信任。该项目的技术目标分为三个方面。第一个重点是开发一个新的深度学习框架，从异构的医疗数据中学习共享的特征表示。具体来说，研究人员将采用机器学习方法，如多视图学习和相关性分析，来利用不同医疗数据源内部和之间的相关性结构。此外，基于对抗训练的领域自适应技术将用于从多队列患者人群中学习关节特征表示。第二个重点是通过利用患者或任务相似性网络和少量学习框架，从有限的医疗数据中进行特征学习。特别是，多任务学习和嵌入技术将用于从特定患者队列或医疗保健任务可用的有限数据中学习特征表示。 在第三个推力中，将使用集成和正则化技术研究所提出的数据驱动方法的模型不确定性。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

Fourier-Based Strategies to Improve Ethnic Feature Generation during Visible-to-Thermal Facial Translation (A work in progress)

基于傅里叶的策略在可见热面部转换过程中改善种族特征生成（正在进行的工作）

• 发表时间: 2022
• 期刊: ICML 2022
• 作者: Ordun, Catherine;Raff, Edward;Purushotham, Sanjay
• 通讯作者: Purushotham, Sanjay

Intelligent Sight and Sound: A Chronic Cancer Facial Pain Dataset

智能视觉和声音：慢性癌症面部疼痛数据集

• 发表时间: 2021
• 期刊: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track
• 作者: Ordun, C.

Deep Multi-Sensor Domain Adaptation on Active and Passive Satellite Remote Sensing Data

• 发表时间: 2020
• 作者: Xin Huang;Sahara Ali;Sanjay Purushotham;Jianwu Wang;Chenxi Wang;Zhibo Zhang

Fair and Interpretable Models for Survival Analysis

公平且可解释的生存分析模型

• DOI: 10.1145/3534678.3539259
• 发表时间: 2022
• 期刊: KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Rahman, Md Mahmudur;Purushotham, Sanjay
• 通讯作者: Purushotham, Sanjay

VDAM: VAE based domain adaptation for cloud property retrieval from multi-satellite data

• DOI: 10.1145/3557915.3561044
• 发表时间: 2022-11
• 期刊: Proceedings of the 30th International Conference on Advances in Geographic Information Systems
• 作者: Xin Huang;Chenxi Wang;S. Purushotham;Jianwu Wang