权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Modeling the Incompleteness and Biases of Health Data

对健康数据的不完整性和偏差进行建模

基本信息

批准号：
10581658
负责人：
YUAN LUO
金额：
$ 30.75万
依托单位：
NORTHWESTERN UNIVERSITY AT CHICAGO
依托单位国家：
美国
项目类别：
财政年份：
2020
资助国家：
美国
起止时间：
2020-06-01 至 2025-03-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10581658
关键词：
Adoption Algorithms Architecture Awareness Clinical Clinical Data Clinical Research Cohort Studies Collaborations Collection Communities Computer software Critical Care Data Data Collection Data Set Dependence Derivation procedure Development Diagnostic Diagnostic tests Electronic Health Record Electronic Medical Records and Genomics Network Evolution Functional disorder General Hospitals Goals Healthcare Healthcare Systems Hospitals Hour Individual Inpatients Institution Intuition Knowledge Knowledge Discovery Laboratories Learning Measurement Medical Memory Methodology Methods Modeling Outcome Patient Care Patient-Focused Outcomes Patients Performance Procedures Process Protocols documentation Regimen Research Research Personnel Resource-limited setting Resources Role Schedule Structure Symptoms System Test Result Testing Time Training Validation clinical decision support clinical decision-making data mining data quality design flexibility graph neural network health care service utilization health data improved lifetime risk machine learning algorithm neglect neural network architecture novel open source patient population personalized diagnostics personalized therapeutic predictive modeling recurrent neural network scale up social health determinants stem structured data text searching tool trait

项目摘要

Modeling the Incompleteness and Biases of Health Data Researchers are increasingly working to “mine” health data to derive new medical knowledge. Unlike experimental data that are collected per a research protocol, the primary role of clinical data is to help clinicians care for patients, so the procedures for its collection are not often systematic. Thus, missing and/or biased data can hinder medical knowledge discovery and data mining efforts. Existing efforts for missing health data imputation often focus on only cross-sectional correlation (e.g., correlation across subjects or across variables) but neglect autocorrelation (e.g., correlation across time points). Moreover, they often focus on modeling incompleteness but neglect the biases in health data. Modeling both the incompleteness and bias may contribute to better understanding of health data and better support clinical decision making. We propose a novel framework of Bias-Aware Missing data Imputation with Cross-sectional correlation and Autocorrelation (BAMICA), and leverage clinical notes to better inform the methods that will otherwise rely on structured health data only. In addition to evaluating its imputation accuracy, we will apply the proposed framework to assist in downstream tasks such as predictive modeling for multiple outcomes across a diverse range of clinical and cohort study datasets. Aim 1 introduces the MICA framework to jointly consider cross-sectional correlation and auto-correlation. In Aim 2, we will augment MICA to be bias-aware (hence BAMICA) to account for biases stemmed from multiple roots such as healthcare process and use them as features in imputing missing health data. This augmentation is achieved by a novel recurrent neural network architecture that keeps track of both evolution of health data variables and bias factors. In Aim 3, we will supplement unstructured clinical notes to structured health data for modeling incompleteness and biases using a novel architecture of graph neural network on top of memory network. We will apply graph neural networks to process clinical notes in order to learn proper representations as input to the memory networks for imputation and downstream predictive modeling tasks. Depending on the clinical problem and data availability, not all modules may be needed. Thus our proposed BAMICA framework is designed to be flexible and consists of selectable modules to meet some or all of the above needs. In summary, our proposal bridges a key knowledge gap in jointly modeling incompleteness and biases in health data and utilizes unstructured clinical notes to supplement and augment such modeling in order to better support predictive modeling and clinical decision making. We will demonstrate generalizability by experimenting on four large clinical and cohort study datasets, and by scaling up to the eMERGE network spanning 11 institutions nationwide. We will disseminate the open-source framework. The principled and flexible framework generated by this project will bring significant methodological advancement and have a direct impact on enhancing discovery from health data.

健康数据的不完整性和偏差建模研究人员越来越多地致力于“挖掘”健康数据，以获得新的医学知识。不像根据研究方案收集的实验数据，临床数据的主要作用是帮助临床医生照顾病人，因此其收集程序往往不是系统的。因此，缺失和/或有偏见的数据会阻碍医学知识发现和数据挖掘工作。为缺失的健康所做的现有努力数据插补通常仅集中于横截面相关性（例如，跨学科或跨学科的相关性变量）但忽略自相关（例如，跨时间点的相关性）。此外，他们经常关注模型不完整，但忽略了健康数据中的偏差。对不完整性和偏差进行建模可能有助于更好地理解健康数据，支持临床决策。我们提出了一个新的偏差感知缺失数据填补框架，横截面相关性和自相关性（BAMICA），并利用临床记录更好地告知这些方法将仅依赖于结构化健康数据。除了评估其归因之外，准确性，我们将应用所提出的框架，以协助下游任务，如预测建模，多种临床和队列研究数据集的多种结局。目标1引入云母框架，共同考虑横截面相关性和自相关性。在目标2，我们将增强云母的偏差意识（因此是BAMICA），以解释源于多个根，如医疗保健过程，并使用它们作为功能，插补缺失的健康数据。这种增强是通过一种新的递归神经网络架构实现的，该架构可以跟踪健康数据的演变，变量和偏倚因素。在目标3中，我们将为结构化健康数据补充非结构化临床记录，基于存储器的图神经网络模型网络我们将应用图神经网络来处理临床笔记，以便学习适当的表示作为记忆网络的输入，用于估算和下游预测建模任务。取决于临床问题和数据可用性，并非所有模块都需要。因此，我们提出的BAMICA框架设计灵活，由可选择的模块组成，以满足部分或全部上述需求。总之，我们的建议弥合了联合建模不完整性和偏见的关键知识差距，健康数据，并利用非结构化的临床笔记来补充和增强这种建模，以便更好地支持预测建模和临床决策。我们将通过以下方式来证明可推广性：在四个大型临床和队列研究数据集上进行实验，并通过扩展到eMERGE网络全国11个机构。我们将传播开源框架。原则性和该项目产生的灵活框架将带来重大的方法进步，对加强从健康数据中发现的直接影响。

项目成果

期刊论文数量（22）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Advances in Machine Learning Approaches to Heart Failure with Preserved Ejection Fraction.

DOI：
10.1016/j.hfc.2021.12.002
发表时间：
2022-04
期刊：
Heart failure clinics
影响因子：
3.4
作者：
Ahmad FS;Luo Y;Wehbe RM;Thomas JD;Shah SJ
通讯作者：
Shah SJ

Distinct clinical phenotypes in paediatric cancer patients with sepsis are associated with different outcomes-an international multicentre retrospective study.

DOI：
10.1016/j.eclinm.2023.102252
发表时间：
2023-11
期刊：
ECLINICALMEDICINE
影响因子：
15.1
作者：
Wosten-van Asperen, Roelie M.;la Roi-Teeuw, Hannah M.;van Amstel, Rombout B. E.;Bos, Lieuwe D. J.;Tissing, Wim J. E.;Jordan, Iolanda;Dohna-Schwake, Christian;Bottari, Gabriella;Pappachan, John;Crazzolara, Roman;Comoretto, Rosanna I.;Mizia-Malarz, Agniezka;Moscatelli, Andrea;Sanchez-Martin, Maria;Willems, Jef;Rogerson, Colin M.;Bennett, Tellen D.;Luo, Yuan;Atreya, Mihir R.;Faustino, E. Vincent S.;Geva, Alon;Weiss, Scott L.;Schlapbach, Luregn J.;Sanchez-Pinto, L. Nelson
通讯作者：
Sanchez-Pinto, L. Nelson

Integrative analysis of functional genomic screening and clinical data identifies a protective role for spironolactone in severe COVID-19.