Cardea: An Open Automated Machine Learning Framework for Electronic Health Records

Published in

International Conference on Data Science and Ad...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

This paper proposes Cardea, an extensible open-source automated machine learning framework encapsulating common prediction problems in the health domain and allows users to build predictive models with their own data.

Abstract

An estimated 180 papers focusing on deep learning and EHR were published between 2010 and 2018. Despite the common workflow structure appearing in these publications, no trusted and verified software framework exists, forcing researchers to arduously repeat previous work. In this paper, we propose Cardea, an extensible open-source automated machine learning framework encapsulating common prediction problems in the health domain and allows users to build predictive models with their own data. This system relies on two components: Fast Healthcare Interoperability Resources (FHIR) – a standardized data structure for electronic health systems – and several AU TOML frameworks for automated feature engineering, model selection, and tuning. We augment these components with an adaptive data assembler and comprehensive data- and modelauditing capabilities. We demonstrate our framework via 5 prediction tasks on MIMIC-III and KAGGLE datasets, which highlight Cardea’s human competitiveness, flexibility in problem definition, extensive feature generation capability, adaptable automatic data assembler, and its usability.

Authors

K. Veeramachaneni

7 papers

Sarah Alnegheimish

2 papers

Najat Alrashed

1 papers

References37 items

A Robust Framework for Accelerated Outcome-driven Risk Factor Identification from EHR

MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

Multi-Task Learning with Incomplete Data for Healthcare

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

Cardea: An Open Automated Machine Learning Framework for Electronic Health Records

Published in

International Conference on Data Science and Ad...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

K. Veeramachaneni

7 papers

Sarah Alnegheimish

2 papers

Najat Alrashed

1 papers

References37 items

A Robust Framework for Accelerated Outcome-driven Risk Factor Identification from EHR

MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

Multi-Task Learning with Incomplete Data for Healthcare

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

Faisal Aleissa

1 papers

Shahad Althobaiti

1 papers

Mansour Alsaleh

1 papers

Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU

Scalable and accurate deep learning with electronic health records

Predicting Annual Length-Of-Stay and its Impact on Health

Automatic Classification of Critical Findings in Radiology Reports

Modeling Patient No-Show History and Predicting Future Outpatient Appointment Behavior in the Veterans Health Administration.

Unplanned readmissions within 30 days after discharge: improving quality through easy prediction.

Intelligent mortality reporting with FHIR

Label, Segment, Featurize: A Cross Domain Framework for Prediction Engineering

Risk Prediction with Electronic Health Records: A Deep Learning Approach

SMART on FHIR: a standards-based, interoperable apps platform for electronic health records

Deep feature synthesis: Towards automating data science endeavors

Efficient and Robust Automated Machine Learning

Simultaneous Modeling of Multiple Diseases for Mortality Prediction in Acute Hospital Care

A comparison of models for predicting early hospital readmissions

Hyperopt: a Python library for model selection and hyperparameter optimization

Personalized Mortality Prediction Driven by Electronic Medical Data and a Patient Similarity Metric

Using FHIR to develop a healthcare mobile application

Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures

Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms

Practical Bayesian Optimization of Machine Learning Algorithms

Risk prediction models: II. External validation, model updating, and impact assessment

Sequential Model-Based Optimization for General Algorithm Configuration

Mortality prediction model using data from the Hospital Information System.

Length of Stay Predictions: Improvements Through the Use of Automated Laboratory and Comorbidity Variables

Clinical Prediction Models

Automating machine learning

Clinical Predictive Modeling Development and Deployment through FHIR Web Services

Towards Standardized Patient Data Exchange: Integrating a FHIR Based API for the Open Medical Record System

Algorithms for hyperparameter optimization

Computational healthcare

What works in readmissions reduction

Field of Study

Computer ScienceMathematics

Journal Information

Name

2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA)

Page

579-588

Venue Information

Name

International Conference on Data Science and Advanced Analytics

Type

conference

URL

N/A

Alternate Names

Int Conf Data Sci Adv Anal
IEEE International Conference on Data Science and Advanced Analytics
IEEE Int Conf Data Sci Adv Anal
DSAA

TL;DR

Abstract

Authors

References37 items

A Robust Framework for Accelerated Outcome-driven Risk Factor Identification from EHR

MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

Multi-Task Learning with Incomplete Data for Healthcare

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

TL;DR

Abstract

Authors

References37 items

A Robust Framework for Accelerated Outcome-driven Risk Factor Identification from EHR

MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

Multi-Task Learning with Incomplete Data for Healthcare

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU

Scalable and accurate deep learning with electronic health records

Predicting Annual Length-Of-Stay and its Impact on Health

Automatic Classification of Critical Findings in Radiology Reports

Modeling Patient No-Show History and Predicting Future Outpatient Appointment Behavior in the Veterans Health Administration.

Unplanned readmissions within 30 days after discharge: improving quality through easy prediction.

Intelligent mortality reporting with FHIR

Label, Segment, Featurize: A Cross Domain Framework for Prediction Engineering

Risk Prediction with Electronic Health Records: A Deep Learning Approach

SMART on FHIR: a standards-based, interoperable apps platform for electronic health records

Deep feature synthesis: Towards automating data science endeavors

Efficient and Robust Automated Machine Learning

Simultaneous Modeling of Multiple Diseases for Mortality Prediction in Acute Hospital Care

A comparison of models for predicting early hospital readmissions

Hyperopt: a Python library for model selection and hyperparameter optimization

Personalized Mortality Prediction Driven by Electronic Medical Data and a Patient Similarity Metric

Using FHIR to develop a healthcare mobile application

Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures

Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms

Practical Bayesian Optimization of Machine Learning Algorithms

Risk prediction models: II. External validation, model updating, and impact assessment

Sequential Model-Based Optimization for General Algorithm Configuration

Mortality prediction model using data from the Hospital Information System.

Length of Stay Predictions: Improvements Through the Use of Automated Laboratory and Comorbidity Variables

Clinical Prediction Models

Automating machine learning

Clinical Predictive Modeling Development and Deployment through FHIR Web Services

Towards Standardized Patient Data Exchange: Integrating a FHIR Based API for the Open Medical Record System

Algorithms for hyperparameter optimization

Kaggle

Computational healthcare

What works in readmissions reduction

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names