Literature DB >> 25048351

Relational machine learning for electronic health record-driven phenotyping.

Peggy L Peissig1, Vitor Santos Costa2, Michael D Caldwell3, Carla Rottscheit4, Richard L Berg4, Eneida A Mendonca5, David Page6.   

Abstract

OBJECTIVE: Electronic health records (EHR) offer medical and pharmacogenomics research unprecedented opportunities to identify and classify patients at risk. EHRs are collections of highly inter-dependent records that include biological, anatomical, physiological, and behavioral observations. They comprise a patient's clinical phenome, where each patient has thousands of date-stamped records distributed across many relational tables. Development of EHR computer-based phenotyping algorithms require time and medical insight from clinical experts, who most often can only review a small patient subset representative of the total EHR records, to identify phenotype features. In this research we evaluate whether relational machine learning (ML) using inductive logic programming (ILP) can contribute to addressing these issues as a viable approach for EHR-based phenotyping.
METHODS: Two relational learning ILP approaches and three well-known WEKA (Waikato Environment for Knowledge Analysis) implementations of non-relational approaches (PART, J48, and JRIP) were used to develop models for nine phenotypes. International Classification of Diseases, Ninth Revision (ICD-9) coded EHR data were used to select training cohorts for the development of each phenotypic model. Accuracy, precision, recall, F-Measure, and Area Under the Receiver Operating Characteristic (AUROC) curve statistics were measured for each phenotypic model based on independent manually verified test cohorts. A two-sided binomial distribution test (sign test) compared the five ML approaches across phenotypes for statistical significance.
RESULTS: We developed an approach to automatically label training examples using ICD-9 diagnosis codes for the ML approaches being evaluated. Nine phenotypic models for each ML approach were evaluated, resulting in better overall model performance in AUROC using ILP when compared to PART (p=0.039), J48 (p=0.003) and JRIP (p=0.003). DISCUSSION: ILP has the potential to improve phenotyping by independently delivering clinically expert interpretable rules for phenotype definitions, or intuitive phenotypes to assist experts.
CONCLUSION: Relational learning using ILP offers a viable approach to EHR-driven phenotyping.
Copyright © 2014 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Electronic health record; Inductive logic programming; Machine learning; Phenotyping; Relational machine learning

Mesh:

Year:  2014        PMID: 25048351      PMCID: PMC4261015          DOI: 10.1016/j.jbi.2014.07.007

Source DB:  PubMed          Journal:  J Biomed Inform        ISSN: 1532-0464            Impact factor:   6.317


  31 in total

1.  Electronic health record use and the quality of ambulatory care in the United States.

Authors:  Jeffrey A Linder; Jun Ma; David W Bates; Blackford Middleton; Randall S Stafford
Journal:  Arch Intern Med       Date:  2007-07-09

2.  Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches.

Authors:  Jionglin Wu; Jason Roy; Walter F Stewart
Journal:  Med Care       Date:  2010-06       Impact factor: 2.983

3.  Pharmacogenomics: the importance of accurate phenotypes.

Authors:  David Gurwitz; Munir Pirmohamed
Journal:  Pharmacogenomics       Date:  2010-04       Impact factor: 2.533

4.  The case-crossover design: a method for studying transient effects on the risk of acute events.

Authors:  M Maclure
Journal:  Am J Epidemiol       Date:  1991-01-15       Impact factor: 4.897

5.  Electronic medical records for clinical research: application to the identification of heart failure.

Authors:  Serguei Pakhomov; Susan A Weston; Steven J Jacobsen; Christopher G Chute; Ryan Meverden; Véronique L Roger
Journal:  Am J Manag Care       Date:  2007-06       Impact factor: 2.229

6.  Identifying Adverse Drug Events by Relational Learning.

Authors:  David Page; Vítor Santos Costa; Sriraam Natarajan; Aubrey Barnard; Peggy Peissig; Michael Caldwell
Journal:  Proc Conf AAAI Artif Intell       Date:  2012-07

7.  Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network.

Authors:  Katherine M Newton; Peggy L Peissig; Abel Ngo Kho; Suzette J Bielinski; Richard L Berg; Vidhu Choudhary; Melissa Basford; Christopher G Chute; Iftikhar J Kullo; Rongling Li; Jennifer A Pacheco; Luke V Rasmussen; Leslie Spangler; Joshua C Denny
Journal:  J Am Med Inform Assoc       Date:  2013-03-26       Impact factor: 4.497

8.  Naïve Electronic Health Record phenotype identification for Rheumatoid arthritis.

Authors:  Robert J Carroll; Anne E Eyler; Joshua C Denny
Journal:  AMIA Annu Symp Proc       Date:  2011-10-22

9.  Demand-Driven Clustering in Relational Domains for Predicting Adverse Drug Events.

Authors:  Jesse Davis; Vítor Santos Costa; Peggy Peissig; Michael Caldwell; Elizabeth Berg; David Page
Journal:  Proc Int Conf Mach Learn       Date:  2012

10.  Detecting new neurodegenerative disease genes: does phenotype accuracy limit the horizon?

Authors:  David C Samuels; David J Burn; Patrick F Chinnery
Journal:  Trends Genet       Date:  2009-10-12       Impact factor: 11.639

View more
  24 in total

1.  Using Electronic Health Records To Generate Phenotypes For Research.

Authors:  Sarah A Pendergrass; Dana C Crawford
Journal:  Curr Protoc Hum Genet       Date:  2018-12-05

2.  Building bridges across electronic health record systems through inferred phenotypic topics.

Authors:  You Chen; Joydeep Ghosh; Cosmin Adrian Bejan; Carl A Gunter; Siddharth Gupta; Abel Kho; David Liebovitz; Jimeng Sun; Joshua Denny; Bradley Malin
Journal:  J Biomed Inform       Date:  2015-04-01       Impact factor: 6.317

3.  A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop.

Authors:  Curtis P Langlotz; Bibb Allen; Bradley J Erickson; Jayashree Kalpathy-Cramer; Keith Bigelow; Tessa S Cook; Adam E Flanders; Matthew P Lungren; David S Mendelson; Jeffrey D Rudie; Ge Wang; Krishna Kandarpa
Journal:  Radiology       Date:  2019-04-16       Impact factor: 11.105

Review 4.  Big Data Science: Opportunities and Challenges to Address Minority Health and Health Disparities in the 21st Century.

Authors:  Xinzhi Zhang; Eliseo J Pérez-Stable; Philip E Bourne; Emmanuel Peprah; O Kenrik Duru; Nancy Breen; David Berrigan; Fred Wood; James S Jackson; David W S Wong; Joshua Denny
Journal:  Ethn Dis       Date:  2017-04-20       Impact factor: 1.847

Review 5.  Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress.

Authors:  S M Meystre; C Lovis; T Bürkle; G Tognola; A Budrionis; C U Lehmann
Journal:  Yearb Med Inform       Date:  2017-09-11

6.  PheKB: a catalog and workflow for creating electronic phenotype algorithms for transportability.

Authors:  Jacqueline C Kirby; Peter Speltz; Luke V Rasmussen; Melissa Basford; Omri Gottesman; Peggy L Peissig; Jennifer A Pacheco; Gerard Tromp; Jyotishman Pathak; David S Carrell; Stephen B Ellis; Todd Lingren; Will K Thompson; Guergana Savova; Jonathan Haines; Dan M Roden; Paul A Harris; Joshua C Denny
Journal:  J Am Med Inform Assoc       Date:  2016-03-28       Impact factor: 4.497

7.  Learning statistical models of phenotypes using noisy labeled training data.

Authors:  Vibhu Agarwal; Tanya Podchiyska; Juan M Banda; Veena Goel; Tiffany I Leung; Evan P Minty; Timothy E Sweeney; Elsie Gyang; Nigam H Shah
Journal:  J Am Med Inform Assoc       Date:  2016-05-12       Impact factor: 4.497

Review 8.  Overview of the First Natural Language Processing Challenge for Extracting Medication, Indication, and Adverse Drug Events from Electronic Health Record Notes (MADE 1.0).

Authors:  Abhyuday Jagannatha; Feifan Liu; Weisong Liu; Hong Yu
Journal:  Drug Saf       Date:  2019-01       Impact factor: 5.606

9.  Intelligent Perioperative System: Towards Real-time Big Data Analytics in Surgery Risk Assessment.

Authors:  Zheng Feng; Rajendra Rana Bhat; Xiaoyong Yuan; Daniel Freeman; Tezcan Baslanti; Azra Bihorac; Xiaolin Li
Journal:  DASC PICom DataCom CyberSciTech 2017 (2017)       Date:  2017-11

10.  Comparison of the cohort selection performance of Australian Medicines Terminology to Anatomical Therapeutic Chemical mappings.

Authors:  Guan N Guo; Jitendra Jonnagaddala; Sanjay Farshid; Vojtech Huser; Christian Reich; Siaw-Teng Liaw
Journal:  J Am Med Inform Assoc       Date:  2019-11-01       Impact factor: 4.497

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.