Using EHRs and Machine Learning for Heart Failure Survival Analysis

Maryam Panahiazar, Vahid Taslimitehrani, Naveen Luke Pereira, Jyotishman Pathak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

'Heart failure (HF) is a frequent health problem with high morbidity and mortality, increasing prevalence and escalating healthcare costs' [1]. By calculating a HF survival risk score based on patient-specific characteristics from Electronic Health Records (EHRs), we can identify high-risk patients and apply individualized treatment and healthy living choices to potentially reduce their mortality risk. The Seattle Heart Failure Model (SHFM) is one of the most popular models to calculate HF survival risk that uses multiple clinical variables to predict HF prognosis and also incorporates impact of HF therapy on patient outcomes. Although the SHFM has been validated across multiple cohorts [1-5], these studies were primarily done using clinical trials databases that do not reflect routine clinical care in the community. Further, the impact of contemporary therapeutic interventions, such as beta-blockers or defibrillators, was incorporated in SHFM by extrapolation from external trials. In this study, we assess the performance of SHFM using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techiniques that applies routine clinical care data. Our results shows the models which were built using EHR data are more accurate (11% improvement in AUC) with the convenience of being more readily applicable in routine clinical care. Furthermore, we demonstrate that new predictive markers (such as co-morbidities) when incorporated into our models improve prognostic performance significantly (8% improvement in AUC).

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
PublisherIOS Press
Pages40-44
Number of pages5
Volume216
ISBN (Print)9781614995630
DOIs
StatePublished - 2015
Event15th World Congress on Health and Biomedical Informatics, MEDINFO 2015 - Sao Paulo, Brazil
Duration: Aug 19 2015Aug 23 2015

Publication series

NameStudies in Health Technology and Informatics
Volume216
ISSN (Print)09269630
ISSN (Electronic)18798365

Other

Other15th World Congress on Health and Biomedical Informatics, MEDINFO 2015
CountryBrazil
CitySao Paulo
Period8/19/158/23/15

Fingerprint

Electronic Health Records
Survival Analysis
Failure analysis
Learning systems
Heart Failure
Health
Area Under Curve
Defibrillators
Morbidity
Machine Learning
Survival
Mortality
Medical problems
Extrapolation
Health Care Costs
Therapeutics
Clinical Trials
Databases

Keywords

  • Electronic Health Records
  • Heart Failure
  • Machine Learning
  • Survival Score

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Panahiazar, M., Taslimitehrani, V., Pereira, N. L., & Pathak, J. (2015). Using EHRs and Machine Learning for Heart Failure Survival Analysis. In Studies in Health Technology and Informatics (Vol. 216, pp. 40-44). (Studies in Health Technology and Informatics; Vol. 216). IOS Press. https://doi.org/10.3233/978-1-61499-564-7-40

Using EHRs and Machine Learning for Heart Failure Survival Analysis. / Panahiazar, Maryam; Taslimitehrani, Vahid; Pereira, Naveen Luke; Pathak, Jyotishman.

Studies in Health Technology and Informatics. Vol. 216 IOS Press, 2015. p. 40-44 (Studies in Health Technology and Informatics; Vol. 216).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Panahiazar, M, Taslimitehrani, V, Pereira, NL & Pathak, J 2015, Using EHRs and Machine Learning for Heart Failure Survival Analysis. in Studies in Health Technology and Informatics. vol. 216, Studies in Health Technology and Informatics, vol. 216, IOS Press, pp. 40-44, 15th World Congress on Health and Biomedical Informatics, MEDINFO 2015, Sao Paulo, Brazil, 8/19/15. https://doi.org/10.3233/978-1-61499-564-7-40
Panahiazar M, Taslimitehrani V, Pereira NL, Pathak J. Using EHRs and Machine Learning for Heart Failure Survival Analysis. In Studies in Health Technology and Informatics. Vol. 216. IOS Press. 2015. p. 40-44. (Studies in Health Technology and Informatics). https://doi.org/10.3233/978-1-61499-564-7-40
Panahiazar, Maryam ; Taslimitehrani, Vahid ; Pereira, Naveen Luke ; Pathak, Jyotishman. / Using EHRs and Machine Learning for Heart Failure Survival Analysis. Studies in Health Technology and Informatics. Vol. 216 IOS Press, 2015. pp. 40-44 (Studies in Health Technology and Informatics).
@inproceedings{411884d544514f238fd5bad695e184fa,
title = "Using EHRs and Machine Learning for Heart Failure Survival Analysis",
abstract = "'Heart failure (HF) is a frequent health problem with high morbidity and mortality, increasing prevalence and escalating healthcare costs' [1]. By calculating a HF survival risk score based on patient-specific characteristics from Electronic Health Records (EHRs), we can identify high-risk patients and apply individualized treatment and healthy living choices to potentially reduce their mortality risk. The Seattle Heart Failure Model (SHFM) is one of the most popular models to calculate HF survival risk that uses multiple clinical variables to predict HF prognosis and also incorporates impact of HF therapy on patient outcomes. Although the SHFM has been validated across multiple cohorts [1-5], these studies were primarily done using clinical trials databases that do not reflect routine clinical care in the community. Further, the impact of contemporary therapeutic interventions, such as beta-blockers or defibrillators, was incorporated in SHFM by extrapolation from external trials. In this study, we assess the performance of SHFM using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techiniques that applies routine clinical care data. Our results shows the models which were built using EHR data are more accurate (11{\%} improvement in AUC) with the convenience of being more readily applicable in routine clinical care. Furthermore, we demonstrate that new predictive markers (such as co-morbidities) when incorporated into our models improve prognostic performance significantly (8{\%} improvement in AUC).",
keywords = "Electronic Health Records, Heart Failure, Machine Learning, Survival Score",
author = "Maryam Panahiazar and Vahid Taslimitehrani and Pereira, {Naveen Luke} and Jyotishman Pathak",
year = "2015",
doi = "10.3233/978-1-61499-564-7-40",
language = "English (US)",
isbn = "9781614995630",
volume = "216",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "40--44",
booktitle = "Studies in Health Technology and Informatics",

}

TY - GEN

T1 - Using EHRs and Machine Learning for Heart Failure Survival Analysis

AU - Panahiazar, Maryam

AU - Taslimitehrani, Vahid

AU - Pereira, Naveen Luke

AU - Pathak, Jyotishman

PY - 2015

Y1 - 2015

N2 - 'Heart failure (HF) is a frequent health problem with high morbidity and mortality, increasing prevalence and escalating healthcare costs' [1]. By calculating a HF survival risk score based on patient-specific characteristics from Electronic Health Records (EHRs), we can identify high-risk patients and apply individualized treatment and healthy living choices to potentially reduce their mortality risk. The Seattle Heart Failure Model (SHFM) is one of the most popular models to calculate HF survival risk that uses multiple clinical variables to predict HF prognosis and also incorporates impact of HF therapy on patient outcomes. Although the SHFM has been validated across multiple cohorts [1-5], these studies were primarily done using clinical trials databases that do not reflect routine clinical care in the community. Further, the impact of contemporary therapeutic interventions, such as beta-blockers or defibrillators, was incorporated in SHFM by extrapolation from external trials. In this study, we assess the performance of SHFM using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techiniques that applies routine clinical care data. Our results shows the models which were built using EHR data are more accurate (11% improvement in AUC) with the convenience of being more readily applicable in routine clinical care. Furthermore, we demonstrate that new predictive markers (such as co-morbidities) when incorporated into our models improve prognostic performance significantly (8% improvement in AUC).

AB - 'Heart failure (HF) is a frequent health problem with high morbidity and mortality, increasing prevalence and escalating healthcare costs' [1]. By calculating a HF survival risk score based on patient-specific characteristics from Electronic Health Records (EHRs), we can identify high-risk patients and apply individualized treatment and healthy living choices to potentially reduce their mortality risk. The Seattle Heart Failure Model (SHFM) is one of the most popular models to calculate HF survival risk that uses multiple clinical variables to predict HF prognosis and also incorporates impact of HF therapy on patient outcomes. Although the SHFM has been validated across multiple cohorts [1-5], these studies were primarily done using clinical trials databases that do not reflect routine clinical care in the community. Further, the impact of contemporary therapeutic interventions, such as beta-blockers or defibrillators, was incorporated in SHFM by extrapolation from external trials. In this study, we assess the performance of SHFM using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techiniques that applies routine clinical care data. Our results shows the models which were built using EHR data are more accurate (11% improvement in AUC) with the convenience of being more readily applicable in routine clinical care. Furthermore, we demonstrate that new predictive markers (such as co-morbidities) when incorporated into our models improve prognostic performance significantly (8% improvement in AUC).

KW - Electronic Health Records

KW - Heart Failure

KW - Machine Learning

KW - Survival Score

UR - http://www.scopus.com/inward/record.url?scp=84952006219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952006219&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-564-7-40

DO - 10.3233/978-1-61499-564-7-40

M3 - Conference contribution

C2 - 26262006

AN - SCOPUS:84952006219

SN - 9781614995630

VL - 216

T3 - Studies in Health Technology and Informatics

SP - 40

EP - 44

BT - Studies in Health Technology and Informatics

PB - IOS Press

ER -