Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics

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

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

12 Citations (Scopus)

Abstract

Electronic Health Records (EHRs) contain a wealth of information about an individual patient's diagnosis, treatment and health outcomes. This information can be leveraged effectively to identify patients who are similar to each for disease diagnosis and prognosis. In recent years, several machine learning methods <sup>1</sup> have been proposed to assessing patient similarity, although the techniques have primarily focused on the use of patient diagnoses data from EHRs for the learning task. In this study, we develop a multidimensional patient similarity assessment technique that leverages multiple types of information from the EHR and predicts a medication plan for each new patient based on prior knowledge and data from similar patients. In our algorithm, patients have been clustered into different groups using a hierarchical clustering approach and subsequently have been assigned a medication plan based on the similarity index to the overall patient population. We evaluated the performance of our approach on a cohort of heart failure patients (N=1386) identified from EHR data at Mayo Clinic and achieved an AUC of 0.74. Our results suggest that it is feasible to harness population-based information from EHRs for an individual patient-specific assessment.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
PublisherIOS Press
Pages369-373
Number of pages5
Volume210
ISBN (Print)9781614995111
DOIs
StatePublished - 2015
Event26th Medical Informatics in Europe Conference, MIE 2015 - Madrid, Spain
Duration: May 27 2015May 29 2015

Other

Other26th Medical Informatics in Europe Conference, MIE 2015
CountrySpain
CityMadrid
Period5/27/155/29/15

Fingerprint

Electronic Health Records
Heart Failure
Health
Therapeutics
Learning systems
Population
Area Under Curve
Cluster Analysis
Learning

Keywords

  • electronic health records
  • heart failure
  • patient similarity

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 for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics. In Studies in Health Technology and Informatics (Vol. 210, pp. 369-373). IOS Press. https://doi.org/10.3233/978-1-61499-512-8-369

Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics. / Panahiazar, Maryam; Taslimitehrani, Vahid; Pereira, Naveen Luke; Pathak, Jyotishman.

Studies in Health Technology and Informatics. Vol. 210 IOS Press, 2015. p. 369-373.

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

Panahiazar, M, Taslimitehrani, V, Pereira, NL & Pathak, J 2015, Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics. in Studies in Health Technology and Informatics. vol. 210, IOS Press, pp. 369-373, 26th Medical Informatics in Europe Conference, MIE 2015, Madrid, Spain, 5/27/15. https://doi.org/10.3233/978-1-61499-512-8-369
Panahiazar M, Taslimitehrani V, Pereira NL, Pathak J. Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics. In Studies in Health Technology and Informatics. Vol. 210. IOS Press. 2015. p. 369-373 https://doi.org/10.3233/978-1-61499-512-8-369
Panahiazar, Maryam ; Taslimitehrani, Vahid ; Pereira, Naveen Luke ; Pathak, Jyotishman. / Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics. Studies in Health Technology and Informatics. Vol. 210 IOS Press, 2015. pp. 369-373
@inproceedings{16228412f5b942a691c0f3f77a477e35,
title = "Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics",
abstract = "Electronic Health Records (EHRs) contain a wealth of information about an individual patient's diagnosis, treatment and health outcomes. This information can be leveraged effectively to identify patients who are similar to each for disease diagnosis and prognosis. In recent years, several machine learning methods 1 have been proposed to assessing patient similarity, although the techniques have primarily focused on the use of patient diagnoses data from EHRs for the learning task. In this study, we develop a multidimensional patient similarity assessment technique that leverages multiple types of information from the EHR and predicts a medication plan for each new patient based on prior knowledge and data from similar patients. In our algorithm, patients have been clustered into different groups using a hierarchical clustering approach and subsequently have been assigned a medication plan based on the similarity index to the overall patient population. We evaluated the performance of our approach on a cohort of heart failure patients (N=1386) identified from EHR data at Mayo Clinic and achieved an AUC of 0.74. Our results suggest that it is feasible to harness population-based information from EHRs for an individual patient-specific assessment.",
keywords = "electronic health records, heart failure, patient similarity",
author = "Maryam Panahiazar and Vahid Taslimitehrani and Pereira, {Naveen Luke} and Jyotishman Pathak",
year = "2015",
doi = "10.3233/978-1-61499-512-8-369",
language = "English (US)",
isbn = "9781614995111",
volume = "210",
pages = "369--373",
booktitle = "Studies in Health Technology and Informatics",
publisher = "IOS Press",

}

TY - GEN

T1 - Using EHRs for Heart Failure Therapy Recommendation Using Multidimensional Patient Similarity Analytics

AU - Panahiazar, Maryam

AU - Taslimitehrani, Vahid

AU - Pereira, Naveen Luke

AU - Pathak, Jyotishman

PY - 2015

Y1 - 2015

N2 - Electronic Health Records (EHRs) contain a wealth of information about an individual patient's diagnosis, treatment and health outcomes. This information can be leveraged effectively to identify patients who are similar to each for disease diagnosis and prognosis. In recent years, several machine learning methods 1 have been proposed to assessing patient similarity, although the techniques have primarily focused on the use of patient diagnoses data from EHRs for the learning task. In this study, we develop a multidimensional patient similarity assessment technique that leverages multiple types of information from the EHR and predicts a medication plan for each new patient based on prior knowledge and data from similar patients. In our algorithm, patients have been clustered into different groups using a hierarchical clustering approach and subsequently have been assigned a medication plan based on the similarity index to the overall patient population. We evaluated the performance of our approach on a cohort of heart failure patients (N=1386) identified from EHR data at Mayo Clinic and achieved an AUC of 0.74. Our results suggest that it is feasible to harness population-based information from EHRs for an individual patient-specific assessment.

AB - Electronic Health Records (EHRs) contain a wealth of information about an individual patient's diagnosis, treatment and health outcomes. This information can be leveraged effectively to identify patients who are similar to each for disease diagnosis and prognosis. In recent years, several machine learning methods 1 have been proposed to assessing patient similarity, although the techniques have primarily focused on the use of patient diagnoses data from EHRs for the learning task. In this study, we develop a multidimensional patient similarity assessment technique that leverages multiple types of information from the EHR and predicts a medication plan for each new patient based on prior knowledge and data from similar patients. In our algorithm, patients have been clustered into different groups using a hierarchical clustering approach and subsequently have been assigned a medication plan based on the similarity index to the overall patient population. We evaluated the performance of our approach on a cohort of heart failure patients (N=1386) identified from EHR data at Mayo Clinic and achieved an AUC of 0.74. Our results suggest that it is feasible to harness population-based information from EHRs for an individual patient-specific assessment.

KW - electronic health records

KW - heart failure

KW - patient similarity

UR - http://www.scopus.com/inward/record.url?scp=84937422357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937422357&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-512-8-369

DO - 10.3233/978-1-61499-512-8-369

M3 - Conference contribution

C2 - 25991168

AN - SCOPUS:84937422357

SN - 9781614995111

VL - 210

SP - 369

EP - 373

BT - Studies in Health Technology and Informatics

PB - IOS Press

ER -