Modeling heart procedures from EHRs: An application of exponential families

Shuo Yang, Fabian Hadiji, Kristian Kersting, Shaun Grannis, Sriraam Natarajan

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

Abstract

In order to facilitate better estimations on coronary artery disease conditions of a patient, we aim to predict the number of Angioplasty (a coronary artery procedure) by taking into account all the information from his/her Electronic Health Record (EHR) data. For this purpose, two exponential family members - multinomial distribution and Poisson distribution models - are considered, which treat the target variable as categorical-valued and count-valued respectively. From the perspective of exponential family, we derive the functional gradient boosting approach for these two distributions and analyze their assumptions with real EHR data. Our empirical results show that Poisson models appear to be more faithful for modeling the number of this procedure.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages491-497
Number of pages7
Volume2017-January
ISBN (Electronic)9781509030491
DOIs
StatePublished - Dec 15 2017
Externally publishedYes
Event2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 - Kansas City, United States
Duration: Nov 13 2017Nov 16 2017

Other

Other2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
CountryUnited States
CityKansas City
Period11/13/1711/16/17

Fingerprint

Electronic Health Records
Health
Poisson Distribution
Poisson distribution
Angioplasty
Coronary Artery Disease
Coronary Vessels

Keywords

  • clinical events prediction
  • EHR
  • exponential family
  • probabilistic models

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Yang, S., Hadiji, F., Kersting, K., Grannis, S., & Natarajan, S. (2017). Modeling heart procedures from EHRs: An application of exponential families. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 (Vol. 2017-January, pp. 491-497). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2017.8217696

Modeling heart procedures from EHRs : An application of exponential families. / Yang, Shuo; Hadiji, Fabian; Kersting, Kristian; Grannis, Shaun; Natarajan, Sriraam.

Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 491-497.

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

Yang, S, Hadiji, F, Kersting, K, Grannis, S & Natarajan, S 2017, Modeling heart procedures from EHRs: An application of exponential families. in Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 491-497, 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017, Kansas City, United States, 11/13/17. https://doi.org/10.1109/BIBM.2017.8217696
Yang S, Hadiji F, Kersting K, Grannis S, Natarajan S. Modeling heart procedures from EHRs: An application of exponential families. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 491-497 https://doi.org/10.1109/BIBM.2017.8217696
Yang, Shuo ; Hadiji, Fabian ; Kersting, Kristian ; Grannis, Shaun ; Natarajan, Sriraam. / Modeling heart procedures from EHRs : An application of exponential families. Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 491-497
@inproceedings{fa6082bd0a0a4bca9d03961ac566f6de,
title = "Modeling heart procedures from EHRs: An application of exponential families",
abstract = "In order to facilitate better estimations on coronary artery disease conditions of a patient, we aim to predict the number of Angioplasty (a coronary artery procedure) by taking into account all the information from his/her Electronic Health Record (EHR) data. For this purpose, two exponential family members - multinomial distribution and Poisson distribution models - are considered, which treat the target variable as categorical-valued and count-valued respectively. From the perspective of exponential family, we derive the functional gradient boosting approach for these two distributions and analyze their assumptions with real EHR data. Our empirical results show that Poisson models appear to be more faithful for modeling the number of this procedure.",
keywords = "clinical events prediction, EHR, exponential family, probabilistic models",
author = "Shuo Yang and Fabian Hadiji and Kristian Kersting and Shaun Grannis and Sriraam Natarajan",
year = "2017",
month = "12",
day = "15",
doi = "10.1109/BIBM.2017.8217696",
language = "English (US)",
volume = "2017-January",
pages = "491--497",
booktitle = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Modeling heart procedures from EHRs

T2 - An application of exponential families

AU - Yang, Shuo

AU - Hadiji, Fabian

AU - Kersting, Kristian

AU - Grannis, Shaun

AU - Natarajan, Sriraam

PY - 2017/12/15

Y1 - 2017/12/15

N2 - In order to facilitate better estimations on coronary artery disease conditions of a patient, we aim to predict the number of Angioplasty (a coronary artery procedure) by taking into account all the information from his/her Electronic Health Record (EHR) data. For this purpose, two exponential family members - multinomial distribution and Poisson distribution models - are considered, which treat the target variable as categorical-valued and count-valued respectively. From the perspective of exponential family, we derive the functional gradient boosting approach for these two distributions and analyze their assumptions with real EHR data. Our empirical results show that Poisson models appear to be more faithful for modeling the number of this procedure.

AB - In order to facilitate better estimations on coronary artery disease conditions of a patient, we aim to predict the number of Angioplasty (a coronary artery procedure) by taking into account all the information from his/her Electronic Health Record (EHR) data. For this purpose, two exponential family members - multinomial distribution and Poisson distribution models - are considered, which treat the target variable as categorical-valued and count-valued respectively. From the perspective of exponential family, we derive the functional gradient boosting approach for these two distributions and analyze their assumptions with real EHR data. Our empirical results show that Poisson models appear to be more faithful for modeling the number of this procedure.

KW - clinical events prediction

KW - EHR

KW - exponential family

KW - probabilistic models

UR - http://www.scopus.com/inward/record.url?scp=85046282794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046282794&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2017.8217696

DO - 10.1109/BIBM.2017.8217696

M3 - Conference contribution

AN - SCOPUS:85046282794

VL - 2017-January

SP - 491

EP - 497

BT - Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -