Temporal reflected logistic regression for probabilistic heart failure survival score prediction

Mingjie Qian, Jyotishman Pathak, Naveen Luke Pereira, Chengxiang Zhai

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

Abstract

Heart failure (HF) has a highly variable annual mortality rate and there is an urgent need of determining patient prognosis to enable informed decision-making about heart failure treatment strategies. Existing survival risk prediction models either require features that limit their applicability or pose difficulties for parameter estimation as physicians have to use a limited set of variables with known hazard ratios published in literature. We propose a new model to predict the probabilistic survival score after HF diagnosis based on all clinical variables derived from the electronic health record (EHR). We formalize the parameter estimation problem by using the maximum likelihood estimation (MLE) principle and devise an effective and efficient algorithm to solve the optimization problem. Experimental results using EHR data of 234 HF patients validate the superiority of this new model in predicting prognosis over the currently used Seattle Heart Failure Model.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages410-416
Number of pages7
Volume2017-January
ISBN (Electronic)9781509030491
DOIs
StatePublished - Dec 15 2017
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

Logistics
Heart Failure
Logistic Models
Survival
Electronic Health Records
Parameter estimation
Health
Maximum likelihood estimation
Decision Making
Hazards
Decision making
Physicians
Mortality
Therapeutics

Keywords

  • Electronic Health Records
  • Heart Failure (HF) Survival Score Prediction
  • Logistic Regression
  • Temporal Models

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Qian, M., Pathak, J., Pereira, N. L., & Zhai, C. (2017). Temporal reflected logistic regression for probabilistic heart failure survival score prediction. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 (Vol. 2017-January, pp. 410-416). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2017.8217684

Temporal reflected logistic regression for probabilistic heart failure survival score prediction. / Qian, Mingjie; Pathak, Jyotishman; Pereira, Naveen Luke; Zhai, Chengxiang.

Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 410-416.

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

Qian, M, Pathak, J, Pereira, NL & Zhai, C 2017, Temporal reflected logistic regression for probabilistic heart failure survival score prediction. in Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 410-416, 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017, Kansas City, United States, 11/13/17. https://doi.org/10.1109/BIBM.2017.8217684
Qian M, Pathak J, Pereira NL, Zhai C. Temporal reflected logistic regression for probabilistic heart failure survival score prediction. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 410-416 https://doi.org/10.1109/BIBM.2017.8217684
Qian, Mingjie ; Pathak, Jyotishman ; Pereira, Naveen Luke ; Zhai, Chengxiang. / Temporal reflected logistic regression for probabilistic heart failure survival score prediction. Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 410-416
@inproceedings{d605a63cb1a64705ab016878eaf9b275,
title = "Temporal reflected logistic regression for probabilistic heart failure survival score prediction",
abstract = "Heart failure (HF) has a highly variable annual mortality rate and there is an urgent need of determining patient prognosis to enable informed decision-making about heart failure treatment strategies. Existing survival risk prediction models either require features that limit their applicability or pose difficulties for parameter estimation as physicians have to use a limited set of variables with known hazard ratios published in literature. We propose a new model to predict the probabilistic survival score after HF diagnosis based on all clinical variables derived from the electronic health record (EHR). We formalize the parameter estimation problem by using the maximum likelihood estimation (MLE) principle and devise an effective and efficient algorithm to solve the optimization problem. Experimental results using EHR data of 234 HF patients validate the superiority of this new model in predicting prognosis over the currently used Seattle Heart Failure Model.",
keywords = "Electronic Health Records, Heart Failure (HF) Survival Score Prediction, Logistic Regression, Temporal Models",
author = "Mingjie Qian and Jyotishman Pathak and Pereira, {Naveen Luke} and Chengxiang Zhai",
year = "2017",
month = "12",
day = "15",
doi = "10.1109/BIBM.2017.8217684",
language = "English (US)",
volume = "2017-January",
pages = "410--416",
booktitle = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Temporal reflected logistic regression for probabilistic heart failure survival score prediction

AU - Qian, Mingjie

AU - Pathak, Jyotishman

AU - Pereira, Naveen Luke

AU - Zhai, Chengxiang

PY - 2017/12/15

Y1 - 2017/12/15

N2 - Heart failure (HF) has a highly variable annual mortality rate and there is an urgent need of determining patient prognosis to enable informed decision-making about heart failure treatment strategies. Existing survival risk prediction models either require features that limit their applicability or pose difficulties for parameter estimation as physicians have to use a limited set of variables with known hazard ratios published in literature. We propose a new model to predict the probabilistic survival score after HF diagnosis based on all clinical variables derived from the electronic health record (EHR). We formalize the parameter estimation problem by using the maximum likelihood estimation (MLE) principle and devise an effective and efficient algorithm to solve the optimization problem. Experimental results using EHR data of 234 HF patients validate the superiority of this new model in predicting prognosis over the currently used Seattle Heart Failure Model.

AB - Heart failure (HF) has a highly variable annual mortality rate and there is an urgent need of determining patient prognosis to enable informed decision-making about heart failure treatment strategies. Existing survival risk prediction models either require features that limit their applicability or pose difficulties for parameter estimation as physicians have to use a limited set of variables with known hazard ratios published in literature. We propose a new model to predict the probabilistic survival score after HF diagnosis based on all clinical variables derived from the electronic health record (EHR). We formalize the parameter estimation problem by using the maximum likelihood estimation (MLE) principle and devise an effective and efficient algorithm to solve the optimization problem. Experimental results using EHR data of 234 HF patients validate the superiority of this new model in predicting prognosis over the currently used Seattle Heart Failure Model.

KW - Electronic Health Records

KW - Heart Failure (HF) Survival Score Prediction

KW - Logistic Regression

KW - Temporal Models

UR - http://www.scopus.com/inward/record.url?scp=85046262464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046262464&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2017.8217684

DO - 10.1109/BIBM.2017.8217684

M3 - Conference contribution

AN - SCOPUS:85046262464

VL - 2017-January

SP - 410

EP - 416

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -