Clinical decision making: A framework for predicting Rx response

Aarti Sathyanarayana, Jyotishman Pathak, Rozalina McCoy, Santiago Romero-Brufau, Maryam Panaziahar, Jaideep Srivastava

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

1 Citation (Scopus)

Abstract

Over seventy percent of Americans take at least one form of prescription medication, with twenty percent taking more than five. The numbers emphasize how important it is for clinicians to understand the effects of the medication and whether these medications are effective. In this paper we propose a data driven framework to predict the effectiveness of medication on a patient, specifically in the case of diabetes. Our dataset contains claims data from 1.5 million patients. A heuristic was established to evaluate the 'effectiveness' of Metformin using a set of three criteria. Decision trees and random forests were used to create prediction models on the training data and select features. The model was able to correctly predict whether a patient responded well to the medication with approximately 80% accuracy and an F1-measure of approximately 90%.

Original languageEnglish
Title of host publicationIEEE International Conference on Data Mining Workshops, ICDMW
PublisherIEEE Computer Society
Pages1185-1188
Number of pages4
Volume2015-January
EditionJanuary
DOIs
Publication statusPublished - 26 Jan 2015
Externally publishedYes
Event14th IEEE International Conference on Data Mining Workshops, ICDMW 2014 - Shenzhen, China
Duration: 14 Dec 2014 → …

Other

Other14th IEEE International Conference on Data Mining Workshops, ICDMW 2014
CountryChina
CityShenzhen
Period14/12/14 → …

Fingerprint

Decision making
Medical problems
Decision trees

Keywords

  • Decision support systems
  • electronic medical records
  • fuzzy logic
  • Medical information systems
  • predictive models
  • supervised learning
  • support vector machines

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Sathyanarayana, A., Pathak, J., McCoy, R., Romero-Brufau, S., Panaziahar, M., & Srivastava, J. (2015). Clinical decision making: A framework for predicting Rx response. In IEEE International Conference on Data Mining Workshops, ICDMW (January ed., Vol. 2015-January, pp. 1185-1188). [7022730] IEEE Computer Society. https://doi.org/10.1109/ICDMW.2014.154

Clinical decision making : A framework for predicting Rx response. / Sathyanarayana, Aarti; Pathak, Jyotishman; McCoy, Rozalina; Romero-Brufau, Santiago; Panaziahar, Maryam; Srivastava, Jaideep.

IEEE International Conference on Data Mining Workshops, ICDMW. Vol. 2015-January January. ed. IEEE Computer Society, 2015. p. 1185-1188 7022730.

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

Sathyanarayana, A, Pathak, J, McCoy, R, Romero-Brufau, S, Panaziahar, M & Srivastava, J 2015, Clinical decision making: A framework for predicting Rx response. in IEEE International Conference on Data Mining Workshops, ICDMW. January edn, vol. 2015-January, 7022730, IEEE Computer Society, pp. 1185-1188, 14th IEEE International Conference on Data Mining Workshops, ICDMW 2014, Shenzhen, China, 14/12/14. https://doi.org/10.1109/ICDMW.2014.154
Sathyanarayana A, Pathak J, McCoy R, Romero-Brufau S, Panaziahar M, Srivastava J. Clinical decision making: A framework for predicting Rx response. In IEEE International Conference on Data Mining Workshops, ICDMW. January ed. Vol. 2015-January. IEEE Computer Society. 2015. p. 1185-1188. 7022730 https://doi.org/10.1109/ICDMW.2014.154
Sathyanarayana, Aarti ; Pathak, Jyotishman ; McCoy, Rozalina ; Romero-Brufau, Santiago ; Panaziahar, Maryam ; Srivastava, Jaideep. / Clinical decision making : A framework for predicting Rx response. IEEE International Conference on Data Mining Workshops, ICDMW. Vol. 2015-January January. ed. IEEE Computer Society, 2015. pp. 1185-1188
@inproceedings{ce16fc585e6747c2baa38aadd2a5a2d5,
title = "Clinical decision making: A framework for predicting Rx response",
abstract = "Over seventy percent of Americans take at least one form of prescription medication, with twenty percent taking more than five. The numbers emphasize how important it is for clinicians to understand the effects of the medication and whether these medications are effective. In this paper we propose a data driven framework to predict the effectiveness of medication on a patient, specifically in the case of diabetes. Our dataset contains claims data from 1.5 million patients. A heuristic was established to evaluate the 'effectiveness' of Metformin using a set of three criteria. Decision trees and random forests were used to create prediction models on the training data and select features. The model was able to correctly predict whether a patient responded well to the medication with approximately 80{\%} accuracy and an F1-measure of approximately 90{\%}.",
keywords = "Decision support systems, electronic medical records, fuzzy logic, Medical information systems, predictive models, supervised learning, support vector machines",
author = "Aarti Sathyanarayana and Jyotishman Pathak and Rozalina McCoy and Santiago Romero-Brufau and Maryam Panaziahar and Jaideep Srivastava",
year = "2015",
month = "1",
day = "26",
doi = "10.1109/ICDMW.2014.154",
language = "English",
volume = "2015-January",
pages = "1185--1188",
booktitle = "IEEE International Conference on Data Mining Workshops, ICDMW",
publisher = "IEEE Computer Society",
edition = "January",

}

TY - GEN

T1 - Clinical decision making

T2 - A framework for predicting Rx response

AU - Sathyanarayana, Aarti

AU - Pathak, Jyotishman

AU - McCoy, Rozalina

AU - Romero-Brufau, Santiago

AU - Panaziahar, Maryam

AU - Srivastava, Jaideep

PY - 2015/1/26

Y1 - 2015/1/26

N2 - Over seventy percent of Americans take at least one form of prescription medication, with twenty percent taking more than five. The numbers emphasize how important it is for clinicians to understand the effects of the medication and whether these medications are effective. In this paper we propose a data driven framework to predict the effectiveness of medication on a patient, specifically in the case of diabetes. Our dataset contains claims data from 1.5 million patients. A heuristic was established to evaluate the 'effectiveness' of Metformin using a set of three criteria. Decision trees and random forests were used to create prediction models on the training data and select features. The model was able to correctly predict whether a patient responded well to the medication with approximately 80% accuracy and an F1-measure of approximately 90%.

AB - Over seventy percent of Americans take at least one form of prescription medication, with twenty percent taking more than five. The numbers emphasize how important it is for clinicians to understand the effects of the medication and whether these medications are effective. In this paper we propose a data driven framework to predict the effectiveness of medication on a patient, specifically in the case of diabetes. Our dataset contains claims data from 1.5 million patients. A heuristic was established to evaluate the 'effectiveness' of Metformin using a set of three criteria. Decision trees and random forests were used to create prediction models on the training data and select features. The model was able to correctly predict whether a patient responded well to the medication with approximately 80% accuracy and an F1-measure of approximately 90%.

KW - Decision support systems

KW - electronic medical records

KW - fuzzy logic

KW - Medical information systems

KW - predictive models

KW - supervised learning

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84936883240&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936883240&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2014.154

DO - 10.1109/ICDMW.2014.154

M3 - Conference contribution

AN - SCOPUS:84936883240

VL - 2015-January

SP - 1185

EP - 1188

BT - IEEE International Conference on Data Mining Workshops, ICDMW

PB - IEEE Computer Society

ER -