Using Unstructured Data to Identify Readmitted Patients

Majid Rastegar-Mojarad; Jenna K. Lovely; Joshua Pankratz; Sunghwan Sohn; Donna M. Ihrke; Amit Merchea; David Larson; Hongfang D Liu

doi:10.1109/ICHI.2017.99

Using Unstructured Data to Identify Readmitted Patients

Majid Rastegar-Mojarad, Jenna K. Lovely, Joshua Pankratz, Sunghwan Sohn, Donna M. Ihrke, Amit Merchea, David Larson, Hongfang D Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Readmission rate is a quality metric for hospitals. The electronic medical record is the main source to identify readmitted patients and calculating readmission rates. Difficulties remain in identifying patients readmitted to a facility different than the one performing the procedure. In this study, we assessed the impact of using unstructured data in detecting readmission within 30 days of surgery. We implemented two rule-based systems to recognize any mention of readmission in follow-up phone call conversions. We evaluated our systems on datasets from two hospitals. Our evaluation showed using unstructured data, in addition to structured data, increased sensitivity in the both dataset, from 53 to 81 and 66 to 87 percent.

Original language	English (US)
Title of host publication	Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781509048816
DOIs	https://doi.org/10.1109/ICHI.2017.99
State	Published - Sep 8 2017
Event	5th IEEE International Conference on Healthcare Informatics, ICHI 2017 - Park City, United States Duration: Aug 23 2017 → Aug 26 2017

Other

Other	5th IEEE International Conference on Healthcare Informatics, ICHI 2017
Country	United States
City	Park City
Period	8/23/17 → 8/26/17

Fingerprint

ASJC Scopus subject areas

Health Informatics

Cite this

Rastegar-Mojarad, M., Lovely, J. K., Pankratz, J., Sohn, S., Ihrke, D. M., Merchea, A., Larson, D., & Liu, H. D. (2017). Using Unstructured Data to Identify Readmitted Patients. In Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017 (pp. 1-4). [8031124] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2017.99

Using Unstructured Data to Identify Readmitted Patients. / Rastegar-Mojarad, Majid; Lovely, Jenna K.; Pankratz, Joshua; Sohn, Sunghwan; Ihrke, Donna M.; Merchea, Amit; Larson, David ; Liu, Hongfang D.

Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-4 8031124.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rastegar-Mojarad, M, Lovely, JK, Pankratz, J, Sohn, S, Ihrke, DM, Merchea, A, Larson, D & Liu, HD 2017, Using Unstructured Data to Identify Readmitted Patients. in Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017., 8031124, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 5th IEEE International Conference on Healthcare Informatics, ICHI 2017, Park City, United States, 8/23/17. https://doi.org/10.1109/ICHI.2017.99

@inproceedings{a951efbfb20347dcaa1b1e8efed6f13c,

title = "Using Unstructured Data to Identify Readmitted Patients",

abstract = "Readmission rate is a quality metric for hospitals. The electronic medical record is the main source to identify readmitted patients and calculating readmission rates. Difficulties remain in identifying patients readmitted to a facility different than the one performing the procedure. In this study, we assessed the impact of using unstructured data in detecting readmission within 30 days of surgery. We implemented two rule-based systems to recognize any mention of readmission in follow-up phone call conversions. We evaluated our systems on datasets from two hospitals. Our evaluation showed using unstructured data, in addition to structured data, increased sensitivity in the both dataset, from 53 to 81 and 66 to 87 percent.",

author = "Majid Rastegar-Mojarad and Lovely, {Jenna K.} and Joshua Pankratz and Sunghwan Sohn and Ihrke, {Donna M.} and Amit Merchea and David Larson and Liu, {Hongfang D}",

year = "2017",

month = sep

day = "8",

doi = "10.1109/ICHI.2017.99",

language = "English (US)",

pages = "1--4",

booktitle = "Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "5th IEEE International Conference on Healthcare Informatics, ICHI 2017 ; Conference date: 23-08-2017 Through 26-08-2017",

}

TY - GEN

T1 - Using Unstructured Data to Identify Readmitted Patients

AU - Rastegar-Mojarad, Majid

AU - Lovely, Jenna K.

AU - Pankratz, Joshua

AU - Sohn, Sunghwan

AU - Ihrke, Donna M.

AU - Merchea, Amit

AU - Larson, David

AU - Liu, Hongfang D

PY - 2017/9/8

Y1 - 2017/9/8

N2 - Readmission rate is a quality metric for hospitals. The electronic medical record is the main source to identify readmitted patients and calculating readmission rates. Difficulties remain in identifying patients readmitted to a facility different than the one performing the procedure. In this study, we assessed the impact of using unstructured data in detecting readmission within 30 days of surgery. We implemented two rule-based systems to recognize any mention of readmission in follow-up phone call conversions. We evaluated our systems on datasets from two hospitals. Our evaluation showed using unstructured data, in addition to structured data, increased sensitivity in the both dataset, from 53 to 81 and 66 to 87 percent.

AB - Readmission rate is a quality metric for hospitals. The electronic medical record is the main source to identify readmitted patients and calculating readmission rates. Difficulties remain in identifying patients readmitted to a facility different than the one performing the procedure. In this study, we assessed the impact of using unstructured data in detecting readmission within 30 days of surgery. We implemented two rule-based systems to recognize any mention of readmission in follow-up phone call conversions. We evaluated our systems on datasets from two hospitals. Our evaluation showed using unstructured data, in addition to structured data, increased sensitivity in the both dataset, from 53 to 81 and 66 to 87 percent.

UR - http://www.scopus.com/inward/record.url?scp=85032359856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032359856&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2017.99

DO - 10.1109/ICHI.2017.99

M3 - Conference contribution

AN - SCOPUS:85032359856

SP - 1

EP - 4

BT - Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE International Conference on Healthcare Informatics, ICHI 2017

Y2 - 23 August 2017 through 26 August 2017

ER -

Access to Document

10.1109/ICHI.2017.99