Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes

Michael Pine, Donald E. Fry, Edward L. Hannan, James M Naessens, Kay Whitman, Agnes Reband, Feng Qian, Joseph Schindler, Mark Sonneborn, Jaclyn Roland, Linda Hyde, Barbara A. Dennison

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Numerical laboratory data at admission have been proposed for enhancement of inpatient predictive modeling from administrative claims. In this study, predictive models for inpatient/30-day postdischarge mortality and for risk-adjusted prolonged length of stay, as a surrogate for severe inpatient complications of care, were designed with administrative data only and with administrative data plus numerical laboratory variables. A comparison of resulting inpatient models for acute myocardial infarction, congestive heart failure, coronary artery bypass grafting, and percutaneous cardiac interventions demonstrated improved discrimination and calibration with administrative data plus laboratory values compared to administrative data only for both mortality and prolonged length of stay. Improved goodness of fit was most apparent in acute myocardial infarction and percutaneous cardiac intervention. The emergence of electronic medical records should make the addition of laboratory variables to administrative data an efficient and practical method to clinically enhance predictive modeling of inpatient outcomes of care.

Original languageEnglish (US)
Pages (from-to)141-147
Number of pages7
JournalAmerican Journal of Medical Quality
Volume32
Issue number2
DOIs
StatePublished - Mar 1 2017
Externally publishedYes

Fingerprint

Risk Adjustment
Inpatients
Length of Stay
Myocardial Infarction
Mortality
Electronic Health Records
Coronary Artery Bypass
Calibration
Heart Failure

Keywords

  • cardiovascular disease
  • clinically enhanced claims data
  • patient outcomes
  • patient safety (measurement)
  • quality of care
  • risk adjustment

ASJC Scopus subject areas

  • Health Policy

Cite this

Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes. / Pine, Michael; Fry, Donald E.; Hannan, Edward L.; Naessens, James M; Whitman, Kay; Reband, Agnes; Qian, Feng; Schindler, Joseph; Sonneborn, Mark; Roland, Jaclyn; Hyde, Linda; Dennison, Barbara A.

In: American Journal of Medical Quality, Vol. 32, No. 2, 01.03.2017, p. 141-147.

Research output: Contribution to journalArticle

Pine, M, Fry, DE, Hannan, EL, Naessens, JM, Whitman, K, Reband, A, Qian, F, Schindler, J, Sonneborn, M, Roland, J, Hyde, L & Dennison, BA 2017, 'Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes', American Journal of Medical Quality, vol. 32, no. 2, pp. 141-147. https://doi.org/10.1177/1062860616629205
Pine, Michael ; Fry, Donald E. ; Hannan, Edward L. ; Naessens, James M ; Whitman, Kay ; Reband, Agnes ; Qian, Feng ; Schindler, Joseph ; Sonneborn, Mark ; Roland, Jaclyn ; Hyde, Linda ; Dennison, Barbara A. / Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes. In: American Journal of Medical Quality. 2017 ; Vol. 32, No. 2. pp. 141-147.
@article{183ac4d4e27d48c9b733c6e582300063,
title = "Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes",
abstract = "Numerical laboratory data at admission have been proposed for enhancement of inpatient predictive modeling from administrative claims. In this study, predictive models for inpatient/30-day postdischarge mortality and for risk-adjusted prolonged length of stay, as a surrogate for severe inpatient complications of care, were designed with administrative data only and with administrative data plus numerical laboratory variables. A comparison of resulting inpatient models for acute myocardial infarction, congestive heart failure, coronary artery bypass grafting, and percutaneous cardiac interventions demonstrated improved discrimination and calibration with administrative data plus laboratory values compared to administrative data only for both mortality and prolonged length of stay. Improved goodness of fit was most apparent in acute myocardial infarction and percutaneous cardiac intervention. The emergence of electronic medical records should make the addition of laboratory variables to administrative data an efficient and practical method to clinically enhance predictive modeling of inpatient outcomes of care.",
keywords = "cardiovascular disease, clinically enhanced claims data, patient outcomes, patient safety (measurement), quality of care, risk adjustment",
author = "Michael Pine and Fry, {Donald E.} and Hannan, {Edward L.} and Naessens, {James M} and Kay Whitman and Agnes Reband and Feng Qian and Joseph Schindler and Mark Sonneborn and Jaclyn Roland and Linda Hyde and Dennison, {Barbara A.}",
year = "2017",
month = "3",
day = "1",
doi = "10.1177/1062860616629205",
language = "English (US)",
volume = "32",
pages = "141--147",
journal = "American Journal of Medical Quality",
issn = "1062-8606",
publisher = "SAGE Publications Inc.",
number = "2",

}

TY - JOUR

T1 - Adding Laboratory Data to Hospital Claims Data to Improve Risk Adjustment of Inpatient/30-Day Postdischarge Outcomes

AU - Pine, Michael

AU - Fry, Donald E.

AU - Hannan, Edward L.

AU - Naessens, James M

AU - Whitman, Kay

AU - Reband, Agnes

AU - Qian, Feng

AU - Schindler, Joseph

AU - Sonneborn, Mark

AU - Roland, Jaclyn

AU - Hyde, Linda

AU - Dennison, Barbara A.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Numerical laboratory data at admission have been proposed for enhancement of inpatient predictive modeling from administrative claims. In this study, predictive models for inpatient/30-day postdischarge mortality and for risk-adjusted prolonged length of stay, as a surrogate for severe inpatient complications of care, were designed with administrative data only and with administrative data plus numerical laboratory variables. A comparison of resulting inpatient models for acute myocardial infarction, congestive heart failure, coronary artery bypass grafting, and percutaneous cardiac interventions demonstrated improved discrimination and calibration with administrative data plus laboratory values compared to administrative data only for both mortality and prolonged length of stay. Improved goodness of fit was most apparent in acute myocardial infarction and percutaneous cardiac intervention. The emergence of electronic medical records should make the addition of laboratory variables to administrative data an efficient and practical method to clinically enhance predictive modeling of inpatient outcomes of care.

AB - Numerical laboratory data at admission have been proposed for enhancement of inpatient predictive modeling from administrative claims. In this study, predictive models for inpatient/30-day postdischarge mortality and for risk-adjusted prolonged length of stay, as a surrogate for severe inpatient complications of care, were designed with administrative data only and with administrative data plus numerical laboratory variables. A comparison of resulting inpatient models for acute myocardial infarction, congestive heart failure, coronary artery bypass grafting, and percutaneous cardiac interventions demonstrated improved discrimination and calibration with administrative data plus laboratory values compared to administrative data only for both mortality and prolonged length of stay. Improved goodness of fit was most apparent in acute myocardial infarction and percutaneous cardiac intervention. The emergence of electronic medical records should make the addition of laboratory variables to administrative data an efficient and practical method to clinically enhance predictive modeling of inpatient outcomes of care.

KW - cardiovascular disease

KW - clinically enhanced claims data

KW - patient outcomes

KW - patient safety (measurement)

KW - quality of care

KW - risk adjustment

UR - http://www.scopus.com/inward/record.url?scp=85015048961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015048961&partnerID=8YFLogxK

U2 - 10.1177/1062860616629205

DO - 10.1177/1062860616629205

M3 - Article

C2 - 26917809

AN - SCOPUS:85015048961

VL - 32

SP - 141

EP - 147

JO - American Journal of Medical Quality

JF - American Journal of Medical Quality

SN - 1062-8606

IS - 2

ER -