An Automated Model to Identify Heart Failure Patients at Risk for 30-Day Readmission or Death Using Electronic Medical Record Data

被引:339
作者
Amarasingham, Ruben [1 ,2 ]
Moore, Billy J. [1 ]
Tabak, Ying P. [3 ]
Drazner, Mark H. [4 ]
Clark, Christopher A. [1 ]
Zhang, Song [5 ]
Reed, W. Gary [1 ,2 ]
Swanson, Timothy S. [1 ]
Ma, Ying [1 ]
Halm, Ethan A. [2 ,5 ]
机构
[1] Parkland Hlth & Hosp Syst, Ctr Clin Innovat, Dallas, TX 75235 USA
[2] Univ Texas SW Med Ctr Dallas, Div Gen Internal Med, Dept Med, Dallas, TX 75390 USA
[3] CareFusion, Clin Res, Marlborough, MA USA
[4] Univ Texas SW Med Ctr Dallas, Dept Med, Div Cardiol, Dallas, TX 75390 USA
[5] Univ Texas SW Med Ctr Dallas, Dept Clin Sci, Dallas, TX 75390 USA
基金
美国国家卫生研究院;
关键词
informatics; quality improvement; health policy; PREDICTIVE ABILITY; SAFETY-NET; ROC CURVE; MORTALITY; CARE; ADJUSTMENT; QUALITY; RECLASSIFICATION; PERFORMANCE; MARKER;
D O I
10.1097/MLR.0b013e3181ef60d9
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Background: A real-time electronic predictive model that identifies hospitalized heart failure (HF) patients at high risk for readmission or death may be valuable to clinicians and hospitals who care for these patients. Methods: An automated predictive model for 30-day readmission and death was derived and validated from clinical and nonclinical risk factors present on admission in 1372 HF hospitalizations to a major urban hospital between January 2007 and August 2008. Data were extracted from an electronic medical record. The performance of the electronic model was compared with mortality and readmission models developed by the Center for Medicaid and Medicare Services (CMS models) and a HF mortality model derived from the Acute Decompensated Heart Failure Registry (ADHERE model). Results: The 30-day mortality and readmission rates were 3.1% and 24.1% respectively. The electronic model demonstrated good discrimination for 30 day mortality (C statistic 0.86) and readmission (C statistic 0.72) and performed as well, or better than, the ADHERE model and CMS models for both outcomes (C statistic ranges: 0.72-0.73 and 0.56-0.66 for mortality and readmissions respectively; P < 0.05 in all comparisons). Markers of social instability and lower socioeconomic status improved readmission prediction in the electronic model (C statistic 0.72 vs. 0.61, P < 0.05). Conclusions: Clinical and social factors available within hours of hospital presentation and extractable from an EMR predicted mortality and readmission at 30 days. Incorporating complex social factors increased the model's accuracy, suggesting that such factors could enhance risk adjustment models designed to compare hospital readmission rates.
引用
收藏
页码:981 / 988
页数:8
相关论文
共 34 条
[1]   HOSPITAL READMISSIONS IN THE MEDICARE POPULATION [J].
ANDERSON, GF ;
STEINBERG, EP .
NEW ENGLAND JOURNAL OF MEDICINE, 1984, 311 (21) :1349-1353
[2]   Postdischarge environmental and socioeconomic factors and the likelihood of early hospital readmission among community-dwelling medicare beneficiaries [J].
Arbaje, Alicia I. ;
Wolff, Jennifer L. ;
Yu, Qilu ;
Powe, Neil R. ;
Anderson, Gerard F. ;
Boult, Chad .
GERONTOLOGIST, 2008, 48 (04) :495-504
[3]   A conceptual framework for the study of early readmission as an indicator of quality of care [J].
Ashton, CM ;
Wray, NP .
SOCIAL SCIENCE & MEDICINE, 1996, 43 (11) :1533-1541
[4]   Could Medicare Readmission Policy Exacerbate Health Care System Inequity? [J].
Bhalla, Rohit ;
Kalkut, Gary .
ANNALS OF INTERNAL MEDICINE, 2010, 152 (02) :114-117
[5]   Stimulating the Adoption of Health Information Technology. [J].
Blumenthal, David .
NEW ENGLAND JOURNAL OF MEDICINE, 2009, 360 (15) :1477-1479
[6]   Incorporating Disparity Reduction into Pay-for-Performance [J].
Chien, Alyna T. ;
Chin, Marshall H. .
JOURNAL OF GENERAL INTERNAL MEDICINE, 2009, 24 (01) :135-136
[7]  
Efron Bradley, 1994, An Introduction to the bootstrap, DOI 10.1201/9780429246593
[8]   Risk-adjusting hospital inpatient mortality using automated inpatient, outpatient, and laboratory databases [J].
Escobar, Gabriel J. ;
Greene, John D. ;
Scheirer, Peter ;
Gardner, Marla N. ;
Draper, David ;
Kipnis, Patricia .
MEDICAL CARE, 2008, 46 (03) :232-239
[9]   So much to do, so little time - Care for the socially disadvantaged and the 15-minute visit [J].
Fiscella, Kevin ;
Epstein, Ronald M. .
ARCHIVES OF INTERNAL MEDICINE, 2008, 168 (17) :1843-1852
[10]   Risk stratification for in-hospital mortality in acutely decompensated heart failure - Classification and regression tree analysis [J].
Fonarow, GC ;
Adams, KF ;
Abraham, WT ;
Yancy, CW ;
Boscardin, WJ .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2005, 293 (05) :572-580