The Use of Fixed-and Random-Effects Models for Classifying Hospitals as Mortality Outliers: A Monte Carlo Assessment

Medical Decision Making - Tập 23 Số 6 - Trang 526-539 - 2003
Peter C. Austin1,2,3, David A. Alter, Jack V. Tu
1Institute for Clinical Evaluative Sciences, G1 06, 2075 Bayview Avenue, Toronto, Ontario, Canada M4N 3M5; telephone: (416) 480-6131; fax: (416) 480-6048;
2fax: (416) 480-6048
3telephone: (416) 480-6131

Tóm tắt

Background. There is an increasing movement towards the release of hospital “report-cards.” However, there is a paucity of research into the abilities of the different methods to correctly classify hospitals as performance outliers.Objective.To examine the ability of risk-adjusted mortality rates computed using conventional logistic regression and random-effects logistic regression models to correctly identify hospitals that have higher than acceptable mortality.Research Design.Monte Carlo simulations.Measures.Sensitivity, specificity, and positive predictive value of a classification as a high-outlier for identifying hospitals with higher than acceptable mortality rates.Results.When the distribution of hospital-specific log-odds of death was normal, random-effects models had greater specificity and positive predictive value than fixed-effects models. However, fixed-effects models had greater sensitivity than random-effects models.Conclusions.Researchers and policy makers need to carefully consider the balance between false positives and false negatives when choosing statistical models for determining which hospitals have higher than acceptablemortality in performance profiling.

Từ khóa


Tài liệu tham khảo

1. Luft HS, Romano PS, RemyLL, Rainwater J. Annual Report of the California Hospital Outcomes Project. Sacramento: California Office of Statewide Health Planning and Development ; 1993.

2. Pennsylvania Health Care Cost Containment Council. Focus on Heart Attack in Pennsylvania. ResearchMethods and Results. Harrisburg: Pennsylvania Health Care Cost Containment Council ; 1996.

3. Tu JV, Austin P, Naylor CD, Iron K, Zhang H. Acute myocardial infarction outcomes in Ontario. In: Naylor CD, Slaugher PM, editors. Cardiovascular Health Services in Ontario: An ICES Atlas. Toronto, Canada: Institute for Clinical Evaluative Sciences ; 1999. p. 83–110.

4. New York State Department of Health. Coronary Artery Bypass Graft Surgery in New York State 1989-1991. Albany: New York State Department of Health ; 1992.

10.1056/NEJM199602083340611

6. Zinman D. State takes docs’ list to heart. Newsday, 18 December 1991, p. 7-7.

7. Iezzoni LI. Risk Adjustment for Measuring Health Care Outcomes. Ann Arbor, MI: Health Administration Press ; 1994.

10.1016/0003-4975(94)91721-3

10.1016/0895-4356(94)00126-B

10.1161/01.CIR.85.4.1254

10.1161/01.CIR.88.2.416

10.1016/0002-9149(88)90918-6

10.1378/chest.108.1.83

10.1056/NEJM198308113090602

10.7326/0003-4819-123-10-199511150-00004

10.1097/00005650-199601000-00002

10.1177/0272989X9601600405

18. DeLong ER, Peterson ED, DeLong DM, Muhlbaier LH, Hackett S, Mark DB. Comparing risk-adjustment methods for provider profiling . Stat Med. 1997;16: 2645–2664 .

10.1016/S0140-6736(97)09362-8

10.1046/j.1365-2753.2001.00261.x

21. Austin PC. AComparison of Bayesianmethods for profiling hospital performance . Med Decis Making. 2002;22: 160–169 .

22. MillerME, Hui SL, TierneyWM, McDonald CJ. Estimating physician costliness: an empirical bayes approach . Med Care. 1993;31: YS16–YS28 .

10.2307/2983325

10.1016/S0167-6296(99)00034-X

25. Normand SL, GlickmanME, Gatsonis CA. Statistical methods for aprofiling providers of medical care: issues and applications . JAmStat Assoc. 1997;92: 803–814 .

26. Tu JV, Naylor CD, Austin P. Temporal changes in the outcomes of acute myocardial infarction in Ontario, 1992-1996 . CanMed Assoc J. 1999;161: 1257–1261 .

10.1016/S0735-1097(01)01109-3

10.1001/jama.285.24.3116

10.1097/00005650-200201000-00008

10.1001/jama.285.16.2101

31. Wennberg DE, Birkmeyer JD, editors. The Dartmouth Atlas of Cardiovascular Health Care. Dartmouth, NH: Center for Evaluative Clinical Sciences ; 1999.

10.1148/radiology.143.1.7063747

33. Snijders TAB, Bosker RJ. Multilevel Analysis. An Introduction to Basic and Advanced Multilevel Modeling. London: Sage ; 1999.

34. Goldstein H. Multilevel Statistical Models. 2nd ed. London: Edward Arnold ; 1995.

10.1007/BF03404950

10.1046/j.1365-2753.2000.00245.x

37. Gatsonis CA, Epstein AM, Newhouse JP, Normand SL, McNeil BJ. Variations in the utilization of coronary angiography for elderly patients with an acute myocardial infarction . An analysis using hierarchical logistic regression. Med Care. 1995;33: 625–642 .

10.1136/bmj.318.7195.1381

10.1016/0277-9536(95)00188-3

10.1097/00005650-199608000-00002

41. Localio AR, Hamory BH, Cocks Fisher A, TenHave TR. The public release of hospital and physician mortality data in Pennsylvania . A case study. Med Care. 1997;35: 272–286 .

42. Breslow NE, Clayton DG. Approximate inference in generalized linear mixed models . J Am Stat Assoc. 1993;88: 9–25 .

Thông tin
Thông tin xuất bản

Medical Decision Making

Tập 23 Số 6

526-539

Thông tin tác giả