Multilevel latent class (MLC) modelling of healthcare provider causal effects on patient outcomes: Evaluation via simulation

Where performance comparison of healthcare providers is of interest, characteristics of both patients and the health condition of interest must be balanced across providers for a fair comparison. This is unlikely to be feasible within observational data, as patient population characteristics may vary geographically and patient care may vary by characteristics of the health condition. We simulated data for patients and providers, based on a previously utilized real-world dataset, and separately considered both binary and continuous covariate-effects at the upper level. Multilevel latent class (MLC) modelling is proposed to partition a prediction focus at the patient level (accommodating casemix) and a causal inference focus at the provider level. The MLC model recovered a range of simulated Trust-level effects. Median recovered values were almost identical to simulated values for the binary Trust-level covariate, and we observed successful recovery of the continuous Trust-level covariate with at least 3 latent Trust classes. Credible intervals widen as the error variance increases. The MLC approach successfully partitioned modelling for prediction and for causal inference, addressing the potential conflict between these two distinct analytical strategies. This improves upon strategies which only adjust for differential selection. Patient-level variation and measurement uncertainty are accommodated within the latent classes.

[1]  L. A. Goodman.  Exploratory latent structure analysis using both identifiable and unidentifiable models , 1974 .

[2]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[3]  L. Corrado.  Generalized Latent Variable Modeling: Multilevel, Longitudinal, and Structural Equation Models , 2005 .

[4]  J. Vermunt.  Latent Class Models , 2004 .

[5]  Ping Li,et al.  Readers guide to critical appraisal of cohort studies: 3. Analytical strategies to reduce confounding , 2005, BMJ : British Medical Journal.

[6]  David Kaplan,et al.  The Sage handbook of quantitative methodology for the social sciences , 2004 .

[7]  Yu-Kang Tu,et al.  Why evidence for the fetal origins of adult disease might be a statistical artifact: the "reversal paradox" for the relation between birth weight and blood pressure in later life. , 2005, American journal of epidemiology.

[8]  J. Pearl,et al.  Causal Inference in Statistics: A Primer , 2016 .

[9]  Amy Downing,et al.  Multilevel Latent Class Modelling of Colorectal Cancer Survival Status at Three Years and Socioeconomic Background Whilst Incorporating Stage of Disease , 2013 .

[10]  F. Song,et al.  Evaluating non-randomised intervention studies. , 2003, Health technology assessment.

[11]  J. Vermunt,et al.  Latent class and finite mixture models for multilevel data sets , 2008, Statistical methods in medical research.

[12]  J. Pearl.  Remarks on the method of propensity score , 2009, Statistics in medicine.

[13]  James M. Robins,et al.  Causal diagrams for epidemiologic research. , 1999 .

[14]  Sebastian Schneeweiss,et al.  Understanding Bias Amplification , 2011 .

[15]  David Forman,et al.  Multilevel latent class casemix modelling: a novel approach to accommodate patient casemix , 2011, BMC health services research.

[16]  Jeroen K. Vermunt,et al.  7. Multilevel Latent Class Models , 2003 .

[17]  S. Greenland,et al.  The table 2 fallacy: presenting and interpreting confounder and modifier coefficients. , 2013, American journal of epidemiology.

[18]  D. Rubin,et al.  Reducing Bias in Observational Studies Using Subclassification on the Propensity Score , 1984 .

[19]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[20]  Andrea Rusnock,et al.  Statistics on the table: The history of statistical concepts and methods , 2002 .

[21]  J. Vermunt,et al.  Latent Gold 4.0 User's Guide , 2005 .

[22]  Jay Magidson,et al.  LG-Syntax user's guide: Manual for Latent GOLD 4.5 Syntax module , 2008 .