Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base.
<h4>Background</h4>Risk adjusted mortality for intensive care units (ICU) is usually estimated via logistic regression. Random effects (RE) or hierarchical models have been advocated to estimate provider risk-adjusted mortality on the basis that standard estimators increase false outlier...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2014-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/25029164/pdf/?tool=EBI |
| _version_ | 1819319449528827904 |
|---|---|
| author | John L Moran Patricia J Solomon ANZICS Centre for Outcome and Resource Evaluation (CORE) of Australian and New Zealand Intensive Care Society (ANZICS) |
| author_facet | John L Moran Patricia J Solomon ANZICS Centre for Outcome and Resource Evaluation (CORE) of Australian and New Zealand Intensive Care Society (ANZICS) |
| author_sort | John L Moran |
| collection | DOAJ |
| description | <h4>Background</h4>Risk adjusted mortality for intensive care units (ICU) is usually estimated via logistic regression. Random effects (RE) or hierarchical models have been advocated to estimate provider risk-adjusted mortality on the basis that standard estimators increase false outlier classification. The utility of fixed effects (FE) estimators (separate ICU-specific intercepts) has not been fully explored.<h4>Methods</h4>Using a cohort from the Australian and New Zealand Intensive Care Society Adult Patient Database, 2009-2010, the model fit of different logistic estimators (FE, random-intercept and random-coefficient) was characterised: Bayesian Information Criterion (BIC; lower values better), receiver-operator characteristic curve area (AUC) and Hosmer-Lemeshow (H-L) statistic. ICU standardised hospital mortality ratios (SMR) and 95%CI were compared between models. ICU site performance (FE), relative to the grand observation-weighted mean (GO-WM) on odds ratio (OR), risk ratio (RR) and probability scales were assessed using model-based average marginal effects (AME).<h4>Results</h4>The data set consisted of 145355 patients in 128 ICUs, years 2009 (47.5%) & 2010 (52.5%), with mean(SD) age 60.9(18.8) years, 56% male and ICU and hospital mortalities of 7.0% and 10.9% respectively. The FE model had a BIC = 64058, AUC = 0.90 and an H-L statistic P-value = 0.22. The best-fitting random-intercept model had a BIC = 64457, AUC = 0.90 and H-L statistic P-value = 0.32 and random-coefficient model, BIC = 64556, AUC = 0.90 and H-L statistic P-value = 0.28. Across ICUs and over years no outliers (SMR 95% CI excluding null-value = 1) were identified and no model difference in SMR spread or 95%CI span was demonstrated. Using AME (OR and RR scale), ICU site-specific estimates diverged from the GO-WM, and the effect spread decreased over calendar years. On the probability scale, a majority of ICUs demonstrated calendar year decrease, but in the for-profit sector, this trend was reversed.<h4>Conclusions</h4>The FE estimator had model advantage compared with conventional RE models. Using AME, between and over-year ICU site-effects were easily characterised. |
| first_indexed | 2024-12-24T11:03:52Z |
| format | Article |
| id | doaj.art-6665c0abe21642cc8c3ba56332911c94 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-24T11:03:52Z |
| publishDate | 2014-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-6665c0abe21642cc8c3ba56332911c942022-12-21T16:58:40ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0197e10229710.1371/journal.pone.0102297Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base.John L MoranPatricia J SolomonANZICS Centre for Outcome and Resource Evaluation (CORE) of Australian and New Zealand Intensive Care Society (ANZICS)<h4>Background</h4>Risk adjusted mortality for intensive care units (ICU) is usually estimated via logistic regression. Random effects (RE) or hierarchical models have been advocated to estimate provider risk-adjusted mortality on the basis that standard estimators increase false outlier classification. The utility of fixed effects (FE) estimators (separate ICU-specific intercepts) has not been fully explored.<h4>Methods</h4>Using a cohort from the Australian and New Zealand Intensive Care Society Adult Patient Database, 2009-2010, the model fit of different logistic estimators (FE, random-intercept and random-coefficient) was characterised: Bayesian Information Criterion (BIC; lower values better), receiver-operator characteristic curve area (AUC) and Hosmer-Lemeshow (H-L) statistic. ICU standardised hospital mortality ratios (SMR) and 95%CI were compared between models. ICU site performance (FE), relative to the grand observation-weighted mean (GO-WM) on odds ratio (OR), risk ratio (RR) and probability scales were assessed using model-based average marginal effects (AME).<h4>Results</h4>The data set consisted of 145355 patients in 128 ICUs, years 2009 (47.5%) & 2010 (52.5%), with mean(SD) age 60.9(18.8) years, 56% male and ICU and hospital mortalities of 7.0% and 10.9% respectively. The FE model had a BIC = 64058, AUC = 0.90 and an H-L statistic P-value = 0.22. The best-fitting random-intercept model had a BIC = 64457, AUC = 0.90 and H-L statistic P-value = 0.32 and random-coefficient model, BIC = 64556, AUC = 0.90 and H-L statistic P-value = 0.28. Across ICUs and over years no outliers (SMR 95% CI excluding null-value = 1) were identified and no model difference in SMR spread or 95%CI span was demonstrated. Using AME (OR and RR scale), ICU site-specific estimates diverged from the GO-WM, and the effect spread decreased over calendar years. On the probability scale, a majority of ICUs demonstrated calendar year decrease, but in the for-profit sector, this trend was reversed.<h4>Conclusions</h4>The FE estimator had model advantage compared with conventional RE models. Using AME, between and over-year ICU site-effects were easily characterised.https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/25029164/pdf/?tool=EBI |
| spellingShingle | John L Moran Patricia J Solomon ANZICS Centre for Outcome and Resource Evaluation (CORE) of Australian and New Zealand Intensive Care Society (ANZICS) Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. PLoS ONE |
| title | Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. |
| title_full | Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. |
| title_fullStr | Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. |
| title_full_unstemmed | Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. |
| title_short | Fixed effects modelling for provider mortality outcomes: Analysis of the Australia and New Zealand Intensive Care Society (ANZICS) Adult Patient Data-base. |
| title_sort | fixed effects modelling for provider mortality outcomes analysis of the australia and new zealand intensive care society anzics adult patient data base |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/25029164/pdf/?tool=EBI |
| work_keys_str_mv | AT johnlmoran fixedeffectsmodellingforprovidermortalityoutcomesanalysisoftheaustraliaandnewzealandintensivecaresocietyanzicsadultpatientdatabase AT patriciajsolomon fixedeffectsmodellingforprovidermortalityoutcomesanalysisoftheaustraliaandnewzealandintensivecaresocietyanzicsadultpatientdatabase AT anzicscentreforoutcomeandresourceevaluationcoreofaustralianandnewzealandintensivecaresocietyanzics fixedeffectsmodellingforprovidermortalityoutcomesanalysisoftheaustraliaandnewzealandintensivecaresocietyanzicsadultpatientdatabase |