Comparing causal random forest and linear regression to estimate the independent association of organisational factors with ICU efficiency.

PURPOSE: Parametric regression models have been the main statistical method for identifying average treatment effects. Causal machine learning models showed promising results in estimating heterogeneous treatment effects in causal inference. Here we aimed to compare the application of causal random forest (CRF) and linear regression modelling (LRM) to estimate the effects of organisational factors on ICU efficiency. METHODS: A retrospective analysis of 277,459 patients admitted to 128 Brazilian and Uruguayan ICUs over three years. ICU efficiency was assessed using the average standardised efficiency ratio (ASER), measured as the average of the standardised mortality ratio (SMR) and the standardised resource use (SRU) according to the SAPS-3 score. Using a causal inference framework, we estimated and compared the conditional average treatment effect (CATE) of seven common structural and organisational factors on ICU efficiency using LRM with interaction terms and CRF. RESULTS: The hospital mortality was 14 %; median ICU and hospital lengths of stay were 2 and 7 days, respectively. Overall median SMR was 0.97 [IQR: 0.76,1.21], median SRU was 1.06 [IQR: 0.79,1.30] and median ASER was 0.99 [IQR: 0.82,1.21]. Both CRF and LRM showed that the average number of nurses per ten beds was independently associated with ICU efficiency (CATE [95 %CI]: -0.13 [-0.24, -0.01] and -0.09 [-0.17,-0.01], respectively). Finally, CRF identified some specific ICUs with a significant CATE in exposures that did not present a significant average effect. CONCLUSION: In general, both methods were comparable to identify organisational factors significantly associated with CATE on ICU efficiency. CRF however identified specific ICUs with significant effects, even when the average effect was nonsignificant. This can assist healthcare managers in further in-dept evaluation of process interventions to improve ICU efficiency.

Preterm Birth is Associated with Lower Academic Attainment at Age 12 Years: A Matched Cohort Study by Linkage of Population-Based Datasets.

OBJECTIVE: To compare academic attainment at age 12 years in preterm children born below 30 weeks of gestation with matched term-born peers, using standardized, nationwide and well-validated school tests. STUDY DESIGN: This population-based, national cohort study was performed by linking perinatal data from the nationwide Netherlands Perinatal Registry with educational outcome data from Statistics Netherlands and included 4677 surviving preterm children born at 250/7-296/7 weeks of gestational age and 366 561 controls born at 40 weeks of gestational age in 2000-2007. First, special education participation rate was calculated. Subsequently, all preterm children with academic attainment test data derived at age 12 years were matched to term-born children using year and month of birth, sex, parity, socioeconomic status, and maternal age. Total, language, and mathematics test scores and secondary school level advice were compared between these 2 groups. RESULTS: Children below 30 weeks of gestation had a higher special education participation rate (10.2% vs 2.7%, P < .001) than term-born peers. Preterm children had lower total (-0.37 SD; 95% CI -0.42 to -0.31), language (-0.21 SD; 95% CI -0.27 to -0.15), and mathematics (-0.45 SD; 95%CI -0.51 to -0.38) z scores, and more often a prevocational secondary school level advice (62% vs 46%, P < .001). CONCLUSIONS: A substantial proportion of children born before 30 weeks of gestation need special education at the end of elementary schooling. These children have significant deficits on all measures of academic attainment at age 12 years, especially mathematics, compared with matched term-born peers.