Targeting a readmission prevention intervention based on predicted treatment effects rather than predicted risk could prevent up to 4458 readmissions annually and decrease the number needed to treat from 33 to 23.
Observational (n=1,539,285)
Sí
Does targeting a readmissions prevention intervention using causal machine learning reduce 30-day readmissions in hospitalized patients?
Causal machine learning can identify patients who benefit most from readmission prevention interventions, demonstrating that targeting by treatment effect rather than baseline risk may prevent more readmissions.
OBJECTIVE: To assess both the feasibility and potential impact of predicting preventable hospital readmissions using causal machine learning applied to data from the implementation of a readmissions prevention intervention (the Transitions Program). DATA SOURCES: Electronic health records maintained by Kaiser Permanente Northern California (KPNC). STUDY DESIGN: Retrospective causal forest analysis of postdischarge outcomes among KPNC inpatients. Using data from both before and after implementation, we apply causal forests to estimate individual-level treatment effects of the Transitions Program intervention on 30-day readmission. These estimates are used to characterize treatment effect heterogeneity and to assess the notional impacts of alternative targeting strategies in terms of the number of readmissions prevented. DATA COLLECTION: 1 539 285 index hospitalizations meeting the inclusion criteria and occurring between June 2010 and December 2018 at 21 KPNC hospitals. PRINCIPAL FINDINGS: ), particularly across levels of predicted risk. Notably, predicted treatment effects become more positive as predicted risk increases; patients at somewhat lower risk appear to have the largest predicted effects. Moreover, these estimates appear to be well calibrated, yielding the same estimate of annual readmissions prevented in the actual treatment subgroup (1246, 95% confidence interval CI 1110-1381) as did a formal evaluation of the Transitions Program (1210, 95% CI 990-1430). Estimates of the impacts of alternative targeting strategies suggest that as many as 4458 (95% CI 3925-4990) readmissions could be prevented annually, while decreasing the number needed to treat from 33 to 23, by targeting patients with the largest predicted effects rather than those at highest risk. CONCLUSIONS: Causal machine learning can be used to identify preventable hospital readmissions, if the requisite interventional data are available. Moreover, our results suggest a mismatch between risk and treatment effects.
Marafino et al. (Fri,) conducted a observational in Hospital readmission (n=1,539,285). Transitions Program (CATE-based targeting) vs. Risk-based targeting was evaluated on 30-day nonelective readmission. Targeting a readmission prevention intervention based on predicted treatment effects rather than predicted risk could prevent up to 4458 readmissions annually and decrease the number needed to treat from 33 to 23.