TY - JOUR
AU - B. J. Marafino
AU - C. Plimier
AU - P. Kipnis
AU - G. J. Escobar
AU - L. C. Myers
AU - M. C. Donnelly
AU - J. D. Greene
AU - M. D. Flagg
AU - J. R. Small
AU - V. X. Liu
A1 - 
AB - Hospital readmission is a key quality metric, yet post-discharge interventions often yield variable results. In the first large-scale randomized evaluation of causal machine learning in a health system, we assessed whether a novel model (the Predicted Benefit Intervention (PBI) score) could identify lower-risk patients most likely to benefit from post-discharge care coordination within Kaiser Permanente Northern California (KPNC). From May to December 2022, 9959 low-risk patients at 19 KPNC hospitals were randomized to usual care or the Transitions Program, which included medication reconciliation, primary care follow-up scheduling, and weekly calls for 30 days. While 30-day readmissions declined in the intervention group (7.7% vs. 8.2%), the difference was not statistically significant. However, the observed-to-expected readmission ratio declined into randomization and remained low thereafter; this decline was statistically significant. This study demonstrates the feasibility of implementing causal machine learning at scale to improve targeting and resource allocation in care delivery.
AD - Kaiser Permanente Division of Research, Pleasanton, CA, USA. ben.j.marafino@kp.org.; Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, CA, USA. ben.j.marafino@kp.org.; Kaiser Permanente Division of Research, Pleasanton, CA, USA.; The Permanente Medical Group, Oakland, CA, USA.; Kaiser Permanente Information Technology, Pleasanton, CA, USA.; Kaiser Foundation Hospitals, Oakland, CA, USA.; Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, CA, USA.
AN - 40993299
BT - NPJ Digit Med
C5 - HIT & Telehealth
CP - 1
DA - Sep 24
DO - 10.1038/s41746-025-01925-3
DP - NLM
ET - 20250924
IS - 1
JF - NPJ Digit Med
LA - eng
N2 - Hospital readmission is a key quality metric, yet post-discharge interventions often yield variable results. In the first large-scale randomized evaluation of causal machine learning in a health system, we assessed whether a novel model (the Predicted Benefit Intervention (PBI) score) could identify lower-risk patients most likely to benefit from post-discharge care coordination within Kaiser Permanente Northern California (KPNC). From May to December 2022, 9959 low-risk patients at 19 KPNC hospitals were randomized to usual care or the Transitions Program, which included medication reconciliation, primary care follow-up scheduling, and weekly calls for 30 days. While 30-day readmissions declined in the intervention group (7.7% vs. 8.2%), the difference was not statistically significant. However, the observed-to-expected readmission ratio declined into randomization and remained low thereafter; this decline was statistically significant. This study demonstrates the feasibility of implementing causal machine learning at scale to improve targeting and resource allocation in care delivery.
PY - 2025
SN - 2398-6352
SP - 571
ST - Expanding care coordination in an integrated health system through causal machine learning
T1 - Expanding care coordination in an integrated health system through causal machine learning
T2 - NPJ Digit Med
TI - Expanding care coordination in an integrated health system through causal machine learning
U1 - HIT & Telehealth
U3 - 10.1038/s41746-025-01925-3
VL - 8
VO - 2398-6352
Y1 - 2025
ER -