Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing.

Autor: Henry KE; Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.; Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA., Adams R; Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA.; Department of Psychiatry and Behavioral Science, Johns Hopkins School of Medicine, Baltimore, MD, USA., Parent C; Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA., Soleimani H; Health Informatics, University of California, San Francisco, San Francisco, CA, USA., Sridharan A; Howard County General Hospital, Columbia, MD, USA., Johnson L; Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA., Hager DN; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA., Cosgrove SE; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA., Markowski A; Suburban Hospital, Bethesda, MD, USA., Klein EY; Department of Emergency Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA., Chen ES; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA., Saheed MO; Department of Emergency Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA., Henley M; Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA., Miranda S; Department of Medicine, The Johns Hopkins Hospital, Baltimore, MD, USA., Houston K; Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA., Linton RC 2nd; Howard County General Hospital, Columbia, MD, USA., Ahluwalia AR; Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA., Wu AW; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA. awu@jhu.edu.; Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. awu@jhu.edu.; Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. awu@jhu.edu.; Department of International Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. awu@jhu.edu., Saria S; Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA. ssaria@cs.jhu.edu.; Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA. ssaria@cs.jhu.edu.; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA. ssaria@cs.jhu.edu.; Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. ssaria@cs.jhu.edu.; Bayesian Health, New York, NY, USA. ssaria@cs.jhu.edu.
Jazyk: angličtina
Zdroj: Nature medicine [Nat Med] 2022 Jul; Vol. 28 (7), pp. 1447-1454. Date of Electronic Publication: 2022 Jul 21.
DOI: 10.1038/s41591-022-01895-z
Abstrakt: Machine learning-based clinical decision support tools for sepsis create opportunities to identify at-risk patients and initiate treatments at early time points, which is critical for improving sepsis outcomes. In view of the increasing use of such systems, better understanding of how they are adopted and used by healthcare providers is needed. Here, we analyzed provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System), which was deployed at five hospitals over a 2-year period. Among 9,805 retrospectively identified sepsis cases, the early detection tool achieved high sensitivity (82% of sepsis cases were identified) and a high rate of adoption: 89% of all alerts by the system were evaluated by a physician or advanced practice provider and 38% of evaluated alerts were confirmed by a provider. Adjusting for patient presentation and severity, patients with sepsis whose alert was confirmed by a provider within 3 h had a 1.85-h (95% CI 1.66-2.00) reduction in median time to first antibiotic order compared to patients with sepsis whose alert was either dismissed, confirmed more than 3 h after the alert or never addressed in the system. Finally, we found that emergency department providers and providers who had previous interactions with an alert were more likely to interact with alerts, as well as to confirm alerts on retrospectively identified patients with sepsis. Beyond efforts to improve the performance of early warning systems, efforts to improve adoption are essential to their clinical impact and should focus on understanding providers' knowledge of, experience with and attitudes toward such systems.
(© 2022. The Author(s), under exclusive licence to Springer Nature America, Inc.)
Databáze: MEDLINE
Externí odkaz: