Evaluation of an approach to clinical decision support for preventing inpatient falls: a pragmatic trial. Issue 2 (6th April 2023)

• Record Type: Journal Article
• Authors: Cho, Insook; Kim, MiSoon; Song, Mi Ra; Dykes, Patricia C
• Is Part Of: JAMIA open. Volume 6:Issue 2(2023)
• Publication Date: 2023-04-06
• Subjects: inpatient falls -- clinical decision support -- machine learning -- prediction model -- clinical evaluation -- tailored interventions; Medical informatics -- Periodicals; 610.285
• DOI: 10.1093/jamiaopen/ooad019
• Languages: English
• ISSNs: 2574-2531

Abstract

Abstract: Objectives: To assess whether a fall-prevention clinical decision support (CDS) approach using electronic analytics that stimulates risk-targeted interventions is associated with reduced rates of falls and injurious falls. Materials and Methods: The CDS intervention included a machine-learning prediction algorithm, individual risk-factor identification, and guideline-based prevention recommendations. After a 5-month plan-do-study-act quality improvement initiative, the CDS intervention was implemented at an academic tertiary hospital and compared with the usual care using a pretest (lasting 24 months and involving 23 498 patients) and posttest (lasting 13 months and involving 17 341 patients) design in six nursing units. Primary and secondary outcomes were the rates of falls and injurious falls per 1000 hospital days, respectively. Outcome measurements were tested using a priori Poisson regression and adjusted with patient-level covariates. Subgroup analyses were conducted according to age. Results: The age distribution, sex, hospital and unit lengths of stay, number of secondary diagnoses, fall history, condition at admission, and overall fall rate per 1000 hospital days did not differ significantly between the intervention and control periods before (1.88 vs 2.05, respectively, P = .1764) or after adjusting for demographics. The injurious-falls rate per 1000 hospital days decreased significantly before (0.68 vs 0.45, P = .0171) and after (rate difference = –0.64, P = .0212) adjusting for demographics. The differences in injury rates were greater among patients aged at least 65 years. Conclusions: This study suggests that a well-designed CDS intervention employing electronic analytics was associated with a decrease in fall-related injuries. The benefits from this intervention were greater in elderly patients aged at least 65 years. Trial Registration: This study was conducted as part of a more extensive study registered with the Clinical Research Information Service (CRIS) (KCT0005378). Lay Summary: Falls are the most common adverse event and a leading cause of injuries among hospital inpatients. Multiple clinical guidelines recommend providing individualized risk-factor-tailored interventions, which are not always implemented in practice, and some interventions do not match the identified risk factors. To help nurses with the considerable cognitive burden of patient falls, this study designed and implemented a clinical decision support (CDS) system for fall prevention based on electronic medical records using the plan-do-study-act quality-improvement process in a collaboration between academic and clinical research staff. The CDS system informs nurses about which patients are at risk in the next 1-h period, individual risk factors, and what interventions should be provided. To evaluate the effectiveness of the fall-prevention CDS system, a clustered pretest (lasting 24 months) and posttest (lasting 13 months) were conducted at an academic tertiary hospital and involved 40 839 patients admitted to six nursing units. The CDS intervention helped to reduce the injurious fall rates, with the benefit being greater for patients aged 65 years and older, but it did not significantly influence the fall rate. It is estimated that the CDS intervention could prevent 28 fall injuries yearly in the six studied units.