Designing a Fall Prediction Model for Inpatient Rehabilitation Facilities Using Readily Available Data.

OBJECTIVE: To create a fall risk assessment tool for inpatient rehabilitation facilities (IRFs) using available data and compare its predictive accuracy with that of the Morse Fall Scale (MFS). DESIGN: We conducted a secondary analysis from a retrospective cohort study. Using a nomogram that displayed the contributions of QI codes associated with falls in a multivariable logistic regression model, we created a novel fall risk assessment, the Inpatient Rehabilitation Fall Scale (IRF Scale). To compare the predictive accuracy of the IRF Scale and MFS, we used receiver operator characteristic (ROC) curve analysis. SETTING: We included data from 4 IRFs owned and operated by Intermountain Health. PARTICIPANTS: Data came from the medical records of 1699 patients. All participants were over the age of 14 and were admitted and discharged from 1 of the 4 sites between January 1 and December 31, 2020. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURE(S): We assigned point values on the IRF Scale based on the adjusted associations of QI codes with falls. Using ROC curve analysis, we discovered an optimal cutoff score, sensitivity, specificity, and overall AUC of the IRF Scale and MFS. RESULTS: ROC curve analysis revealed the optimal IRF Scale cutoff score of 22.4 yielded a sensitivity of 0.74 and a specificity of 0.63. With an AUC of 0.72, the IRF Scale demonstrated acceptable accuracy at identifying patients who fell in our retrospective cohort. CONCLUSIONS: Because the IRF Scale uses readily available data, it minimizes staff assessment and outperforms the MFS at identifying patients who previously fell. Prospective research is needed to investigate if it can adequately identify in advance which patients will fall during their IRF stay.

Using Quality Indicator Codes to Identify Patients' Fall Risk in Inpatient Rehabilitation Facilities.

OBJECTIVE: To discover if quality indicator (QI) codes are associated with patient falls in inpatient rehabilitation facilities (IRFs). DESIGN: This retrospective cohort study explored differences between patients who fell and those who did not fall. We analyzed potential associations between QI codes and falls using univariable and multivariable logistic regression models. SETTING: We collected data from electronic medical records at 4 IRFs. PARTICIPANTS: In 2020, our 4 data collection sites admitted and discharged a total of 1742 patients older than 14 years . We only excluded patients (N=43) from statistical analysis if they were discharged before admission data had been assigned. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Using a data extraction report, we collected age, sex, race and ethnicity, diagnosis, falls, and QI codes for communication, self-care, and mobility performance. Staff documented communication codes on a 1-4 scale and self-care and mobility codes on a 1-6 scale, with higher codes representing greater independence. RESULTS: Ninety-seven patients (5.71%) fell in the 4 IRFs over a 12-month period. The group who fell had lower QI codes for communication, self-care, and mobility. When adjusting for bed mobility, transfer, and stair-climbing ability, low performance with understanding, walking 10 feet, and toileting were significantly associated with falls. Patients with admission QI codes below 4 for understanding had 78% higher odds of falling. If they were assigned admission QI codes below 3 for walking 10 feet or toileting, they had 2 times greater odds of falling. We did not find a significant association between falls and patients' diagnosis, age, sex, or race and ethnicity in our sample. CONCLUSIONS: Communication, self-care, and mobility QI codes appear to be significantly associated with falls. Future research should explore how to use these required codes to better identify patients likely to fall in IRFs.