External validation of a new predictive model for falls among inpatients using the official Japanese ADL scale, Bedriddenness ranks: a double-centered prospective cohort study

Using machine learning models to predict falls in hospitalised adults

BACKGROUND

Identifying patients at high risk of falling is crucial in implementing effective fall prevention programs. While the integration of information systems is becoming more widespread in the healthcare industry, it poses a significant challenge in analysing vast amounts of data to identify factors that could enhance patient safety.

OBJECTIVE

To determine fall-associated factors and develop high-performance prediction tools for at-risk patients in acute and sub-acute care services in Australia.

METHODS

A retrospective study of 672,400 patients admitted to acute and sub-acute care services within a large metropolitan tertiary health service in Victoria, Australia, between January 1, 2019, and December 31, 2021. Data were obtained from four sources: the Department of Health Victorian Admitted Episodes Dataset, RiskManTM, electronic health records, and the health workforce dataset. Machine learning techniques, including Random Forest and Deep Neural Network models, were used to analyse the data, predict patient falls, and identify the most important risk factors for falls in this population. Model performance was evaluated using accuracy, F1-score, precision, recall, specificity, Matthew's correlation coefficient, and the area under the receiver operating characteristic curve (AUC).

RESULTS

The deep neural network and random forest models were highly accurate in predicting hospital patient falls. The deep neural network model achieved an accuracy of 0.988 and a specificity of 0.999, while the RF achieved an accuracy of 0.989 and a specificity of 1.000. The top 20 variables impacting falls were compared across both models, and 12 common factors were identified. These factors can be broadly classified into three categories: patient-related factors, staffing-related factors, and admission-related factors. Although not all factors are modifiable, they must be considered when planning fall prevention interventions.

CONCLUSION

The study demonstrated machine learning's potential to predict falls and identify key risk factors. Further validation across diverse populations and settings is essential for broader applicability.

Validation and Improvement of the Saga Fall Risk Model: A Multicenter Retrospective Observational Study

Purpose

We conducted a pilot study in an acute care hospital and developed the Saga Fall Risk Model 2 (SFRM2), a fall prediction model comprising eight items: Bedriddenness rank, age, sex, emergency admission, admission to the neurosurgery department, history of falls, independence of eating, and use of hypnotics. The external validation results from the two hospitals showed that the area under the curve (AUC) of SFRM2 may be lower in other facilities. This study aimed to validate the accuracy of SFRM2 using data from eight hospitals, including chronic care hospitals, and adjust the coefficients to improve the accuracy of SFRM2 and validate it.

Patients and Methods

This study included all patients aged ≥20 years admitted to eight hospitals, including chronic care, acute care, and tertiary hospitals, from April 1, 2018, to March 31, 2021. In-hospital falls were used as the outcome, and the AUC and shrinkage coefficient of SFRM2 were calculated. Additionally, SFRM2.1, which was modified from the coefficients of SFRM2 using logistic regression with the eight items comprising SFRM2, was developed using two-thirds of the data randomly selected from the entire population, and its accuracy was validated using the remaining one-third portion of the data.

Results

Of the 124,521 inpatients analyzed, 2,986 (2.4%) experienced falls during hospitalization. The median age of all inpatients was 71 years, and 53.2% were men. The AUC of SFRM2 was 0.687 (95% confidence interval [CI]:0.678-0.697), and the shrinkage coefficient was 0.996. SFRM2.1 was created using 81,790 patients, and its accuracy was validated using the remaining 42,731 patients. The AUC of SFRM2.1 was 0.745 (95% CI: 0.731-0.758).

Conclusion

SFRM2 showed good accuracy in predicting falls even on validating in diverse populations with significantly different backgrounds. Furthermore, the accuracy can be improved by adjusting the coefficients while keeping the model's parameters fixed.

Effects of Caregiver's Gender or Distance Between Caregiver and Patient's Home on Home Discharge from Hospital in 285 Patients Aged ≥75 Years in Japan

BACKGROUND Many hospitalized aged patients in Japan, the most super-aged society, are unable to be discharged home. This study was performed to clarify the factors associated with home discharge, not to a long-term care (LTC) facility or another hospital, among inpatients aged ≥75 years. MATERIAL AND METHODS A single-center prospective cohort study was performed for inpatients aged ≥75 years in a rural acute-care hospital in Japan, from November 2017 to October 2019. We divided the patients into 2 groups: those who resided at home or had died at home by 30 days after discharge, and others. We obtained data from medical charts and questionnaires given to patients and their caregivers. For each factor shown to be statistically significant by the univariable analysis, a multivariable analysis with adjustment was conducted. RESULTS In all, 285 patients agreed to participate. With adjustment by where the patient was admitted from, residing with other family members, cognitive function scores, and Barthel index, multivariable analysis using each factor identified as relevant by univariable analysis identified the following as associated with home discharge: being less informed about LTC insurance; cost of home-visit medical, nursing, or LTC services; shorter hospital stays; close proximity between patient and caregiver; main caregiver being female; and life expectancy of over 6 months (P<0.05). CONCLUSIONS Male gender and a long distance between the caregiver and patient's home significantly hindered home discharge in patients aged ≥75 years, suggesting the need to provide information regarding home-visit services under Japan's LTC insurance system for such caregivers.

History of Falls and Bedriddenness Ranks are Useful Predictive Factors for in-Hospital Falls: A Single-Center Retrospective Observational Study Using the Saga Fall Risk Model

INTRODUCTION

In our former study, we had validated the previously developed predictive model for in-hospital falls (Saga fall risk model) using eight simple factors (age, sex, emergency admission, department of admission, use of hypnotic medications, history of falls, independence of eating, and Bedriddenness ranks [BRs]), proving its high reliability. We found that only admission to the neurosurgery department, history of falls, and BRs had significant relationships with falls. In the present study, we aimed to clarify whether each of these three items had a significant relationship with falls in a different group of patients.

METHODS

This was a single-center based, retrospective study in an acute care hospital in a rural city of Japan. We enrolled all inpatients aged 20 years or older admitted from April 2015 to March 2018. We randomly selected patients to fulfill the required sample size. We performed multivariable logistic regression analysis using forced entry on the association between falls and each of the eight items in the Saga fall risk model 2.

RESULTS

A total of 2932 patients were randomly selected, of whom 95 (3.2%) fell. The median age was 79 years, and 49.9% were men. Multivariable analysis showed that female sex (odds ratio [OR] 0.6, 95% confidence interval [CI] 0.39-0.93, p = 0.022), having a history of falls (OR 1.9, 95% CI 1.16-2.99, p = 0.010), requiring help with eating (OR 1.9, 95% CI 1.12-3.35, p = 0.019), BR of A (OR 6.6, 95% CI 2.82-15.30, p < 0.001), BR of B (OR 7.5, 95% CI 2.95-19.06, p < 0.001), and BR of C (OR 4.1, 95% CI 1.53-11.04, p = 0.005) were significantly associated with falls.

CONCLUSION

History of falls and BRs were independently associated with in-hospital falls.