Inpatient Fall Prediction Models: A Scoping Review

Abstract

<b><i>Introduction:</i></b> The digitization of hospital systems, including integrated electronic medical records, has provided opportunities to improve the prediction performance of inpatient fall risk models and their application to computerized clinical decision support systems. This review describes the data sources and scope of methods reported in studies that developed inpatient fall prediction models, including machine learning and more traditional approaches to inpatient fall risk prediction. <b><i>Methods:</i></b> This scoping review used methods recommended by the Arksey and O’Malley framework and its recent advances. PubMed, CINAHL, IEEE Xplore, and EMBASE databases were systematically searched. Studies reporting the development of inpatient fall risk prediction approaches were included. There was no restriction on language or recency. Reference lists and manual searches were also completed. Reporting quality was assessed using adherence to Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis statement (TRIPOD), where appropriate. <b><i>Results:</i></b> Database searches identified 1,396 studies, 63 were included for scoping assessment and 45 for reporting quality assessment. There was considerable overlap in data sources and methods used for model development. Fall prediction models typically relied on features from patient assessments, including indicators of physical function or impairment, or cognitive function or impairment. All but two studies used patient information at or soon after admission and predicted fall risk over the entire admission, without consideration of post-admission interventions, acuity changes or length of stay. Overall, reporting quality was poor, but improved in the past decade. <b><i>Conclusion:</i></b> There was substantial homogeneity in data sources and prediction model development methods. Use of artificial intelligence, including machine learning with high-dimensional data, remains underexplored in the context of hospital falls. Future research should consider approaches with the potential to utilize high-dimensional data from digital hospital systems, which may contribute to greater performance and clinical usefulness.

A systematic review of fall prediction models for community-dwelling older adults: comparison between models based on research cohorts and models based on routinely collected data

“…Consequently, many of the included models are not available in a format such that they can be used, reproduced and critically evaluated, which hinders their translation into clinical practice [ 5 ]. This trend of suboptimal reporting has also been observed in several other systematic reviews on falls [ 14 , 53 , 54 ] and other domains [ 55–57 ].…”

A Fall Risk Assessment Model for Community-Dwelling Elderly Individuals Based on Gait Parameters

“…However, these methods have low sensitivity and specificity because falls are caused by multiple and complex factors [13], [14]. Furthermore, these methods are subjective and their applicability is often limited to a specific setting or population [14], [15]. It has been argued that no single fall risk assessment tool is significantly superior and none can accurately determine falls with high efficiency and confidence [16], [17].…”

Development of a Machine Learning-Based Model to Predict Timed-Up-and-Go Test in Older Adults

“…The reporting quality was generally poor, but it has improved over the past decade. The review recommends exploring artificial intelligence and machine learning with high-dimensional data from digital hospital systems to enhance fall risk prediction in hospitals [9].…”