The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review.

Falls are a common problem associated with significant morbidity, mortality, and economic costs. Current fall prevention policies in local healthcare settings are often guided by information provided by fall risk assessment tools, incident reporting, and coding data. This review was conducted with the aim of identifying studies which utilized natural language processing (NLP) for the automated detection and prediction of falls in the healthcare setting. The databases Ovid Medline, Ovid Embase, Ovid Emcare, PubMed, CINAHL, IEEE Xplore, and Ei Compendex were searched from 2012 until April 2023. Retrospective derivation, validation, and implementation studies wherein patients experienced falls within a healthcare setting were identified for inclusion. The initial search yielded 2611 publications for title and abstract screening. Full-text screening was conducted on 105 publications, resulting in 26 unique studies that underwent qualitative analyses. Studies applied NLP towards falls risk factor identification, known falls detection, future falls prediction, and falls severity stratification with reasonable success. The NLP pipeline was reviewed in detail between studies and models utilizing rule-based, machine learning (ML), deep learning (DL), and hybrid approaches were examined. With a growing literature surrounding falls prediction in both inpatient and outpatient environments, the absence of studies examining the impact of these models on patient and system outcomes highlights the need for further implementation studies. Through an exploration of the application of NLP techniques, it may be possible to develop models with higher performance in automated falls prediction and detection.

Falls and fractures in the acute care setting: A retrospective cohort study.

OBJECTIVES: Falls with fracture in hospitalised patients remain a common occurrence with significant morbidity and mortality. Our objectives were to determine the characteristics of patients who suffer falls with fractures in hospital, and to examine whether outcomes in this cohort differ from those of patients who fall without sustaining a fracture. METHODS: Coding data pertaining to a 6-year period (2012-2017) were interrogated. Patients coded as having suffered a fall in hospital during this period were identified and divided into those who did and those who did not suffer fractures due to their fall. Patient demographics and comorbidities were compared between groups and outcome measures examined with descriptive statistics and binary logistic regression. RESULTS: From 236,720 inpatient admissions, 721 falls were recorded, 128 of which were associated with a fracture. Delirium (30% in those who suffered a fracture vs. 21% in those who did not, p < 0.040), dementia (23% vs. 13%, p < 0.004), female sex (53% vs. 44%, p < 0.020) and older age (76.8 vs. 72.8 years, p < 0.010) were associated with falls with fractures in hospital. Falls with fractures were associated with a longer length of inpatient stay by 9.2 days (95% CI 5.5-12.9, p < 0.001) and were an independent predictor of inpatient mortality. CONCLUSIONS: Greater understanding of characteristics of patients at risk of falls with fractures, as well as knowledge of the considerable associated morbidity and mortality, will help to prognosticate when these events occur and, potentially, to put preventative measures in place.