Impact of a Clinical Text–Based Fall Prediction Model on Preventing Extended Hospital Stays for Elderly Inpatients: Model Development and Performance Evaluation

Abstract

Background Falls may cause elderly people to be bedridden, requiring professional intervention; thus, fall prevention is crucial. The use of electronic health records (EHRs) is expected to provide highly accurate risk assessment and length-of-stay data related to falls, which may be used to estimate the costs and benefits of prevention. However, no studies to date have investigated the extent to which hospital stays could be shortened through fall avoidance resulting from the use of prediction tools. Objective We first estimated the extended length of hospital stay caused by falls among elderly inpatients. Next, we developed a model that predicts falls using clinical text as input and evaluated its accuracy. Finally, we estimated the potentially shortened hospital stay that would be made possible by appropriate interventions based on the prediction model. Methods Patients aged 65 years or older were selected as subjects, and the EHRs of 1728 falls and 70,586 nonfalls were subjected to analysis. The extended-stay lengths were estimated using propensity score matching of 49 associated variables. Bidirectional encoder representations from transformers and bidirectional long short-term memory methods were used to predict falls from clinical text. The estimated length of stay and the outputs of the prediction model were used to determine stay reductions. Results The extended length of hospital stay due to falls was estimated to be 17.8 days (95% CI 16.6-19.0), which dropped to 8.6 days when there were unobserved covariates at an odds ratio of 2.0. The accuracy of the prediction model was as follows: area under the receiver operating characteristic curve, 0.851; F-value, 0.165; recall, 0.737; precision, 0.093; and specificity, 0.839. When assuming interventions with 25% or 100% effectiveness against cases where the model predicted a fall, the stay reduction was estimated at 0.022 and 0.099 days/day, respectively. Conclusions The accuracy of the prediction model using clinical text is considered to be higher than the prediction accuracy of conventional assessments. However, our model’s precision remained low at 9.3%. This may be due, in part, to the inclusion of cases in which falls did not occur because of preventative interventions during hospitalization. Nonetheless, it is estimated that interventions for cases when falls were predicted will reduce medical costs by 886 Yen/day (~US $6.50/day) of intervention, even if the preventative effect is 25%. Limitations include the fact that these results cannot be extrapolated to short- or long-term hospitalization cases, and that this was a single-center study.

Time-Varying Hazard of Patient Falls in Hospital: A Retrospective Case–Control Study

“…This study reported that the fall group had a longer length of stay with 11.86 days than the non-fall group with 7.34 days, which was comparable to the result of the previous study that the faller group tended to be with a longer hospital stay [33]. On the other hand, there was a previous study showing a converse relationship that the extended length of hospital stay was due to patient falls [34]. Therefore, we estimated the relative odds and relative hazard in patient falls according to the length of stay in hospital.…”

Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms

“…The absence of external validation is another significant limitation, as it is crucial for confirming the efficacy and robustness of our models. Finally, the dependency of radiomics and deep learning models on imaging quality means that variations in (46)(47)(48). Therefore, due to the small sample size in our study, we did not adopt this model methodology.…”

Improving postsurgical fall detection for older Americans using LLM-driven analysis of clinical narratives

“…LLMs are powerful and can be used for fall detection. Current literature has explored other tools that have identified fall events within controlled settings with very high sensitivities and specificities 12,13 . However, these approaches have largely been institution-specific and have relied on large annotated datasets which are cumbersome to produce.…”

“…Their approach examined how to balance false positives and false negatives with multiple models. Kawazoe et al (2022) 12 developed an approach using structured data and BERT to classify clinical notes written in Japanese to detect and predict falls. Their approach had good sensitivity (0.74) and specificity (0.84) but low PPV (0.09).…”