Fall Risk Program for Oncology Inpatients: Addition of the "Traffic Light" Fall Risk Assessment Tool

Interventions to Prevent Falls and Injuries in Inpatient Oncology Units: A Scoping Review

BACKGROUND

Individuals with cancer are at a heightened risk of experiencing falls and related injuries during hospitalization.

PURPOSE

Our aim was to systematically summarize and evaluate the literature examining the effectiveness of fall prevention interventions employed in the oncology inpatient setting.

METHODS

Guided by the PRISMA statement, a health librarian conducted searches of 5 databases, which uncovered 1039 unduplicated studies that were screened by 2 independent reviewers. The Quality Improvement Minimum Quality Criteria Set was used to evaluate methodological quality.

RESULTS

The 10 quality improvement studies all included a multifactorial intervention and most based these on an assessment with few targeting cancer-specific factors. Most interventions were staff-focused with a few incorporating the patient's input.

CONCLUSIONS

Individualized assessments and interventions enhance care effectiveness when patient care teams and patients are aligned. Nurse rounding and engaging patients improve communication, self-assessment, satisfaction, and adherence, warranting further research and technological advancements.

Constructing a fall risk prediction model for hospitalized patients using machine learning

STUDY OBJECTIVES

This study aimed to identify the risk factors associated with falls in hospitalized patients, develop a predictive risk model using machine learning algorithms, and evaluate the validity of the model's predictions.

STUDY DESIGN

A cross-sectional design was employed using data from the DRYAD public database.

RESEARCH METHODS

The study utilized data from the Fukushima Medical University Hospital Cohort Study, obtained from the DRYAD public database. 20% of the dataset was allocated as an independent test set, while the remaining 80% was utilized for training and validation. To address data imbalance in binary variables, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was applied. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to analyze and screen variables. Predictive models were constructed by integrating key clinical features, and eight machine learning algorithms were evaluated to identify the most effective model. Additionally, SHAP (Shapley Additive Explanations) was used to interpret the predictive models and rank the importance of risk factors.

RESULTS

The final model included the following variables: Adl_standing, Adl_evacuation, Age_group, Planned_surgery, Wheelchair, History_of_falls, Hypnotic_drugs, Psychotropic_drugs, and Remote_caring_system. Among the evaluated models, the Random Forest algorithm demonstrated superior performance, achieving an AUC of 0.814 (95% CI: 0.802-0.827) in the training set, 0.781 (95% CI: 0.740-0.821) in the validation set, and 0.795 (95% CI: 0.770-0.820) in the test set.

CONCLUSION

Machine learning algorithms, particularly Random Forest, are effective in predicting fall risk among hospitalized patients. These findings can significantly enhance fall prevention strategies within healthcare settings.

Optimizing Post-Acute Care Patient Safety: A Scoping Review of Multifactorial Fall Prevention Interventions for Older Adults

Accidental falls are preventable adverse events for older post-acute care (PAC) patients. Yet, due to the functional and medical care needs of this population, there is little guidance to inform multidisciplinary prevention efforts. This scoping review aims to characterize the evidence for multifactorial PAC fall prevention interventions. Of the 33 included studies, common PAC intervention domains included implementing facility-based strategies (e.g., staff education), evaluating patient-specific fall risk factors (e.g., function), and developing an individualized risk profile and treatment plan that targets the patient's constellation of fall risk factors. However, there was variability across studies in how and to what extent the domains were addressed. While further research is warranted, health system efforts to prevent accidental falls in PAC should consider a patient-centered multifactorial approach that fosters a culture of safety, addresses individuals' fall risk, and champions a multidisciplinary team.

Increased Mobility and Fall Reduction: An Interdisciplinary Approach on a Hematology-Oncology and Stem Cell Transplantation Unit

Patients in the hematology-oncology and stem cell transplantation (SCT) setting are at high risk for functional decline and falls related to prolonged hospitalizations and inactivity during inpatient treatment. After underperforming on the Press Ganey National Database of Nursing Quality Indicators benchmark for falls in 2018, staff on a hematology-oncology and SCT unit implemented a practical and evidence-based fall prevention program. Fall rates from 2018 to 2019 ranged from 3.4 to 4.8 falls per 1,000 patient days. After the introduction of the unit-based gym program, early mobility increased and falls decreased to 2.57 per 1,000 patient days.

Preserving Well-being in Patients With Advanced and Late Prostate Cancer

Androgen deprivation therapy, alone or in combination with androgen signaling inhibitors, is a treatment option for patients with advanced prostate cancer (PC). When making treatment decisions, health care providers must consider the long-term effects of treatment on the patient's overall health and well-being. Herein, we review the effects of these treatments on the musculoskeletal and cardiovascular systems, cognition, and fall risk, and provide management approaches for each. We also include an algorithm to help health care providers implement best clinical practices and interdisciplinary care for preserving the overall well-being of PC patients.

Factors included in adult fall risk assessment tools (FRATs): a systematic review

Falls often have severe financial and environmental consequences, not only for those who fall, but also for their families and society at large. Identifying fall risk in older adults can be of great use in preventing or reducing falls and fall risk, and preventative measures that are then introduced can help reduce the incidence and severity of falls in older adults. The overall aim of our systematic review was to provide an analysis of existing mechanisms and measures for evaluating fall risk in older adults. The 43 included FRATs produced a total of 493 FRAT items which, when linked to the ICF, resulted in a total of 952 ICF codes. The ICF domain with the most used codes was body function, with 381 of the 952 codes used (40%), followed by activities and participation with 273 codes (28%), body structure with 238 codes (25%) and, lastly, environmental and personal factors with only 60 codes (7%). This review highlights the fact that current FRATs focus on the body, neglecting environmental and personal factors and, to a lesser extent, activities and participation. This over-reliance on the body as the point of failure in fall risk assessment clearly highlights the need for gathering qualitative data, such as from focus group discussions with older adults, to capture the perspectives and views of the older adults themselves about the factors that increase their risk of falling and comparing these perspectives to the data gathered from published FRATs as described in this review.

A Protocol-Driven, Bedside Digital Conversational Agent to Support Nurse Teams and Mitigate Risks of Hospitalization in Older Adults: Case Control Pre-Post Study

BACKGROUND

Hospitalized older adults often experience isolation and disorientation while receiving care, placing them at risk for many inpatient complications, including loneliness, depression, delirium, and falls. Embodied conversational agents (ECAs) are technological entities that can interact with people through spoken conversation. Some ECAs are also relational agents, which build and maintain socioemotional relationships with people across multiple interactions. This study utilized a novel form of relational ECA, provided by Care Coach (care.coach, inc): an animated animal avatar on a tablet device, monitored and controlled by live health advocates. The ECA implemented algorithm-based clinical protocols for hospitalized older adults, such as reorienting patients to mitigate delirium risk, eliciting toileting needs to prevent falls, and engaging patients in social interaction to facilitate social engagement. Previous pilot studies of the Care Coach avatar have demonstrated the ECA's usability and efficacy in home-dwelling older adults. Further study among hospitalized older adults in a larger experimental trial is needed to demonstrate its effectiveness.

OBJECTIVE

The aim of the study was to examine the effect of a human-in-the-loop, protocol-driven relational ECA on loneliness, depression, delirium, and falls among diverse hospitalized older adults.

METHODS

This was a clinical trial of 95 adults over the age of 65 years, hospitalized at an inner-city community hospital. Intervention participants received an avatar for the duration of their hospital stay; participants on a control unit received a daily 15-min visit from a nursing student. Measures of loneliness (3-item University of California, Los Angeles Loneliness Scale), depression (15-item Geriatric Depression Scale), and delirium (confusion assessment method) were administered upon study enrollment and before discharge.

RESULTS

Participants who received the avatar during hospitalization had lower frequency of delirium at discharge (P<.001), reported fewer symptoms of loneliness (P=.01), and experienced fewer falls than control participants. There were no significant differences in self-reported depressive symptoms.

CONCLUSIONS

The study findings validate the use of human-in-the-loop, relational ECAs among diverse hospitalized older adults.