Improved accuracy and efficiency of primary care fall risk screening of older adults using a machine learning approach.

BACKGROUND: While many falls are preventable, they remain a leading cause of injury and death in older adults. Primary care clinics largely rely on screening questionnaires to identify people at risk of falls. Limitations of standard fall risk screening questionnaires include suboptimal accuracy, missing data, and non-standard formats, which hinder early identification of risk and prevention of fall injury. We used machine learning methods to develop and evaluate electronic health record (EHR)-based tools to identify older adults at risk of fall-related injuries in a primary care population and compared this approach to standard fall screening questionnaires. METHODS: Using patient-level clinical data from an integrated healthcare system consisting of 16-member institutions, we conducted a case-control study to develop and evaluate prediction models for fall-related injuries in older adults. Questionnaire-derived prediction with three questions from a commonly used fall risk screening tool was evaluated. We then developed four temporal machine learning models using routinely available longitudinal EHR data to predict the future risk of fall injury. We also developed a fall injury-prevention clinical decision support (CDS) implementation prototype to link preventative interventions to patient-specific fall injury risk factors. RESULTS: Questionnaire-based risk screening achieved area under the receiver operating characteristic curve (AUC) up to 0.59 with 23% to 33% similarity for each pair of three fall injury screening questions. EHR-based machine learning risk screening showed significantly improved performance (best AUROC = 0.76), with similar prediction performance between 6-month and one-year prediction models. CONCLUSIONS: The current method of questionnaire-based fall risk screening of older adults is suboptimal with redundant items, inadequate precision, and no linkage to prevention. A machine learning fall injury prediction method can accurately predict risk with superior sensitivity while freeing up clinical time for initiating personalized fall prevention interventions. The developed algorithm and data science pipeline can impact routine primary care fall prevention practice.

Cost of Inpatient Falls and Cost-Benefit Analysis of Implementation of an Evidence-Based Fall Prevention Program.

Importance: There is insufficient research on the costs of patient falls in health care systems, a leading source of nonreimbursable adverse events. Objective: To report the costs of inpatient falls and the cost savings associated with implementation of an evidence-based fall prevention program. Design, Setting, and Participants: In this economic evaluation, a matched case-control study used the findings from an interrupted time series analysis that assessed changes in fall rates following implementation of an evidence-based fall prevention program to understand the cost of inpatient falls. An economic analysis was then performed to assess the cost benefits associated with program implementation across 2 US health care systems from June 1, 2013, to August 31, 2019, in New York, New York, and Boston, Massachusetts. All adults hospitalized in participating units were included in the analysis. Data analysis was performed from October 2021 to November 2022. Interventions: Evidence-based fall prevention program implemented in 33 medical and surgical units in 8 hospitals. Main Outcomes and Measures: Primary outcome was cost of inpatient falls. Secondary outcome was the costs and cost savings associated with the evidence-based fall prevention program. Results: A total of 10 176 patients who had a fall event (injurious or noninjurious) with 29 161 matched controls (no fall event) were included in the case-control study and the economic analysis (51.9% were 65-74 years of age, 67.1% were White, and 53.6% were male). Before the intervention, there were 2503 falls and 900 injuries; after the intervention, there were 2078 falls and 758 injuries. Based on a 19% reduction in falls and 20% reduction in injurious falls from the beginning to the end of the postintervention period, the economic analysis demonstrated that noninjurious and injurious falls were associated with cost increases of $35 365 and $36 776, respectively. The implementation of the evidence-based fall prevention program was associated with $14 600 in net avoided costs per 1000 patient-days. Conclusions and Relevance: This economic evaluation found that fall-related adverse events represented a clinical and financial burden to health care systems and that the current Medicare policy limits reimbursement. In this study, costs of falls only differed marginally by injury level. Policies that incentivize organizations to implement evidence-based strategies that reduce the incidence of all falls may be effective in reducing both harm and costs.

Development and Validation of a Fall Prevention Efficiency Scale.

OBJECTIVES: Fall TIPS (Tailoring Interventions for Patient Safety) is an evidence-based fall prevention program that led to a 25% reduction in falls in hospitalized adults. Because it would be helpful to assess nurses' perceptions of burdens imposed on them by using Fall TIPS or other fall prevention program, we conducted a study to learn benefits and burdens. METHODS: A 3-phase mixed-method study was conducted at 3 hospitals in Massachusetts and 3 in New York: (1) initial qualitative, elicited and categorized nurses' views of time spent implementing Fall TIPS; (2) second qualitative, used nurses' quotes to develop items, research team inputs for refinement and organization, and clinical nurses' evaluation and suggestions to develop the prototype scale; and (3) quantitative, evaluated psychometric properties. RESULTS: Four "time" themes emerged: (1) efficiency, (2) inefficiency, (3) balances out, and (4) valued. A 20-item prototype Fall Prevention Efficiency Scale was developed, administered to 383 clinical nurses, and reduced to 13 items. Individual items demonstrated robust stability with Pearson correlations of 0.349 to 0.550 and paired t tests of 0.155 to 1.636. Four factors explained 74.3% variance and provided empirical support for the scale's conceptual basis. The scale achieved excellent internal consistency values (0.82-0.92) when examined with the test, validation, and paired (both test and retest) samples. CONCLUSIONS: This new scale assess nurses' perceptions of how a fall prevention program affects their efficiency, which impacts the likelihood of use. Learning nurses' beliefs about time wasted when implementing new programs allows hospitals to correct problems that squander time.

Use of a perceived efficacy tool to evaluate the FallTIPS program.

BACKGROUND/OBJECTIVES: To assess nurses' opinions of the efficacy of using the FallTIPS (Tailoring Interventions for Patient Safety) fall prevention program. DESIGN: Survey research. SETTING: Seven adult acute-care hospitals in 2 hospital centers located in Boston and NYC. PARTICIPANTS: A total of 298 medical-surgical nurses on 14 randomly selected units. INTERVENTION: Three-step FallTIPS fall prevention program that had been in use as a clinical program for a minimum of 2 years in each hospital. MEASUREMENTS: Fall Prevention Efficiency Scale (FPES), range 13-52; four-factorilly derived subscales: valued, efficiency, balances out and inefficiency; and 13 psychometrically validated individual items. RESULTS: Nurses perceived the FallTIPS fall prevention program to be efficacious. The FPES mean score of 38.55 (SD = 5.05) and median of 39 were well above the lowest possible score of 13 and scale midpoint of 32.5. Most nurses (N = 270, 90.6%) scored above 33. There were no differences in FPES scores between nurses who had only used FallTIPS and nurses who had previously used a different fall prevention program. CONCLUSION: The nurses who used FallTIPS perceived that efficiencies in patient care compensated for the time spent on FallTIPS. Nurses valued the program and findings confirmed the importance of patient and family engagement with staff in the fall prevention process. Regardless of the fall prevention program used, organizations should examine staff perceptions of their fall prevention program because programs that are not perceived as being useful, efficient, and valuable will lead to nonadherence over time and then will not reduce falls and injuries. The recently developed FPES used in this study is a brief tool available for organizations to assess nurses' perceptions of the efficacy of their fall prevention program. Additional FPES research is needed with larger and more diverse samples.

Classification of Injurious Fall Severity in Hospitalized Adults.

BACKGROUND: Many hospital systems in the United States report injurious inpatient falls using the National Database of Nursing Quality Indicators categories: None, Minor, Moderate, Major, and Death. The Major category is imprecise, including injuries ranging from a wrist fracture to potentially fatal subdural hematoma. The purpose of this project was to refine the Major injury classification to derive a valid and reliable categorization of the types and severities of Major inpatient fall-related injuries. METHODS: Based on published literature and ranking of injurious fall incident reports (n = 85) from a large Academic Medical Center, we divided the National Database of Nursing Quality Indicators Major category into three subcategories: Major A-injuries that caused temporary functional impairment (eg, wrist fracture), major facial injury without internal injury (eg, nasal bone fracture), or disruption of a surgical wound; Major B-injuries that caused long-term functional impairment or had the potential risk of increased mortality (eg, multiple rib fractures); and Major C-injuries that had a well-established risk of mortality (eg, hip fracture). Based on the literature and expert opinion, our research team reached consensus on an administration manual to promote accurate classification of Major injuries into one of the three subcategories. RESULTS: The team tested and validated each of the categories which resulted in excellent interrater reliability (kappa = .96). Of the Major injuries, the distribution of Major A, B, and C was 40.3%, 16.1%, and 43.6%, respectively. CONCLUSIONS: These subcategories enhance the National Database of Nursing Quality Indicators categorization. Using the administration manual, trained personnel can classify injurious fall severity with excellent reliability.

Safety and utility of acute electroconvulsive therapy for agitation and aggression in dementia.

OBJECTIVE: Agitation and aggression are among the most frequent and disruptive behavioral complications of dementia that contribute to increased cost of care, hospitalization, caregiver burden, and risk of premature institutionalization. This current study examined the safety and efficacy of electroconvulsive therapy (ECT) as a treatment for behavioral disturbances in dementia. We hypothesized that ECT would result in reduced agitated and aggressive behaviors between baseline and discharge. METHODS: Twenty-three participants admitted to McLean Hospital (Belmont, MA, USA) and Pine Rest Christian Mental Health Services (Grand Rapids, MI, USA), with a diagnosis of dementia who were referred for ECT to treat agitation and/or aggression, were enrolled in the study. We administered the Cohen-Mansfield Agitation Inventory-Short Form, Neuropsychiatric Inventory-Nursing Home Version, Cornell Scale for Depression in Dementia, and the Clinical Global Impression Scale at baseline, during, and after the ECT course. RESULTS: Regression analyses revealed a significant decrease from baseline to discharge on the Cohen-Mansfield Agitation Inventory (F(4,8) = 13.3; p = 0.006) and Neuropsychiatric Inventory (F(4,31) = 14.6; p < 0.001). There was no statistically significant change in scores on the Cornell Scale for Depression in Dementia. The Clinical Global Impression scores on average changed from a rating of "markedly agitated/aggressive" at baseline to "borderline agitated/aggressive" at discharge. Treatment with ECT was well tolerated by most participants; discontinuation of ECT occurred for two participants because of recurrence of agitation and for three participants because of adverse events. CONCLUSIONS: Electroconvulsive therapy may be a safe treatment option to reduce symptoms of agitation and aggression in patients with dementia whose behaviors are refractory to medication management.

Sexual health and dissociative experiences among abused women.

Sexually transmitted infections are a significant public health issue impacting women. Intimate partner violence (IPV) is one risk factor for STIs/HIV. Women who are the victims of IPV often experience psychological difficulties, including dissociation. Dissociative symptoms may play a role in women's ability to practice safe sex and negotiate condom use, although this has been underexplored. This mixed methods study examined the dissociative symptoms of 22 women experiencing IPV and examined the ways in which these women described their own sexual health and behaviors as well as how they protected themselves from sexually transmitted infections and HIV.

A comparison of multisensory and traditional interventions on inpatient psychiatry and geriatric neuropsychiatry units.

Sensory rooms and the use of multisensory interventions are becoming popular in inpatient psychiatry. The empirical data supporting their use are limited, and there is only anecdotal evidence indicating effectiveness in psychiatric populations. The specific aims of this observational pilot study were to determine whether multisensory-based therapies were effective in managing psychiatric symptoms and to evaluate how these interventions compared to traditional ones used in the milieu. The study found that multisensory interventions were as effective as traditional ones in managing symptoms, and participants' Brief Psychiatric Rating Scale scores significantly improved following both kinds of intervention. Medication administration did not affect symptom reduction. This article explores how multisensory interventions offer choice in symptom management. Education regarding multisensory strategies should become integral to inpatient and outpatient group programs, in that additional symptom management strategies can only be an asset.

Report on an open-label prospective study of divalproex sodium for the behavioral and psychological symptoms of dementia as monotherapy and in combination with second-generation antipsychotic medication.

BACKGROUND: Studies of pharmacotherapy for agitation in dementia have primarily been limited to single-drug trials and have not determined if some forms of agitated behaviors are more responsive to treatment than others. OBJECTIVE: The goal of this study was to determine if manifestations of agitation (ie, physical aggression, physically nonaggressive behavior, and verbally agitated behaviors) show different degrees of response to divalproex sodium (extended release or sprinkles) alone or in combination with second-generation antipsychotic agents. METHODS: This was a 6-week, open-label, naturalistic pilot study of patients aged >60 years recruited from a geriatric psychiatry inpatient unit, 2 nursing homes, and 4 assisted living residences. Patients were referred for study if they displayed Behavioral and Psychological Symptoms of Dementia. The primary outcome measure was the Cohen-Mansfield Agitation Inventory (CMAI), an instrument whose subscales allow measurement of physically aggressive behaviors, physically nonaggressive behaviors (eg, wandering), and verbally agitated behaviors. The Neuropsychiatric Inventory-Nursing Home version (NPI-NH) was also used to assess patients' behavior. RESULTS: Fifteen patients were included in the study (10 men, 5 women; mean [SD] age, 81.9 [7.7] years). Total CMAI improved by 17.1% at week 1, showed an additional improvement of 3.4% at week 3, and no further improvement by week 6 (total score dropped by 1.1%). Aggressive behavior improved at weeks 3 and 6 while physically nonaggressive and verbally agitated behaviors improved at weeks 1 and 3, and lost much of the gains by week 6. The NPI-NH agitation/aggression score decreased a mean (SE) of 1.3 (0.5) points (P = 0.03), the irritability/lability subscale decreased a mean (SE) of 2.3 (0.6) points (P = 0.005), and the disinhibition subscale decreased a mean (SE) of 1.4 (0.4) points (P < 0.01). Seven patients were on divalproex monotherapy and 8 patients were on combination therapy. Daily doses of divalproex (mean dose, 656 mg/d) in combination with a second-generation antipsychotic were 28% lower than divalproex monotherapy (mean dose, 914 mg/d). The most common adverse events were somnolence (7 of 15) and gait disturbance (5 of 15). One death was observed in the study; the death was due to a prior medical condition and was judged unlikely to be study related. CONCLUSIONS: Patients with higher levels of agitation receiving divalproex had reduced agitation on the physical aggression subscale of the CMAI. Divalproex was less effective on physically nonaggressive behavior and verbal agitation. Irritability, as measured on the NPI-NH, was also reduced. Patients who received both divalproex and an antipsychotic agent were responsive at lower doses of divalproex. In either case, the effective dosage of divalproex was lower than that commonly used for epilepsy or mania in elderly patients. The most common adverse events included somnolence and gait disturbance.