Machine learning to develop a predictive model of pressure injury in persons with spinal cord injury.

STUDY DESIGN: A 5-year longitudinal, retrospective, cohort study. OBJECTIVES: Develop a prediction model based on electronic health record (EHR) data to identify veterans with spinal cord injury/diseases (SCI/D) at highest risk for new pressure injuries (PIs). SETTING: Structured (coded) and text EHR data, for veterans with SCI/D treated in a VHA SCI/D Center between October 1, 2008, and September 30, 2013. METHODS: A total of 4709 veterans were available for analysis after randomly selecting 175 to act as a validation (gold standard) sample. Machine learning models were created using ten-fold cross validation and three techniques: (1) two-step logistic regression; (2) regression model employing adaptive LASSO; (3) and gradient boosting. Models based on each method were compared using area under the receiver-operating curve (AUC) analysis. RESULTS: The AUC value for the gradient boosting model was 0.62 (95% CI = 0.54-0.70), for the logistic regression model it was 0.67 (95% CI = 0.59-0.75), and for the adaptive LASSO model it was 0.72 (95% CI = 0.65-80). Based on these results, the adaptive LASSO model was chosen for interpretation. The strongest predictors of new PI cases were having fewer total days in the hospital in the year before the annual exam, higher vs. lower weight and most severe vs. less severe grade of injury based on the American Spinal Cord Injury Association (ASIA) Impairment Scale. CONCLUSIONS: While the analyses resulted in a potentially useful predictive model, clinical implications were limited because modifiable risk factors were absent in the models.

An evaluation of the Veterans Health Administration National Nursing Education Initiative.

BACKGROUND: Since 1999, the Veterans Health Administration's (VHA) National Nursing Education Initiative (NNEI) has provided 16,294 scholarships for registered nurses to attain baccalaureate and advanced nursing degrees. PURPOSE: The goal of this evaluation was to determine factors that enhanced or hindered a scholarship recipient in the completion of their degree and service obligation. METHODS: A regression analysis was performed to identify predictors of degree completion for 10,043 participants in 162 VHA facilities. FINDINGS: Significant predictor variables for degree completion were intended occupation, entry degree, gender, age, and year entering the program. Eighty-six percent (86.7%) of participants completed the degree requirement. Of those who completed their degree, 97% completed the service obligation. DISCUSSION: As recruitment and retention initiative, NNEI scholarships are poised to address the VHA nursing staffing shortages as well as build a highly qualified nursing workforce capable of providing the best care to our Nation's Veterans.

A preliminary evaluation of full practice authority of advance practice registered nurses in the Veterans Health Administration.

BACKGROUND: Responding to National Academy of Medicine and National Council of State Boards of Nursing recommendations, the Department of Veterans Health Affairs (VHA) implemented full practice authority (FPA) for Advanced Practice Registered Nurses in VHA medical centers (VAMCs) in 2017. PURPOSE: To evaluate FPA policy implementation's impact on quality indicators including access to care as measured by new patient appointments in primary, specialty and mental health services. METHODS: Linear growth models compared early (n = 85) vs. late (n = 55) FPA implementing VAMCs on the trajectories of each of the three quality indicators. FINDINGS: Early FPA implementing VAMCs showed greater rates of improvement over time in new patient appointments completed within 30 days of preferred date for primary care (p = .003), specialty care (p = 0.05), and mental health (p = 0.001). DISCUSSION: VAMCs that started implementation of FPA policy early showed greater improvement in access to care for Veterans over time than VAMCs that did not.

Qualitative assessment of the use of a smart phone application to manage post-concussion symptoms in Veterans with traumatic brain injury.

PURPOSE: As part of a larger study to test the efficacy of the Concussion Coach cell phone application for patients with post-concussion symptoms, qualitative data were gathered to assess barriers and facilitators for app use and differences in use of the app among those who declined or improved in symptom severity, or were low-use users. MATERIALS AND METHODS: Using a prospective descriptive study design, 35 semi-structured qualitative interviews were conducted between 2016-2018. Participants had a history of mild traumatic brain injury and were symptomatic. Interview data were analyzed using qualitative content analysis. RESULTS: Primary facilitators were the app's ease of use, privacy, availability/portability, and increased self-efficacy of the user. Primary barriers were a lack of sufficient app training, stigma, overly "basic" content, and symptom severity. While there were not prominent differences among user groups, users whose symptom severity improved described using more modules of the app than users who declined. Low-users attributed not using the app to content that was too basic or to their forgetting. CONCLUSION: Interview data suggest that Concussion Coach can benefit Veterans with post-concussive symptoms through increased agency, perceived benefits to emotional well-being, and the availability of non-stigmatized strategies for symptom management.

Pressure Injury Documentation Practices in the Department of Veteran Affairs: A Quality Improvement Project.

Evidence suggests that inaccurate and incomplete pressure injury (PI) documentation threatens the validity of treatment and undermines policy and quality improvement. This quality improvement project sought to identify barriers and facilitators when conducting and documenting the daily comprehensive skin assessment in 31 Department of Veterans Affairs (VA) facilities. Evaluators in this 1-year, cross-sectional quality improvement project, using a qualitative approach, interviewed nurses of medical-surgical and critical care units. Participants (N = 62) from 12 high reassessment units (HRUs) and 13 low reassessment units (LRUs) were interviewed using telephone focus groups. Staff from HRUs reported 9 activities that ensured consistency in clinical practices, in validating data, and in correcting inaccuracies. The LRU staff tended to report performing only 2 of the 9 activities. The main barriers to accurate documentation were lack of knowledge, poor templates, and staffing issues such as understaffing and turnover, and main facilitators were an internal data validation process and a documentation template to local practices. Findings from this project led to increased VA leadership engagement, development of 3 innovative, award-winning VA mobile PI prevention and management applications, updated policies and directives on PI prevention, and upgrading of the national VA HAPI workgroup to an advisory committee and improved collaboration between the PI advisory committee and nursing informatics.

Community Reintegration, Participation, and Employment Issues in Veterans and Service Members With Traumatic Brain Injury.

Traumatic brain injury (TBI) has been called the signature injury of the post-9/11 wars in Iraq, Afghanistan, and neighboring countries. Although similarities exist between veterans and service members with TBI, levels of severity and different constellations of coexisting comorbid conditions affect them differently. These conditions affect physical, cognitive, and emotional function, which in turn can complicate community reintegration (CR), or the ability to return to family, vocational, and community life. This special supplement of the Archives of Physical Medicine and Rehabilitation consists of articles written by accomplished teams from multiple disciplines, including anthropology, neuropsychology, nursing, occupational therapy, psychology, and rehabilitation sciences. Each article brings a different perspective to bear on what CR means for veterans and service members from examination of predictors and perceptions of veterans and service members and others to measurement studies. Collectively, this group of articles represents current thinking about CR and lays the groundwork for testing interventions to improve CR outcomes for veterans and service members (eg, employment, living situation, family life).

Post-deployment Mental Health Screening: A Systematic Review of Current Evidence and Future Directions.

Population-based post-deployment screening programs within the Departments of Defense and Veterans Affairs have been implemented to assess for mental health conditions and traumatic brain injury. The purpose of this paper is to systematically review the literature on post-deployment screening within this context and evaluate evidence compared to commonly accepted screening implementation criteria. Findings reflected highly variable psychometric properties of the various screens, variable treatment referral rates following screening, low to moderate treatment initiation rates following screening, and no information on treatment completion or long-term outcomes following screening. In sum, the evidence supporting population based post-deployment screening is inconclusive. Implications are discussed.

Community Reintegration Problems Among Veterans and Active Duty Service Members With Traumatic Brain Injury.

OBJECTIVES: To examine community reintegration problems among Veterans and military service members with mild or moderate/severe traumatic brain injury (TBI) at 1 year postinjury and to identify unique predictors that may contribute to these difficulties. SETTING: VA Polytrauma Rehabilitation Centers. PARTICIPANTS: Participants were 154 inpatients enrolled in the VA TBI Model Systems Program with available injury severity data (mild = 28.6%; moderate/severe = 71.4%) and 1-year postinjury outcome data. DESIGN: Prospective, longitudinal cohort. MAIN MEASURES: Community reintegration outcomes included independent driving, employability, and general community participation. Additional measures assessed depression, posttraumatic stress, and cognitive and motor functioning. RESULTS: In the mild TBI (mTBI) group, posttraumatic stress disorder and depressive symptoms were associated with lower levels of various community reintegration outcomes. In the moderate/severe TBI group, cognition and motor skills were significantly associated with lower levels of community participation, independent driving, and employability. CONCLUSION: Community reintegration is problematic for Veterans and active duty service members with a history of TBI. Unique comorbidities across injury severity groups inhibit full reintegration into the community. These findings highlight the ongoing rehabilitation needs of persons with TBI, specifically evidence-based mental healthcare, in comprehensive rehabilitation programs consistent with a chronic disease management model.

Predictors of Employment Outcomes in Veterans With Traumatic Brain Injury: A VA Traumatic Brain Injury Model Systems Study.

OBJECTIVES: To examine the length of time to return to work (RTW) among service members and veterans (SM/V) with traumatic brain injury (TBI) and to identify variables predictive of RTW. SETTING: Department of Veterans Affairs Polytrauma Rehabilitation Centers (VA PRC). PARTICIPANTS: SM/V enrolled in the VA PRC Traumatic Brain Injury Model Systems database who were of 18 to 60 years of age and admitted with the diagnosis of TBI. DESIGN: Prospective observational cohort study. MAIN OUTCOME MEASURES: Employment status at 1-year postinjury follow-up; Time to Employment (ie, number of days it took to RTW) as documented during 1-year postinjury follow-up. RESULTS: The final sample (n = 293) included male (96%) SM/V with severe TBI (69%). Approximately 21% of the sample participants were employed at 1 year postinjury. Younger individuals who self-identified as nonminority returned to work sooner. Significant associations were observed for time to employment for cause of injury and injury severity. CONCLUSIONS: Few SM/V with moderate to severe TBI returned to work at 1 year postinjury. Predictors such as younger age at the time of injury, minority status, and severity of TBI affected time to and probability of RTW. Findings from this study have important implications for rehabilitation planning and service delivery across the continuum of recovery.

Difficulty in Identifying Factors Responsible for Pressure Ulcer Healing in Veterans With Spinal Cord Injury.

OBJECTIVE: To identify characteristics associated with pressure ulcer (PrU) healing for individuals with spinal cord injury (SCI). DESIGN: Secondary analysis of a large clinical trial's data for healing PrUs in individuals with SCI; prospective Delphi process was conducted with SCI and/or PrU experts. SETTING: Spinal cord injury centers. PARTICIPANTS: There were 629 screening and 162 treatment participants (N=791); 185 SCI clinicians/national PrU/wound care experts participated in the Delphi process. INTERVENTIONS: None. MAIN OUTCOME MEASURE: PrU healing of 50% and 100% at weeks 4 and 12. RESULTS: Poisson regression models using the top Delphi-recommended factors found that only ulcer stage consistently predicted 50% and 100% healing at weeks 4 and 12. Additionally, ischial/perineal location was associated with 33% higher likelihood of 50% healing at week 4. Patient noncompliance with treatment recommendations, the top-ranked Delphi factor, did not predict healing at week 4 or 12. Expanded models found that at week 4, baseline PrU size, PrU stage IV, PrU pain, and American Spinal Injury Association grade A significantly predicted 100% healing, while at week 12, only PrU stage (IV) significantly predicted 100% healing. Significant predictors of 50% healing at week 4 included baseline PrU size, stage, ischial/perianal location body mass index >30kg/m2, foul odor, and signs of infection. At week 12, PrU duration, paraplegia predicted 50% healing. SCI center identifiers consistently showed 2- to 5-fold variation in predicting 50% PrU healing at weeks 4 and 12. CONCLUSIONS: Delphi panel-recommended factors (eg, patient compliance) did not predict PrU healing. Reducing center-level variability in wound healing by learning from best practices should be a health system goal. PrU healing in SCI is still poorly understood, and future studies should focus on as yet unidentified or underappreciated factors.

A Multisite Quality Improvement Project to Standardize the Assessment of Pressure Ulcer Healing in Veterans with Spinal Cord Injuries/Disorders.

OBJECTIVE: The objective was to implement the evidence-based Spinal Cord Impairment Pressure Ulcer Monitoring Tool (SCI-PUMT) in 23 Spinal Cord Injury/Disorders Centers (SCI/D) in the Veterans Health Administration (VHA). SETTING: A collaborative was held in Minnesota that was attended by key personnel from SCI/D Centers in the VHA. METHODS: This initiative was based on a 3-year longitudinal study that established the validity and reliability of a novel pressure ulcer monitoring tool for persons with spinal cord impairment. A multifaceted evidence-based strategy was used to implement the Institute for Healthcare Improvement's framework of Plan-Do-Study-Act. The plan was executed by clinical champions who implemented the tool in their respective SCI/D Centers following a conference that used both didactic and practicum approaches. OUTCOMES: A 15-item toolkit was developed to educate clinicians and patients regarding use of the SCI-PUMT. Toolkit elements were frequently accessed over the VA intranet (n = 3254). The 1.5-day national conference rolled out the new tool to the SCI/D Centers. Pre/post SCI-PUMT knowledge of the SCI-PUMT improved by 78% during the conference. Following the conference, periodic conference calls cemented the implementation efforts of the SCI-PUMT clinical champions and barriers were mitigated.

Improving identification of fall-related injuries in ambulatory care using statistical text mining.

OBJECTIVES: We determined whether statistical text mining (STM) can identify fall-related injuries in electronic health record (EHR) documents and the impact on STM models of training on documents from a single or multiple facilities. METHODS: We obtained fiscal year 2007 records for Veterans Health Administration (VHA) ambulatory care clinics in the southeastern United States and Puerto Rico, resulting in a total of 26 010 documents for 1652 veterans treated for fall-related injury and 1341 matched controls. We used the results of an STM model to predict fall-related injuries at the visit and patient levels and compared them with a reference standard based on chart review. RESULTS: STM models based on training data from a single facility resulted in accuracy of 87.5% and 87.1%, F-measure of 87.0% and 90.9%, sensitivity of 92.1% and 94.1%, and specificity of 83.6% and 77.8% at the visit and patient levels, respectively. Results from training data from multiple facilities were almost identical. CONCLUSIONS: STM has the potential to improve identification of fall-related injuries in the VHA, providing a model for wider application in the evolving national EHR system.

Perceptions of practice guidelines for people with spinal cord injury.

PURPOSE: The Consortium for Spinal Cord Medicine published clinical practice guidelines (CPG) related to upper limb (UL) preservation in people with spinal cord injury (SCI) in 2005. The purpose of this qualitative research was to identify stakeholder agreement with recommendations, performance gaps, and barriers and facilitators to CPG implementation. DESIGN: This 6-month study focused on the perspectives of healthcare providers, veterans, and key informants. The Promoting Action on Research Implementation in Health Services (PARiHS) was used to frame the interview questions, analyze data from focus groups and interviews, and develop conclusions and recommendations. METHOD: SCI Centers at the Tampa, Seattle, and Hines Veterans' hospitals participated. The purposeful sample for the focus groups included 32 healthcare providers, 21 veterans with SCI, and 3 key informants. Analysis of qualitative data netted the percent of agreement with recommendations, performance gaps, and strategies for CPG implementation. FINDINGS: Content analysis of focus group data revealed that healthcare providers agreed or partially agreed with 20 (57%) of the 35 CSCM CPG on UL preservation of function. Agreement ranged from 100% for assessment to 28% for equipment use. Barriers for implementation related to administrative and system issues. CONCLUSION: Consideration of gaps, barriers, and facilitators to implementation will assist clinicians to target interventions to preserve UL function.

Effects of a national safe patient handling program on nursing injury incidence rates.

OBJECTIVE: The objective of the study was to identify which components of a system-wide safe patient handling (SPH) program reduced musculoskeletal injury (MSI) due to patient handling among nurses. METHODS: The 3-year longitudinal study from 2008 to 2011 used a pretest-posttest design. The study was conducted in the Veterans Health Administration, and all medical centers participated. The outcome was 2011 MSI incidence rates due to patient-related handling for nurses, expressed as injuries per 10 000 full-time employees. RESULTS: Three organizational risk factors, bed days of care, facility complexity level, and baseline MSI incidence rate, were significantly associated with MSI incidence rate and explained 21% of its variation. Five SPH components, including deployment of ceiling lifts and other new technologies, peer leader effectiveness, competency in SPH equipment use, facility coordinator link with safety committee, and peer leader training, uniquely accounted for an additional 23% of the total variation. CONCLUSIONS: Findings provide evidence to support the effectiveness of a multicomponent approach to SPH programs given contextual considerations.

A qualitative understanding of patient falls in inpatient mental health units.

BACKGROUND: Falls are the leading cause of injury-related deaths among people age 65 and older, and fractures are the major category of serious injuries produced by falls. OBJECTIVE: Determine market segment-specific recommendations for "selling" falls prevention in acute inpatient psychiatry. DESIGN: Descriptive using focus groups. SETTING: One inpatient unit at a Veterans' hospital in the Southeastern United States and one national conference of psychiatric and mental health nurses. PATIENTS: A convenience sample of 22 registered nurses and advanced practice nurses, one physical therapist and two physicians participated in one of six focus groups. INTERVENTION: None. MEASUREMENTS: Focus groups were conducted by expert facilitators using a semistructured interview guide. Focus groups were recorded and transcribed. Content analysis was used to organize findings. RESULTS: Findings were grouped into fall risk assessment, clinical fall risk precautions, programmatic fall prevention, and "selling" fall prevention in psychiatry. Participants focused on falls prevention instead of fall injury prevention, were committed to reducing risk, and were receptive to learning how to improve safety. Participants recognized unique features of their patients and care settings that defined risk, and were highly motivated to work with other disciplines to keep patients safe. CONCLUSIONS: Selling fall injury prevention to staff in psychiatric settings is similar to selling fall injury prevention to staff in other health care settings. Appealing to the larger construct of patient safety will motivate staff in psychiatric settings to implement best practices and customize these to account for unique population needs characteristics.

Health outcomes associated with military deployment: mild traumatic brain injury, blast, trauma, and combat associations in the Florida National Guard.

OBJECTIVES: To determine the association between specific military deployment experiences and immediate and longer-term physical and mental health effects, as well as examine the effects of multiple deployment-related traumatic brain injuries (TBIs) on health outcomes. DESIGN: Online survey of cross-sectional cohort. Odds ratios were calculated to assess the association between deployment-related factors (ie, physical injuries, exposure to potentially traumatic deployment experiences, combat, blast exposure, and mild TBI) and current health status, controlling for potential confounders, demographics, and predeployment experiences. SETTING: Nonclinical. PARTICIPANTS: Members (N=3098) of the Florida National Guard (1443 deployed, 1655 not deployed). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Presence of current psychiatric diagnoses and health outcomes, including postconcussive and non-postconcussive symptoms. RESULTS: Surveys were completed an average of 31.8 months (SD=24.4, range=0-95) after deployment. Strong, statistically significant associations were found between self-reported military deployment-related factors and current adverse health status. Deployment-related mild TBI was associated with depression, anxiety, posttraumatic stress disorder (PTSD), and postconcussive symptoms collectively and individually. Statistically significant increases in the frequency of depression, anxiety, PTSD, and a postconcussive symptom complex were seen comparing single to multiple TBIs. However, a predeployment TBI did not increase the likelihood of sustaining another TBI in a blast exposure. Associations between blast exposure and abdominal pain, pain on deep breathing, shortness of breath, hearing loss, and tinnitus suggested residual barotrauma. Combat exposures with and without physical injury were each associated not only with PTSD but also with numerous postconcussive and non-postconcussive symptoms. The experience of seeing others wounded or killed or experiencing the death of a buddy or leader was associated with indigestion and headaches but not with depression, anxiety, or PTSD. CONCLUSIONS: Complex relationships exist between multiple deployment-related factors and numerous overlapping and co-occurring current adverse physical and psychological health outcomes. Various deployment-related experiences increased the risk for postdeployment adverse mental and physical health outcomes, individually and in combination. These findings suggest that an integrated physical and mental health care approach would be beneficial to postdeployment care.

Teaching Family Caregivers to Assist Safely with Mobility: Methods for safe patient handling can and should be used in the home.

This article is part of a series, Supporting Family Caregivers: No Longer Home Alone, published in collaboration with the AARP Public Policy Institute. Results of focus groups, conducted as part of the AARP Public Policy Institute's No Longer Home Alone video project, supported evidence that family caregivers aren't given the information they need to manage the complex care regimens of family members. This series of articles and accompanying videos aims to help nurses provide caregivers with the tools they need to manage their family member's health care at home. The articles in this new installment of the series explain principles for promoting safe mobility that nurses should reinforce with family caregivers. Each article also includes an informational tear sheet-Information for Family Caregivers-that contains links to instructional videos. To use this series, nurses should read the article first, so they understand how best to help family caregivers, and then encourage the caregivers to watch the videos and ask questions. For additional information, see Resources for Nurses.

Preventing Falls and Fall-Related Injuries at Home: Teaching family caregivers about home modification and what to do if a fall occurs.

This article is part of a series, Supporting Family Caregivers: No Longer Home Alone, published in collaboration with the AARP Public Policy Institute. Results of focus groups, conducted as part of the AARP Public Policy Institute's No Longer Home Alone video project, supported evidence that family caregivers aren't given the information they need to manage the complex care regimens of family members. This series of articles and accompanying videos aims to help nurses provide caregivers with the tools they need to manage their family member's health care at home. The articles in this new installment of the series explain principles for promoting safe mobility that nurses should reinforce with family caregivers. Each article also includes an informational tear sheet-Information for Family Caregivers-that contains links to instructional videos. To use this series, nurses should read the article first, so they understand how best to help family caregivers, and then encourage the caregivers to watch the videos and ask questions. For additional information, see Resources for Nurses.

Wheelchair Seated Posture and Health Outcomes of Older Veterans in Community Living Centers.

PURPOSE: Nursing home residents sit in wheelchairs (WCs) for extended periods, often with slumped posture. They often experience pneumonia, pressure ulcers, and pain. This study described WC seated posture with its selected predictors and outcomes in the nursing home environment, throughout the daytime hours of 1 day. DESIGN AND METHODS: This observational study (n = 45) in two Veterans Administration Community Living Centers introduced a new measure of WC fit and described WC seated posture of older Veterans, with selected predictors and outcomes. FINDINGS: Wheelchair seated posture was predicted by cognitive status, WC fit, WC skills, and duration of sitting, but not by level of sitting ability. Poor posture measured by the Seated Posture Scale was associated with pain. Highest interface pressures measurable were seen in peak pressure index (PPI = 200 mm Hg), indicating risk of pressure injury. Veterans often denied discomfort, possibly lowering overall pain scores, while reporting severe pain in specific body parts. CONCLUSIONS: Wheelchair seated posture was predicted by cognitive status, WC fit, WC skills, and duration of sitting. Poor posture was associated with pain, and poor posture was an outcome of poor WC fit. Poor WC fit in this study supported earlier findings in non-Veterans Administration nursing homes.