Determining Pressure Injury Risk on Admission to Inpatient Spinal Cord Injury Rehabilitation: A Comparison of the FIM, Spinal Cord Injury Pressure Ulcer Scale, and Braden Scale

Integrated Machine Learning Approach for the Early Prediction of Pressure Ulcers in Spinal Cord Injury Patients

(1) Background: Pressure ulcers (PUs) substantially impact the quality of life of spinal cord injury (SCI) patients and require prompt intervention. This study used machine learning (ML) techniques to develop advanced predictive models for the occurrence of PUs in patients with SCI. (2) Methods: By analyzing the medical records of 539 patients with SCI, we observed a 35% incidence of PUs during hospitalization. Our analysis included 139 variables, including baseline characteristics, neurological status (International Standards for Neurological Classification of Spinal Cord Injury [ISNCSCI]), functional ability (Korean version of the Modified Barthel Index [K-MBI] and Functional Independence Measure [FIM]), and laboratory data. We used a variety of ML methods-a graph neural network (GNN), a deep neural network (DNN), a linear support vector machine (SVM_linear), a support vector machine with radial basis function kernel (SVM_RBF), K-nearest neighbors (KNN), a random forest (RF), and logistic regression (LR)-focusing on an integrative analysis of laboratory, neurological, and functional data. (3) Results: The SVM_linear algorithm using these composite data showed superior predictive ability (area under the receiver operating characteristic curve (AUC) = 0.904, accuracy = 0.944), as demonstrated by a 5-fold cross-validation. The critical discriminators of PU development were identified based on limb functional status and laboratory markers of inflammation. External validation highlighted the challenges of model generalization and provided a direction for future research. (4) Conclusions: Our study highlights the importance of a comprehensive, multidimensional data approach for the effective prediction of PUs in patients with SCI, especially in the acute and subacute phases. The proposed ML models show potential for the early detection and prevention of PUs, thus contributing substantially to improving patient care in clinical settings.

Provider perspectives of community-acquired pressure injury prevention in veterans with spinal cord injury

CONTEXT/OBJECTIVE

Community-acquired pressure injuries (CAPrI) are a common and costly complication of spinal cord injury (SCI). Most studies and interventions focus on the prevention of pressure injuries acquired in the hospital. The goal of this study is to better understand SCI provider perspectives of the risks, actions and resources needed to prevent CAPrIs.

DESIGN

Qualitative descriptive, semi-structured interviews of SCI providers analyzed using a deductive-inductive approach.

SETTING

Three geographically different veteran health administration spinal cord injury/disorder centers.

PARTICIPANTS

30 interprofessional SCI providers.

INTERVENTIONS

Not applicable.

OUTCOME MEASURES

Provider perspective of risks, actions and resources for CAPrI prevention in veterans with SCI.

RESULTS

30 interviews revealed a model of provider perspectives of CAPrI prevention including veteran risk characteristics, veteran preventive activities and provider, family, community caregiving resources.

CONCLUSION

Understanding provider perspectives of Veteran CAPrI preventive risks, actions and resources guides more appropriate interventions to prevent CAPrIs in individuals living with SCI.

Association between functional outcomes and psychological variables in persons with spinal cord injury

We aimed to explore the association of functional outcomes with psychological variables, including depression, anxiety, sleep quality, and suicide risk, in persons with spinal cord injuries (SCIs). The secondary aim was to determine specific functions related to the psychological variables. This retrospective study included 259 persons with SCIs who were admitted to the Korean National Rehabilitation Center between 2019 and 2021. The participants were interviewed by a psychiatrist and completed questionnaires, including the Korean Beck Depression Inventory II (K-BDI-II), Korean Beck Anxiety Index, Insomnia Severity Index, and Mini International Neuropsychiatric Interview. To assess functional outcomes, the Spinal Cord Independence Measure III (SCIM III) and Walking Index for Spinal Cord Injury were determined by a physical therapist. The findings revealed a negative correlation of SCIM III subdivisions 1 and 3 with K-BDI-II. Specifically, feeding and mobility in bed and actions to prevent pressure injuries were functional factors associated with all four psychological variables. Our findings can guide clinicians to focus on improving functional independence and activities of daily living during the management of persons with SCI to prevent psychological consequences. Developing devices that aid in improving functional independence is crucial and may improve psychological problems in such individuals.

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.

Machine Learning Techniques, Applications, and Potential Future Opportunities in Pressure Injuries (Bedsores) Management: A Systematic Review

Pressure Injuries (PI) are one of the most common health conditions in the United States. Most acute or long-term care patients are at risk of developing PI. Machine Learning (ML) has been utilized to manage patients with PI, in which one systematic review describes how ML is used in PI management in 32 studies. This research, different from the previous systematic review, summarizes the previous contributions of ML in PI from January 2007 to July 2022, categorizes the studies according to medical specialties, analyzes gaps, and identifies opportunities for future research directions. PRISMA guidelines were adopted using the four most common databases (PubMed, Web of Science, Scopus, and Science Direct) and other resources, which result in 90 eligible studies. The reviewed articles are divided into three categories based on PI time of occurrence: before occurrence (48%); at time of occurrence (16%); and after occurrence (36%). Each category is further broken down into sub-fields based on medical specialties, which result in sixteen specialties. Each specialty is analyzed in terms of methods, inputs, and outputs. The most relevant and potentially useful applications and methods in PI management are outlined and discussed. This includes deep learning techniques and hybrid models, integration of existing risk assessment tools with ML that leads to a partnership between provider assessment and patients' Electronic Health Records (EHR).

A Hybrid System of Braden Scale and Machine Learning to Predict Hospital-Acquired Pressure Injuries (Bedsores): A Retrospective Observational Cohort Study

Background: The Braden Scale is commonly used to determine Hospital-Acquired Pressure Injuries (HAPI). However, the volume of patients who are identified as being at risk stretches already limited resources, and caregivers are limited by the number of factors that can reasonably assess during patient care. In the last decade, machine learning techniques have been used to predict HAPI by utilizing related risk factors. Nevertheless, none of these studies consider the change in patient status from admission until discharge. Objectives: To develop an integrated system of Braden and machine learning to predict HAPI and assist with resource allocation for early interventions. The proposed approach captures the change in patients' risk by assessing factors three times across hospitalization. Design: Retrospective observational cohort study. Setting(s): This research was conducted at ChristianaCare hospital in Delaware, United States. Participants: Patients discharged between May 2020 and February 2022. Patients with HAPI were identified from Nursing documents (N = 15,889). Methods: Support Vector Machine (SVM) was adopted to predict patients' risk for developing HAPI using multiple risk factors in addition to Braden. Multiple performance metrics were used to compare the results of the integrated system versus Braden alone. Results: The HAPI rate is 3%. The integrated system achieved better sensitivity (74.29 ± 1.23) and detection prevalence (24.27 ± 0.16) than the Braden scale alone (sensitivity (66.90 ± 4.66) and detection prevalence (41.96 ± 1.35)). The most important risk factors to predict HAPI were Braden sub-factors, overall Braden, visiting ICU during hospitalization, and Glasgow coma score. Conclusions: The integrated system which combines SVM with Braden offers better performance than Braden and reduces the number of patients identified as at-risk. Furthermore, it allows for better allocation of resources to high-risk patients. It will result in cost savings and better utilization of resources. Relevance to clinical practice: The developed model provides an automated system to predict HAPI patients in real time and allows for ongoing intervention for patients identified as at-risk. Moreover, the integrated system is used to determine the number of nurses needed for early interventions. Reporting Method: EQUATOR guidelines (TRIPOD) were adopted in this research to develop the prediction model. Patient or Public Contribution: This research was based on a secondary analysis of patients' Electronic Health Records. The dataset was de-identified and patient identifiers were removed before processing and modeling.

Long-term outcome following surgical treatment of posttraumatic tethered cord syndrome: a retrospective population-based cohort study

STUDY DESIGN

Retrospective population-based cohort study.

OBJECTIVE

To investigate the long-term outcome following surgery for posttraumatic spinal cord tethering (PSCT).

SETTING

Publicly funded tertiary care center.

METHODS

Patients surgically treated for PSCT between 2005-2020 were identified and included. No patients were excluded or lost to follow-up. Medical records and imaging data were retrospectively reviewed.

RESULTS

Seventeen patients were included. Median age was 52 (23-69) years and 7 (41%) were female. PSCT was diagnosed at a median of 5.0 (0.6-27) years after the initial trauma. Motor deficit was the most common neurological manifestation (71%), followed by sensory deficit (53%), spasticity (53%), pain (41%) and gait disturbance (24%). Median follow-up time was 5.1 (0.7-13) years. Fifteen patients (88%) showed satisfactory results following untethering, defined as improvement or halted progression of one or more of the presenting symptoms. Treatment goals were met for motor symptoms in 92%, sensory loss in 100%, spasticity in 100%, gait disturbance in 100% and pain in 86%. Statistically, a significant improvement in motor deficit (p = 0.031) and syrinx decrease (p = 0.004) was also seen. A postoperative complication occurred in four patients: three cases of cerebrospinal fluid leakage and one postoperative hematoma. Two patients showed a negative surgical outcome: 1 with increased neck pain and 1 with left arm weakness following the postoperative hematoma.

CONCLUSION

Surgical treatment of PSCT results in improved neurological function or halted neurological deterioration in the vast majority of patients.

Policy analysis on power standing systems

Power wheelchairs provide people with mobility disabilities opportunities for independence in mobility and repositioning themselves. However, current power wheelchair power options covered by Medicare limit the person to a horizontal plane. In the home, access to the vertical plane is also required for mobility related activities of daily living. Power standing systems on power wheelchairs are one option for providing access to the vertical environment, although currently these systems are not covered by Medicare. Power standing systems also aid in medical management and in preventing common comorbidities associated with chronic neurological and congenital healthcare conditions. Therefore, a legal group led an interdisciplinary effort to change Medicare policy on power standing systems. A policy analysis using Bardach’s Eightfold policy framework was conducted to analyze a clinical groups’ action within this interdisciplinary team. The clinical team considered three viable options to address the problem and evaluated these options against five criteria. Ultimately, a national coverage determination reconsideration would provide a needed opportunity for the coverage of power standing systems. Suggested coverage criteria for power standing systems, based on existing literature and expert clinical experience, are proposed.

Effect of acceptance and commitment therapy on rehabilitation patients with spinal cord injury

This study aimed to explore the differences between the effectiveness of using a combination of rehabilitation and acceptance commitment therapy (ACT), and rehabilitation therapy alone for the treatment of spinal cord injury (SCI). The newly admitted patients with spinal cord injury whose post-traumatic stress disorder (PTSD) score was higher than 38 points were randomly categorized into the treatment group and control group, with 30 patients in each group. One group underwent ACT and rehabilitation treatment, while the other underwent rehabilitation treatment only. PTSD and functional independence measure (FIM) scores were evaluated. Changes in scores were compared between the two groups before, one month, two months, and three months after treatment. The total PTSD score in SCI patients who were treated with ACT was significantly different before and after treatment (P < 0.05). Total FIM scores were also significantly different before and after treatment (P < 0.05). The FIM score in the treatment group was significantly higher than that in the control group after 2 and 3 months of treatment (P < 0.05). The combination of rehabilitation therapy and ACT could immediately reduce stress levels and significantly improve impaired function, lifelong self-care ability, and the impact of rehabilitation therapy.

Risk factors for hospital acquired pressure injury in patients with spinal cord injury during first rehabilitation: prospective cohort study

STUDY DESIGN

Prospective observational cohort study.

OBJECTIVES

First, describe pressure injury (PI) and associated risk factors in individuals with spinal cord injury/disorder (SCI/D) during first rehabilitation. Second, evaluate a prediction model for hospital acquired PI (HAPI) development.

SETTING

Acute care and rehabilitation clinic specialized in SCI/D.

METHODS

Patients ≥18 years of age with SCI/D were included during first rehabilitation between 08/2018 and 12/2019. We performed a systematic literature search to identify risk factors for PI development. Patients were classified according to HAPI developed. Between group differences of patients' characteristics and risk factors were analyzed using descriptive statistics. Logistic predictive models were performed to estimate HAPI development and receiver operator characteristic (ROC) curve was used to test the model.

RESULTS

In total, 94 patients were included, 48 (51.1%) developed at least one HAPI and in total 93 were observed, mainly stage I and stage II HAPI according to the European Pressure Ulcer Advisory Panel. We found nine significantly associated risk factors: completeness of SCI/D, pneumonia, sedative medications, autonomic dysreflexia, Braden ≤12 points, SCIPUS ≥9 points, lower admission SCIM and lower admission FIM-cognition, longer length of stay (LOS) (p ≤ 0.0005). In a predictive model, none of the risk factors was associated with HAPI development (AUC = 0.5).

CONCLUSION

HAPIs in patients with SCI/D during first rehabilitation are a frequent and complex condition and associated with several risk factors. No predictive model exists but with the identified risk factors of this study, larger studies can create a tailored and flexible HAPI risk prediction model.

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review

Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.