The Spinal Cord Injury Pressure Ulcer Scale (SCIPUS): an assessment of validity using Rasch analysis

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.

The relationship between in-seat movement and pressure ulcers in wheelchair users with SCI/D

OBJECTIVE

To identify parameters that are associated with time at pressure, are most related to pressure ulcer outcomes, and that may be used to influence pressure ulcer (PrU) outcomes in future intervention studies.

DESIGN

Analysis used datasets from cross-sectional and longitudinal observational studies. Wheelchair-usage and in-seat metrics thresholds were optimized to differentiate individuals in PrU or No PrU groups. Logistic regression identified the demographics and in-seat activity metrics that impacted PrU outcomes.

SETTING

General Community.

PARTICIPANTS

Fifty individuals with spinal cord injuries and/or disorders (SCI/D) who use a wheelchair as their primary mobility device. 22 subjects were within the first year following injury and 28 had been using a wheelchair for over 2 years. Twenty-one participants reported PrU outcomes.

INTERVENTIONS

Not applicable.

OUTCOME MEASURES

Time in chair, pressure relief frequency, weight shift frequency, percentage of seated time that the subject is active (CoP Percent Active), frequency of in-seat movement, unloading event frequency, maximum time between events, and number of transfers.

RESULTS

Optimal cutoff thresholds for the most significant in-seat movement metrics included: unloading event frequency of 3.1 times per hour (OR 0.353, 95% CI [0.110, 1.137]), maximum time between events of 155.4 min (OR 2.888, 95% CI [0.886, 9.413]), and CoP Percent Active of 2.6% (OR 0.221, 95% CI [0.063, 0.767]). When individuals were more active than these cutoffs, significantly more individuals were in the no pressure ulcer group. In predictive modeling, CoP Percent Active was the in-seat movement metric that significantly predicted PrU outcomes. The model was improved by adding age, occupation, and injury completeness.

CONCLUSION

Of the 4 significant predictors in the model, only CoP Percent Active was modifiable. Therefore, an opportunity exists to design approaches to modify behavior. However, the results illustrate that the key to preventative movement may be through functional movement as opposed to scheduled, routine pressure reliefs.

Pressure Injuries and Management after Spinal Cord Injury

Spinal cord injury (SCI) results in motor paralysis and sensory loss that places individuals at particularly high risk of pressure injuries. Multiple comorbidities associated with autonomic, cardiovascular, pulmonary, endocrine, gastrointestinal, genitourinary, neurological, and musculoskeletal dysfunction makes it even more likely that pressure injuries will occur. This manuscript will review the structure and function of the integumentary system, and address the multidisciplinary approach required to prevent and manage pressure injuries in this vulnerable population.