Spinal Cord Injury AIS Predictions Using Machine Learning

Predicting the Outcome and Survival of Patients with Spinal Cord Injury Using Machine Learning Algorithms: A Systematic Review

BACKGROUND

Spinal cord injury (SCI) is a significant public health issue, leading to physical, psychological, and social complications. Machine learning (ML) algorithms have shown potential in diagnosing and predicting the functional and neurologic outcomes of subjects with SCI. ML algorithms can predict scores for SCI classification systems and accurately predict outcomes by analyzing large amounts of data. This systematic review aimed to examine the performance of ML algorithms for diagnosing and predicting the outcomes of subjects with SCI.

METHODS

The literature was comprehensively searched for the pertinent studies from inception to May 25, 2023. Therefore, electronic databases of PubMed, Embase, Scopus, and Web of Science were systematically searched with individual search syntax.

RESULTS

A total of 9424 individuals diagnosed with SCI across multiple studies were analyzed. Among the 21 studies included, 5 specifically aimed to evaluate diagnostic accuracy, while the remaining 16 focused on exploring prognostic factors or management strategies.

CONCLUSIONS

ML and deep learning (DL) have shown great potential in various aspects of SCI. ML and DL algorithms have been employed multiple times in predicting and diagnosing patients with SCI. While there are studies on diagnosing acute SCI using DL algorithms, further research is required in this area.

Prediction of mortality among severely injured trauma patients A comparison between TRISS and machine learning-based predictive models

BACKGROUND

Given the huge impact of trauma on hospital systems around the world, several attempts have been made to develop predictive models for the outcomes of trauma victims. The most used, and in many studies most accurate predictive model, is the "Trauma Score and Injury Severity Score" (TRISS). Although it has proven to be fairly accurate and is widely used, it has faced criticism for its inability to classify more complex cases. In this study, we aimed to develop machine learning models that better than TRISS could predict mortality among severely injured trauma patients, something that has not been studied using data from a nationwide register before.

METHODS

Patient data was collected from the national trauma register in Sweden, SweTrau. The studied period was from the 1st of January 2015 to 31st of December 2019. After feature selection and multiple imputation of missing data three machine learning (ML) methods (Random Forest, eXtreme Gradient Boosting, and a Generalized Linear Model) were used to create predictive models. The ML models and TRISS were then tested on predictive ability for 30-day mortality.

RESULTS

The ML models were well-calibrated and outperformed TRISS in all the tested measurements. Among the ML models, the eXtreme Gradient Boosting model performed best with an AUC of 0.91 (0.88-0.93).

CONCLUSION

This study showed that all the developed ML-based prediction models were superior to TRISS for the prediction of trauma mortality.

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 Predictive Abilities of Machine Learning Algorithms in Patients with Thoracolumbar Spinal Cord Injuries

OBJECTIVES

The goal of this study is to implement machine learning (ML) algorithms to predict mortality, non-home discharge, prolonged length of stay (LOS), prolonged length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with thoracolumbar spinal cord injury, while creating a publicly accessible online tool.

METHODS

The American College of Surgeons Trauma Quality Program database was used to identify patients with thoracolumbar spinal cord injury. Feature selection was performed with the Least Absolute Shrinkage and Selection Operator algorithm. Five ML algorithms, including TabPFN, TabNet, XGBoost, LightGBM, and Random Forest, were used along with the Optuna optimization library for hyperparameter tuning.

RESULTS

A total of 147,819 patients were included in the analysis. For each outcome, we determined the best model for deployment in our web application based on the area under the receiver operating characteristic (AUROC) values. The top performing algorithms were as follows: LightGBM for mortality with an AUROC of 0.885, TabPFN for non-home discharge with an AUROC of 0.801, LightGBM for prolonged LOS with an AUROC of 0.673, Random Forest for prolonged ICU-LOS with an AUROC of 0.664, and LightGBM for major complications with an AUROC of 0.73.

CONCLUSIONS

ML models demonstrate good predictive ability for in-hospital mortality and non-home discharge, fair predictive ability for major complications and prolonged ICU-LOS, but poor predictive ability for prolonged LOS. We have developed a web application that allows these models to be accessed.

Can the Initial Parameters of Functional Scales Predict Recovery in Patients with Complete Spinal Cord Injury? A Retrospective Cohort Study

Regaining greater independence in performing daily activities constitutes a priority for people with tetraplegia following spinal cord injury (SCI). The highest expectations are connected with the improvement of hand function. Therefore, it is so important for the clinician to identify reliable and commonly applicable prognostic factors for functional improvement. The aim of this study was to conduct an analysis to assess the impact of initial functional factors on the clinical improvement in patients during early neurological rehabilitation (ENR). This study assessed 38 patients with complete SCI aged 17-78 who underwent ENR in 2012-2022. The analysis included the motor score from the AIS (MS), the Barthel Index (BI) and the SCIM scale values at the beginning of the ENR program and after its completion. During ENR, patients achieved a statistically significant improvement in MS, BI and SCIM. The initial MS and the level of neurological injury constituted the predictors of functional improvement during ENR. Significant statistical relationships were observed primarily in the correlations between the initial MS and BI, and the increase in the analyzed functional scales of SCI patients. Higher initial MS may increase the chances of a greater and faster functional improvement during ENR.

Serum glucose/potassium ratio as a clinical risk factor for predicting the severity and prognosis of acute traumatic spinal cord injury

OBJECTIVE

Acute traumatic Spinal cord injury (TSCI) is a devastating event that causes severe sensory and motor impairments as well as autonomic dysfunction in patients, yet relevant clinical biomarkers have not been established. This study aimed to determine the significance of the serum glucose/potassium ratio (GPR) in evaluating TSCI severity and predicting prognosis.

METHODS

An analysis of 520 clinical records of acute TSCI patients from January 2012 to June 2022 was conducted. The relationships between serum GPR and The American Spinal Injury Association Impairment Scale (AIS) grade 6-month post-trauma prognosis and the admission AIS grade were analyzed. To evaluate the discriminatory ability, a receiver operating characteristic curve (ROC) analysis was used. All methods were performed in accordance with the relevant guidelines and regulations.

RESULTS

Based on the initial assessment of AIS grade, 256 (49.2%) patients were categorized into the severe TSCI group (AIS A-B), and there was a significant correlation between the severe TSCI group and serum GPR (p < 0.001). Serum GPR was reduced in an AIS grade-dependent manner (R = - 0.540, p < 0.001). Of the 520 patients, 262 (50.4%) patients were classified as having a poor prognosis according to the AIS grade at discharge. Serum GPR was also reduced in an AIS grade at discharge-dependent manner (R = - 0.599, p < 0.001), and was significantly higher in the poor prognosis group compared to the good prognosis group (p < 0.001). Poor prognosis was significantly associated with sex (p = 0.009), severity of TSCI (p < 0.001), location of TSCI (p < 0.001), surgical decompression (p < 0.018), body temperature (p < 0.001), heart rate (p < 0.001), systolic arterial pressure (SAP) (p < 0.001), diastolic arterial pressure (DAP) (p < 0.001), serum GPR (p < 0.001), serum glucose (p < 0.001), serum potassium (p < 0.001), and white blood cell count (p = 0.003). Multivariate logistic regression analysis showed a significant correlation between poor prognosis and serum GPR (p = 0.023). The ROC analysis showed the area under the curve of serum GPR to be a poor predictor of prognosis in TSCI patients at 0.842 (95% confidence interval, 0.808-0.875).

CONCLUSION

There was a significant relationship between serum GPR and admission injury severity and the 6-month prognosis of acute TSCI patients. Serum GPR serves as a readily available clinical risk factor for predicting the severity and 6-month prognosis of acute traumatic spinal cord injury, which holds potential clinical significance for patients with TSCI.