Use of Regression Tree Analysis for Predicting the Functional Outcome after Traumatic Spinal Cord Injury

Data-driven prediction of spinal cord injury recovery: An exploration of current status and future perspectives

Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is a promising approach to enhance the prediction of recovery trajectories, but its integration into clinical practice requires a thorough understanding of its efficacy and applicability. We systematically reviewed the current literature on data-driven models of SCI recovery prediction. The included studies were evaluated based on a range of criteria assessing the approach, implementation, input data preferences, and the clinical outcomes aimed to forecast. We observe a tendency to utilize routinely acquired data, such as International Standards for Neurological Classification of SCI (ISNCSCI), imaging, and demographics, for the prediction of functional outcomes derived from the Spinal Cord Independence Measure (SCIM) III and Functional Independence Measure (FIM) scores with a focus on motor ability. Although there has been an increasing interest in data-driven studies over time, traditional machine learning architectures, such as linear regression and tree-based approaches, remained the overwhelmingly popular choices for implementation. This implies ample opportunities for exploring architectures addressing the challenges of predicting SCI recovery, including techniques for learning from limited longitudinal data, improving generalizability, and enhancing reproducibility. We conclude with a perspective, highlighting possible future directions for data-driven SCI recovery prediction and drawing parallels to other application fields in terms of diverse data types (imaging, tabular, sequential, multimodal), data challenges (limited, missing, longitudinal data), and algorithmic needs (causal inference, robustness).

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.

Harnessing Artificial Neural Networks for Spinal Cord Injury Prognosis

Background: Prediction of neurorehabilitation outcomes after a Spinal Cord Injury (SCI) is crucial for healthcare resource management and improving prognosis and rehabilitation strategies. Artificial neural networks (ANNs) have emerged as a promising alternative to conventional statistical approaches for identifying complex prognostic factors in SCI patients. Materials: a database of 1256 SCI patients admitted for rehabilitation was analyzed. Clinical and demographic data and SCI characteristics were used to predict functional outcomes using both ANN and linear regression models. The former was structured with input, hidden, and output layers, while the linear regression identified significant variables affecting outcomes. Both approaches aimed to evaluate and compare their accuracy for rehabilitation outcomes measured by the Spinal Cord Independence Measure (SCIM) score. Results: Both ANN and linear regression models identified key predictors of functional outcomes, such as age, injury level, and initial SCIM scores (correlation with actual outcome: R = 0.75 and 0.73, respectively). When also alimented with parameters recorded during hospitalization, the ANN highlighted the importance of these additional factors, like motor completeness and complications during hospitalization, showing an improvement in its accuracy (R = 0.87). Conclusions: ANN seemed to be not widely superior to classical statistics in general, but, taking into account complex and non-linear relationships among variables, emphasized the impact of complications during the hospitalization on recovery, particularly respiratory issues, deep vein thrombosis, and urological complications. These results suggested that the management of complications is crucial for improving functional recovery in SCI patients.

Prediction of gait recovery using machine learning algorithms in patients with spinal cord injury

With advances in artificial intelligence, machine learning (ML) has been widely applied to predict functional outcomes in clinical medicine. However, there has been no attempt to predict walking ability after spinal cord injury (SCI) based on ML. In this situation, the main purpose of this study was to predict gait recovery after SCI at discharge from an acute rehabilitation facility using various ML algorithms. In addition, we explored important variables that were related to the prognosis. Finally, we attempted to suggest an ML-based decision support system (DSS) for predicting gait recovery after SCI. Data were collected retrospectively from patients with SCI admitted to an acute rehabilitation facility between June 2008 to December 2021. Linear regression analysis and ML algorithms (random forest [RF], decision tree [DT], and support vector machine) were used to predict the functional ambulation category at the time of discharge (FAC_DC) in patients with traumatic or non-traumatic SCI (n = 353). The independent variables were age, sex, duration of acute care and rehabilitation, comorbidities, neurological information entered into the International Standards for Neurological Classification of SCI worksheet, and somatosensory-evoked potentials at the time of admission to the acute rehabilitation facility. In addition, the importance of variables and DT-based DSS for FAC_DC was analyzed. As a result, RF and DT accurately predicted the FAC_DC measured by the root mean squared error. The root mean squared error of RF and the DT were 1.09 and 1.24 for all participants, 1.20 and 1.06 for those with trauma, and 1.12 and 1.03 for those with non-trauma, respectively. In the analysis of important variables, the initial FAC was found to be the most influential factor in all groups. In addition, we could provide a simple DSS based on strong predictors such as the initial FAC, American Spinal Injury Association Impairment Scale grades, and neurological level of injury. In conclusion, we provide that ML can accurately predict gait recovery after SCI for the first time. By focusing on important variables and DSS, we can guide early prognosis and establish personalized rehabilitation strategies in acute rehabilitation hospitals.

Predictors for the Knee Extension Strength at 2 Yrs After Total Knee Arthroplasty Using Regression Tree Analysis

OBJECTIVE

The aim of the study is to clarify the interactive combinations of clinical factors associated with knee extension strength 2 yrs after total knee arthroplasty.

DESIGN

A retrospective cohort study was conducted on 264 patients who underwent total knee arthroplasty. Knee extension strength was assessed preoperatively, 3 wks, and 2 yrs after total knee arthroplasty. Physical functions were measured with 10-m walking test, Timed Up and Go test, one-leg standing time, isometric knee flexion strength, knee joint stability, knee pain, femora-tibial angle, and passive knee extension and flexion angle before surgery as a baseline and 3 wks after total knee arthroplasty as acute phase. Regression tree analysis was conducted to clarify the interactive combinations that accurately predict the knee extension strength 2 yrs after total knee arthroplasty.

RESULTS

Operational side knee extension strength (>1.00 Nm/kg) at acute phase was the primal predictor for the highest knee extension strength at 2 yrs after total knee arthroplasty. Acute phase Timed Up and Go test (≤10.13 secs) and baseline 10-m walking test (≤11.72 secs) was the second predictor. Acute phase nonoperative side knee extension strength (>0.90 Nm/kg) was also selected as the predictor.

CONCLUSIONS

This study demonstrated that knee extension strength or Timed Up and Go test in the acute phase and 10-m walking test before total knee arthroplasty are useful for estimating the knee extension strength after total knee arthroplasty. The results will help determine specific postoperative rehabilitation goals and training options.

Machine Learning Web Application for Predicting Functional Outcomes in Patients With Traumatic Spinal Cord Injury Following Inpatient Rehabilitation

Accurately predicting functional outcomes in patients with spinal cord injury (SCI) helps clinicians set realistic functional recovery goals and improve the home environment after discharge. The present study aimed to develop and validate machine learning (ML) models to predict functional outcomes in patients with SCI and deploy the models within a web application. The study included data from the Japan Association of Rehabilitation Database from January 1, 1991, to December 31, 2015. Patients with SCI who were admitted to an SCI center or transferred to a participating post-acute rehabilitation hospital after receiving acute treatment were enrolled in this database. The primary outcome was functional ambulation at discharge from the rehabilitation hospital. The secondary outcome was the total motor Functional Independence Measure (FIM) score at discharge. We used binary classification models to predict whether functional ambulation was achieved, as well as regression models to predict total motor FIM scores at discharge. In the training dataset (70% random sample) using demographic characteristics and neurological and functional status as predictors, we built prediction performance matrices of multiple ML models and selected the best one for each outcome. We validated each model's predictive performance in the test dataset (the remaining 30%). Among the 4181 patients, 3827 were included in the prediction model for the total motor FIM score. The mean (standard deviation [SD]) age was 50.4 (18.7) years, and 3211 (83.9%) patients were male. There were 3122 patients included in the prediction model for functional ambulation. The CatBoost Classifier and regressor models showed the best performances in the training dataset. On the test dataset, the CatBoost Classifier had an area under the receiver operating characteristic curve of 0.8572 and an accuracy of 0.7769 for predicting functional ambulation. Likewise, the CatBoost Regressor performed well, with an R2 of 0.7859, a mean absolute error of 9.2957, and a root mean square error of 13.4846 for predicting the total motor FIM score. The final models were deployed in a web application to provide functional predictions. The application can be found at http://3.138.174.54:8501. In conclusion, our prediction models developed using ML successfully predicted functional outcomes in patients with SCI and were deployed in an open-access web application.

Changes in functional independence after inpatient rehabilitation in patients with spinal cord injury: A simultaneous evaluation of prognostic factors

OBJECTIVE

This study aimed to investigate the improvements of functional independence following inpatient rehabilitation and compare those improvements between different levels and severities of Spinal Cord Injury (SCI). Prognostic factors affecting the patient's outcomes were also studied.

SETTINGS

Rofeideh Rehabilitation Hospital.

OUTCOME MEASURES

Spinal Cord Independence Measure version III (SCIM III), and Functional Independence Measure (FIM).

METHOD

In this retrospective cohort study, 180 patients with SCI were enrolled to record their functional independence upon admission and discharge, and the changes were compared between different levels and severities of injury using non-parametric tests. The prognostic factors of outcomes were studied by generalized estimating equation (GEE) analysis.

RESULTS

The independence changes were significant for all the severities (American Spinal Injury Association Impairment Scale (AIS)) and levels of injury except for the patients with AIS A and B at upper cervical levels (P < 0.05). The level of injury, AIS, Length of Stay (LOS), and pressure ulcer had a significant prognostic value on patient's outcomes. Furthermore, there was a significant difference between different levels of injury with the same AIS grade in functional improvement (P < 0.05), while there was a significant difference between AIS groups with the same level of injury only at upper and middle cervical lesions (P < 0.05).

CONCLUSION

Recording the values of functional independence before and after rehabilitation in individuals with SCI can help clinicians approximately expect the outcomes of future patients. Moreover, a deeper study of the prognostic factors can provide a more logical expectation of rehabilitation outcomes.

Are Clinical Prediction Rules Used in Spinal Cord Injury Care? A Survey of Practice

Background

Accurate outcome prediction is desirable post spinal cord injury (SCI), reducing uncertainty for patients and supporting personalized treatments. Numerous attempts have been made to create clinical prediction rules that identify patients who are likely to recover function. It is unknown to what extent these rules are routinely used in clinical practice.

Objectives

To better understand knowledge of, and attitudes toward, clinical prediction rules amongst SCI clinicians in the United Kingdom.

Methods

An online survey was distributed via mailing lists of clinical special interest groups and relevant National Health Service Trusts. Respondents answered questions about their knowledge of existing clinical prediction rules and their general attitudes to using them. They also provided information about their level of experience with SCI patients.

Results

One hundred SCI clinicians completed the survey. The majority (71%) were unaware of clinical prediction rules for SCI; only 8% reported using them in clinical practice. Less experienced clinicians were less likely to be aware. Lack of familiarity with prediction rules was reported as being a barrier to their use. The importance of clinical expertise when making prognostic decisions was emphasized. All respondents reported interest in using clinical prediction rules in the future.

Conclusion

The results show widespread lack of awareness of clinical prediction rules amongst SCI clinicians in the United Kingdom. However, clinicians were positive about the potential for clinical prediction rules to support decision-making. More focus should be directed toward refining current rules and improving dissemination within the SCI community.

Classifying clinical phenotypes of functional recovery for acute traumatic spinal cord injury. An observational cohort study

PURPOSE

Identify patient subgroups with different functional outcomes after SCI and study the association between functional status and initial ISNCSCI components.

METHODS

Using CART, we performed an observational cohort study on data from 675 patients enrolled in the Rick-Hansen Registry(RHSCIR) between 2014 and 2019. The outcome was the Spinal Cord Independence Measure (SCIM) and predictors included AIS, NLI, UEMS, LEMS, pinprick(PPSS), and light touch(LTSS) scores. A temporal validation was performed on data from 62 patients treated between 2020 and 2021 in one of the RHSCIR participating centers.

RESULTS

The final CART resulted in four subgroups with increasing totSCIM according to PPSS, LEMS, and UEMS: 1)PPSS < 27(totSCIM = 28.4 ± 16.3); 2)PPSS ≥ 27, LEMS < 1.5, UEMS < 45(totSCIM = 39.5 ± 19.0); 3)PPSS ≥ 27, LEMS < 1.5, UEMS ≥ 45(totSCIM = 57.4 ± 13.8); 4)PPSS ≥ 27, LEMS ≥ 1.5(totSCIM = 66.3 ± 21.7). The validation model performed similarly to the original model. The adjusted R-squared and F-test were respectively 0.556 and 62.2(P-value <0.001) in the development cohort and, 0.520 and 31.9(P-value <0.001) in the validation cohort.

CONCLUSION

Acknowledging the presence of four characteristic subgroups of patients with distinct phenotypes of functional recovery based on PPSS, LEMS, and UEMS could be used by clinicians early after tSCI to plan rehabilitation and establish realistic goals. An improved sensory function could be key for potentiating motor gains, as a PPSS ≥ 27 was a predictor of a good function.

Functional Outcome Prediction After Spinal Cord Injury Using Ensemble Machine Learning

OBJECTIVES

To establish a machine learning model to predict functional outcomes after SCI with Spinal Cord Independence Measure (SCIM) using features present at the time of rehabilitation admission.

STUDY DESIGN

A retrospective, single-center study. The following data were collected from the medical charts: age, sex, acute length of stay (LOS), level of injury, American Spinal Injury Association Impairment Scale (AIS), motor scores of each key muscle, Upper Extremity Motor Score (UEMS), Lower Extremity Motor Score (LEMS), SCIM total scores, and subtotal scores on admission and discharge. Based on the multivariate linear regression analysis, age, acute LOS, UEMS, LEMS, and SCIM subtotal scores were selected as features for machine learning algorithms. Random forest, support vector machine, neural network, and gradient boosting were used as the base models and combined using ridge regression as a metamodel.

SETTING

A spinal center in Tokyo, Japan.

PARTICIPANTS

Participants were individuals with SCI admitted to our hospital from March 2016 to October 2021 for the first rehabilitation after the injury. They were divided into 2 groups: training (n=140) and testing (n=70).

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

The root-mean-square error (RMSE), R2, and Mean Absolute Error (MAE) were used as accuracy measures.

RESULTS

RMSE, R2, and MAE of the meta-model using the testing group were 9.7453, 0.8835, and 7.4743, respectively, outperforming any other single base model.

CONCLUSIONS

Our study revealed that functional prognostication could be achieved using machine-learning methods with features present at the time of rehabilitation admission. Goals can be set at the beginning of rehabilitation. Moreover, our model can be used to evaluate advanced medical treatments, such as regenerative medicine.

Interactive Combinations Between Gait Speed and Physical Function at Acute Phase Can Predict the Physical Activity at 2 Years After Total Knee Arthroplasty Using Classification and Regression Tree Analysis

OBJECTIVE

To clarify the interactive combinations of various clinical factors associated with physical activity (PA) at 2 years after total knee arthroplasty (TKA) using classification and regression tree (CART) analysis.

DESIGN

A retrospective cohort study.

SETTING

A single university hospital.

PARTICIPANTS

286 patients who underwent TKA (N=286).

MAIN OUTCOME MEASURES

PA was assessed preoperatively, 3 weeks, and 2 years after TKA. Physical functions, namely, 10 m walking test (10MWT), timed Up and Go test, 1-leg standing time, isometric knee extension and flexion strength, knee joint stability, knee pain, femora-tibial angle, and the passive knee extension and flexion angle, were measured before surgery as a baseline and 3 weeks after TKA as acute phase. CART analysis was conducted to clarify the interactive combinations that accurately predict the PA at 2 years after TKA.

RESULTS

The results of CART analysis indicated that gait speed (≥1.05 m/s) at the acute phase after TKA was the primal predictor for the postoperative PA at 2 years. The highest postoperative PA at 2 years was determined by gait speed (≥1.05 m/s) and PA (>74.5) at the acute phase. The PA at baseline and at acute phase, as well as the body mass index were also selected as predictors of postoperative PA at 2 years.

CONCLUSION

The present study suggested that acquiring gait speed (≥1.05 m/s) and PA (>74.5) in the postoperative acute phase is the predictive of a high PA at 2 years after TKA.

Predictors of spinal trauma care and outcomes in a resource-constrained environment: a decision tree analysis of spinal trauma surgery and outcomes in Tanzania

OBJECTIVE

The burden of spinal trauma in low- and middle-income countries (LMICs) is immense, and its management is made complex in such resource-restricted settings. Algorithmic evidence-based management is cost-prohibitive, especially with respect to spinal implants, while perioperative care is work-intensive, making overall care dependent on multiple constraints. The objective of this study was to identify determinants of decision-making for surgical intervention, improvement in function, and in-hospital mortality among patients experiencing acute spinal trauma in resource-constrained settings.

METHODS

This study was a retrospective analysis of prospectively collected data in a cohort of patients with spinal trauma admitted to a tertiary referral hospital center in Dar es Salam, Tanzania. Data on demographic, clinical, and treatment characteristics were collected as part of a quality improvement neurotrauma registry. Outcome measures were surgical intervention, American Spinal Injury Association (ASIA) Impairment Scale (AIS) grade improvement, and in-hospital mortality, based on existing treatment protocols. Univariate analyses of demographic and clinical characteristics were performed for each outcome of interest. Using the variables associated with each outcome, a machine learning algorithm-based regression nonparametric decision tree model utilizing a bootstrapping method was created and the accuracy of the three models was estimated.

RESULTS

Two hundred eighty-four consecutively admitted patients with acute spinal trauma were included over a period of 33 months. The median age was 34 (IQR 26-43) years, 83.8% were male, and 50.7% had experienced injury in a motor vehicle accident. The median time to hospital admission after injury was 2 (IQR 1-6) days; surgery was performed after a further median delay of 22 (IQR 13-39) days. Cervical spine injury comprised 38.4% of the injuries. Admission AIS grades were A in 48.9%, B in 16.2%, C in 8.5%, D in 9.5%, and E in 16.6%. Nearly half (45.1%) of the patients underwent surgery, 12% had at least one functional improvement in AIS grade, and 11.6% died in the hospital. Determinants of surgical intervention were age ≤ 30 years, spinal injury level, admission AIS grade, delay in arrival to the referral hospital, undergoing MRI, and type of insurance; admission AIS grade, delay to arrival to the hospital, and injury level for functional improvement; and delay to arrival, injury level, delay to surgery, and admission AIS grade for in-hospital mortality. The best accuracies for the decision tree models were 0.62, 0.34, and 0.93 for surgery, AIS grade improvement, and in-hospital mortality, respectively.

CONCLUSIONS

Operative intervention and functional improvement after acute spinal trauma in this tertiary referral hospital in an LMIC environment were low and inconsistent, which suggests that nonclinical factors exist within complex resource-driven decision-making frameworks. These nonclinical factors are highlighted by the authors' results showing clinical outcomes and in-hospital mortality were determined by natural history, as evidenced by the highest accuracy of the model predicting in-hospital mortality.

Machine learning in clinical diagnosis, prognostication, and management of acute traumatic spinal cord injury (SCI): A systematic review

Background

Machine learning has been applied to improve diagnosis and prognostication of acute traumatic spinal cord injury. We investigate potential for clinical integration of machine learning in this patient population to navigate variability in injury and recovery.

Materials and methods

We performed a systematic review using PRISMA guidelines through PubMed database to identify studies that use machine learning algorithms for clinical application toward improvements in diagnosis, management, and predictive modeling.

Results

Of the 132 records identified, a total of 13 articles met inclusion criteria and were included in final analysis. Of the 13 articles, 5 focused on diagnostic accuracy and 8 were related to prognostication or management of traumatic spinal cord injury. Across studies, 1983 patients with spinal cord injury were evaluated with most classifying as ASIA C or D. Retrospective designs were used in 10 of 13 studies and 3 were prospective. Studies focused on MRI evaluation and segmentation for diagnostic accuracy and prognostication, investigation of mean arterial pressure in acute care and intraoperative settings, prediction of ambulatory and functional ability, chronic complication prevention, and psychological quality of life assessments. Decision tree, random forests (RF), support vector machines (SVM), hierarchical cluster tree analysis (HCTA), artificial neural networks (ANN), convolutional neural networks (CNN) machine learning subtypes were used.

Conclusions

Machine learning represents a platform technology with clinical application in traumatic spinal cord injury diagnosis, prognostication, management, rehabilitation, and risk prevention of chronic complications and mental illness. SVM models showed improved accuracy when compared to other ML subtypes surveyed. Inherent variability across patients with SCI offers unique opportunity for ML and personalized medicine to drive desired outcomes and assess risks in this patient population.

Utility of transcranial magnetic stimulation in the assessment of spinal cord injury: Current status and future directions

Comprehensive assessment following traumatic spinal cord injury (SCI) is needed to improve prognostication, advance the understanding of the neurophysiology and better targeting of clinical interventions. The International Standards for Neurological Classification of Spinal Cord Injury is the most common clinical examination recommended for use after a SCI. In addition, there are over 30 clinical assessment tools spanning across different domains of the International Classification of Functioning, Disability, and Health that have been validated and recommended for use in SCI. Most of these tools are subjective in nature, have limited value in predicting neurologic recovery, and do not provide insights into neurophysiological mechanisms. Transcranial magnetic stimulation (TMS) is a non-invasive neurophysiology technique that can supplement the clinical assessment in the domain of body structure and function during acute and chronic stages of SCI. TMS offers a better insight into neurophysiology and help in better detection of residual corticomotor connectivity following SCI compared to clinical assessment alone. TMS-based motor evoked potential and silent period duration allow study of excitatory and inhibitory mechanisms following SCI. Changes in muscle representations in form of displacement of TMS-based motor map center of gravity or changes in the map area can capture neuroplastic changes resulting from SCI or following rehabilitation. Paired-pulse TMS measures help understand the compensatory reorganization of the cortical circuits following SCI. In combination with peripheral stimulation, TMS can be used to study central motor conduction time and modulation of spinal reflexes, which can be used for advanced diagnostic and treatment purposes. To strengthen the utility of TMS in SCI assessment, future studies will need to standardize the assessment protocols, address population-specific concerns, and establish the psychometric properties of TMS-based measurements in the SCI population.

Factors for Predicting Instant Neurological Recovery of Patients with Motor Complete Traumatic Spinal Cord Injury

The objective of this study was to analyze the factors affecting the instant recovery of neurological function in patients with motor complete traumatic spinal cord injury (TSCI) treated in hospital. Methods: A retrospective analysis of 1053 patients with TSCI classified according to the American Spinal Cord Injury Association (ASIA) as grades A and B at 59 tertiary hospitals from 1 January 2018 to 31 December 2018 was performed. All patients were classified into motor complete injury (ASIA A or B) and motor incomplete injury (ASIA C or D) groups, according to the ASIA upon discharge. The injury level, fracture segment, fracture type, ASIA score at admission and discharge, treatment protocol, and complications were recorded. Univariate and multivariate analyses were performed to evaluate the relationship between various factors and the recovery of neurological function. Results: The results of multiple logistic regression analysis revealed that the ASIA score on admission (p < 0.001, odds ratio (OR) = 5.722, 95% confidence interval (CI): 4.147−7.895), fracture or dislocation (p = 0.001, OR = 0.523, 95% CI: 0.357−0.767), treatment protocol (p < 0.001; OR = 2.664, 95% CI: 1.689−4.203), and inpatient rehabilitation (p < 0.001, OR = 2.089, 95% CI: 1.501−2.909) were independently associated with the recovery of neurological function. Conclusion: The recovery of neurological function is dependent on the ASIA score on admission, fracture or dislocation, treatment protocol, and inpatient rehabilitation.

Research on Rehabilitation Effect Prediction for Patients with SCI Based on Machine Learning

OBJECTIVE

Due to the complex condition of Spinal Cord Injury (SCI) patients, it is difficult to accurately calculate the Activity of Daily Living (ADL) score of discharged patients. In view of the above problem, this research proposes a prediction model of discharged ADL score based on machine learning, in order to get the rehabilitation effect of patients after rehabilitation training.

METHODS

Firstly, the medical records of 1231 SCI patients were collected, and the corresponding data preprocessing was carried out. Secondly, Pearson Correlation Coefficient method (PCC) was combined with feature selection method based on Random Forest (RF) to screen out six features closely related to discharged ADL score. Then RF and RF optimized by Harris Hawks Optimizer (HHO-RF) were used to predict discharged ADL score of SCI patients. The Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Coefficient of determination () were used as evaluation indicators of the model.

RESULTS

The prediction features selected by feature extraction were ADL score on admission, age, injury segment, injury reason, injury position, and injury degree. After 10-fold cross-validation, MAE, RMSE and of RF were 0.0875, 0.1346 and 0.7662. MAE, RMSE and of HHO-RF were 0.0821, 0.1089 and 0.8537. The prediction effect of HHO-RF has been greatly improved.

CONCLUSIONS

In clinical treatment, HHO-RF can accurately predict discharged ADL score and provide a reasonable direction for patients to choose rehabilitation programs.

Early clinical predictors of functional recovery following traumatic spinal cord injury: a population-based study of 143 patients

BACKGROUND

Traumatic spinal cord injuries (TSCI) are associated with uncertainty regarding the prognosis of functional recovery. The aim of the present study was to evaluate the potential of early clinical variables to predict the degree of functional independence assessed by Spinal Cord Independence Measure III (SCIM-III) up to 1 year after injury.

METHODS

Prospectively collected data from 143 SCI patients treated in Western Denmark during 2012-2019 were retrospectively analysed. Data analysis involved univariate methods and multivariable linear regression modelling total SCIM-III scores against age, gender, body mass index (BMI), comorbidity, American Spinal Injury Association (ASIA) Impairment Scale (AIS) grades A-B and C-D, ASIA Motor Score (AMS), timing of surgical treatment and occurrence of medical complications. Statistical significance was set at p < .05.

RESULTS

Univariate analyses indicated that variables significantly associated with decreased functional independence included increased age (p = .023), increased BMI (p = .012), pre-existing comorbidity (p = .001), AIS grades A-B (p < .001), decreased AMS (p < .001) and occurrence of medical complications (p < .001). However, in the multivariable regression model were pre-existing comorbidity (p = .010), AIS grades A-B (p < .001), low AMS (p < .001) and late surgical treatment (p = .018) significant predictors of decreased functional independence 1 year after injury.

CONCLUSION

TSCI patients with greatest potential for functional recovery up to 1 year after injury seem to be patients that immediately after trauma present with few or no comorbidities, who sustain motor-incomplete injuries and undergo early decompressive surgery.

The potential of prediction models of functioning remains to be fully exploited: A scoping review in the field of spinal cord injury rehabilitation

OBJECTIVE

The study aimed to explore existing prediction models of functioning in spinal cord injury (SCI).

STUDY DESIGN AND SETTING

The databases PubMed, EBSCOhost CINAHL Complete, and IEEE Xplore were searched for relevant literature. The search strategy included published search filters for prediction model and impact studies, index terms and keywords for SCI, and relevant outcome measures able to assess functioning as reflected in the International Classification of Functioning, Disability and Health (ICF). The search was completed in October 2020.

RESULTS

We identified seven prediction model studies reporting twelve prediction models of functioning. The identified prediction models were mainly envisioned to be used for rehabilitation planning, however, also other possible applications were stated. The method predominantly used was regression analysis and the investigated predictors covered mainly the ICF-components of body functions and activities and participation, next to characteristics of the health condition and health interventions.

CONCLUSION

Findings suggest that the development of prediction models of functioning for use in clinical practice remains to be fully exploited. By providing a comprehensive overview of what has been done, this review informs future research on prediction models of functioning in SCI and contributes to an efficient use of research evidence.

Improving Diagnostic Workup Following Traumatic Spinal Cord Injury: Advances in Biomarkers

PURPOSE OF REVIEW

Traumatic spinal cord injury (SCI) is a life-changing event with drastic implications for patients due to sensorimotor impairment and autonomous dysfunction. Current clinical evaluations focus on the assessment of injury level and severity using standardized neurological examinations. However, they fail to predict individual trajectories of recovery, which highlights the need for the development of advanced diagnostics. This narrative review identifies recent advances in the search of clinically relevant biomarkers in the field of SCI.

RECENT FINDINGS

Advanced neuroimaging and molecular biomarkers sensitive to the disease processes initiated by the SCI have been identified. These biomarkers range from advanced neuroimaging techniques, neurophysiological readouts, and molecular biomarkers identifying the concentrations of several proteins in blood and CSF samples. Some of these biomarkers improve current prediction models based on clinical readouts. Validation with larger patient cohorts is warranted. Several biomarkers have been identified-ranging from imaging to molecular markers-that could serve as advanced diagnostic and hence supplement current clinical assessments.

Clinical judgment is a cornerstone for validating and using clinical prediction rules: a head-to-head study on ambulation outcomes for spinal cord injured patients

STUDY DESIGN

Retrospective comparative study.

OBJECTIVE

Clinical prediction rules (CPRs) are an effervescent topic in the medical literature. Recovering ambulation after a traumatic spinal cord injury (tSCI) is a priority for patients and multiple CPRs have been proposed for predicting ambulation outcomes. Our objective is to confront clinical judgment to an established CPR developed for patients with tSCI.

SETTINGS

Level one trauma center specialized in tSCI and its affiliated rehabilitation center.

METHOD

In this retrospective comparative study, six physicians had to predict the ambulation outcome of 68 patients after a tSCI based on information from the acute hospitalization. Ambulation was also predicted according to the CPR of van Middendorp (CPR-vM). The success rate of the CPR-vM and clinicians to predict ambulation was compared using criteria of 5% for defining clinical significance, and a level of statistical significance of 0.05 for bilateral McNemar tests.

RESULTS

There was no statistical difference between the overall performance of physicians (success rate of 79%) and of the CPR-vM (81%) for predicting ambulation. The differences between the CPR-vM and physicians varied clinically and significantly with the level of experience, clinical setting, and field of expertise.

CONCLUSION

Confronting CPRs with the judgment of a group of clinicians should be an integral part of the design and validation of CPRs. Head-to-head comparison of CPRs with clinicians is also a cornerstone for defining the optimal strategy for translation into the clinical practice, and for defining which clinician and specific clinical context would benefit from using the CPR.

The effect of age and injury severity on clinical prediction rules for ambulation among individuals with spinal cord injury

BACKGROUND CONTEXT

While several models for predicting independent ambulation early after traumatic spinal cord injury (SCI) based upon age and specific motor and sensory level findings have been published and validated, their accuracy, especially in individual American Spinal Injury Association [ASIA] Impairment Scale (AIS) classifications, has been questioned. Further, although age is widely used in prediction rules, its role and possible modifications have not been adequately evaluated until now.

PURPOSE

To evaluate the predictive accuracy of existing clinical prediction rules for independent ambulation among individuals at spinal cord injury model systems (SCIMS) Centers as well as the effect of modifying the age parameter from a cutoff of 65 years to 50 years.

STUDY DESIGN

Retrospective analysis of a longitudinal database.

PATIENT SAMPLE

Adult individuals with traumatic SCI.

OUTCOME MEASURES

The FIM locomotor score was used to assess independent walking ability at the 1-year follow-up.

METHODS

In all, 639 patients were enrolled in the SCIMS database between 2011 and 2015, with complete neurological examination data within 15 days following the injury and a follow-up assessment with functional independence measure (FIM) at 1-year post injury. Two previously validated logistic regression models were evaluated for their ability to predict independent walking at 1-year post injury with participants in the SCIMS database. Area under the receiver operating curve (AUC) was calculated for the individual AIS categories and for different age groups. Prediction accuracy was also calculated for a new modified LR model (with cut-off age of 50).

RESULTS

Overall AUC for each of the previous prediction models was found to be consistent with previous reports (0.919 and 0.904). AUCs for grouped AIS levels (A+D, B+C) were consistent with prior reports, moreover, prediction for individual AIS grades continued to reveal lower values. AUCs by different age categories showed a decline in prognostication accuracy with an increase in age, with statistically significant improvement of AUC when age-cut off was reduced to 50.

CONCLUSIONS

We confirmed previous results that former prediction models achieve strong prognostic accuracy by combining AIS subgroups, yet prognostication of the separate AIS groups is less accurate. Further, prognostication of persons with AIS B+C, for whom a clinical prediction model has arguably greater clinical utility, is less accurate than those with AIS A+D. Our findings emphasize that age is an important factor in prognosticating ambulation following SCI. Prediction accuracy declines for older individuals compared with younger ones. To improve prediction of independent ambulation, the age of 50 years may be a better cutoff instead of age of 65.

Impact of complications at admission to rehabilitation on the functional status of patients with spinal cord lesion

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

Aim of the study is to evaluate the impact of complications at admission on the functional status of spinal cord lesions patients.

SETTING

Rehabilitation hospital in Italy.

METHODS

Two hundred and seven patients with complications (mostly pressure ulcers) at admission to rehabilitation were matched for neurological level of injury and AIS grade with 207 patients without complications.

MEASURES

International Standards for Neurological Classification of Spinal Cord Injury, Spinal Cord Independence Measure, Rivermead Mobility Index, and Walking Index for Spinal Cord Injury. These measures were recorded at admission to rehabilitation and at discharge. We also recorded length of acute and rehabilitation stay and discharge destination.

STATISTICS

Student's T test for paired samples, McNemar's chi-square test.

RESULTS

Patients with complications at admission suffered more often from a traumatic lesions. The functional status at admission and discharge of the patients without complications was significantly better than the functional status of patients with complications (Spinal Cord Independence Measure mean difference between the two groups 5.7 (CI 2.8-8.5) at admission, and 10 (CI 5.3-14.7) at discharge). Length of stay was significantly higher in patients with complications. Patients with complications were more often institutionalized than their counterparts (46/161 vs. 20/187, odds ratio 0.4 (CI 0.2-0.7)).

CONCLUSIONS

Complications seem to be more frequent in patients with traumatic lesions. The presence of complications has a negative effect on patients' functional status at discharge and length of stay, and it determines a higher risk of being institutionalized.

Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients

BACKGROUND CONTEXT

Traumatic spinal cord injury can have a dramatic effect on a patient's life. The degree of neurologic recovery greatly influences a patient's treatment and expected quality of life. This has resulted in the development of machine learning algorithms (MLA) that use acute demographic and neurologic information to prognosticate recovery. The van Middendorp et al. (2011) (vM) logistic regression (LR) model has been established as a reference model for the prediction of walking recovery following spinal cord injury as it has been validated within many different countries. However, an examination of the way in which these prediction models are evaluated is warranted. The area under the receiver operators curve (AUROC) has been consistently used when evaluating model performance, but it has been shown that AUROC overemphasizes the most common event resulting in an inaccurate assessment when the data are imbalanced. Furthermore, there is evidence that the use of more advanced MLA, such as an unsupervised k-means model, may show superior performance compared to LR as they can handle a larger number of features.

PURPOSE

The first objective of the study was to assess the performance of both an unsupervised MLA and LR model with complete admission neurologic information against the vM and Hicks models. Second, a comparison between the accuracy of the AUROC and the F1-score will be made to determine which method is superior for the assessment of diagnostic performance of prediction models on large-scale datasets.

STUDY DESIGN

Retrospective review of a prospective cohort study.

PATIENT SAMPLE

The Rick Hansen Spinal Cord Injury Registry (RHSCIR) was used in this study. All patients enrolled between 2004 and 2017 with complete neurologic examination and Functional Independence Measure outcome data at ≥1 year follow-up or who could walk at discharge were included. The prognostic variables included age (dichotomized at ≥65 years old); American Spinal Injury Association Impairment Scale (AIS) grade; and individual motor, light touch, and pinprick score from L2 to S1.

OUTCOME MEASURES

The Functional Independence Measure locomotor score was used to assess independent walking ability at discharge or 1-year follow-up.

METHODS

An unsupervised MLA with k=2 was chosen in order to identify a "walk" cluster and a "not walk" cluster. Model performance was assessed through the development of a receiver operating characteristic curve with associated AUROC and a precision-recall curve with associated F1-score. The study and the RHSCIR are supported by funding from Health Canada, Western Economic Diversification Canada, and the Governments of Alberta, British Columbia, Manitoba, and Ontario. These funders had no role in the study or study reporting and the authors have no conflicts of interest to report.

RESULTS

No clinically relevant differences were found between with the use of an unsupervised MLA with a greater amount of initial neurologic information compared to the established standards for any AIS classification. Although demonstrated for all separate AIS classifications, most notably, the AUROC for the vM (0.78) and Hicks models (0.76) were found to be superior to that of the new LR model (0.72); however, the vM and Hicks models had more than double the amount of false negative classifications compared to the LR. The F1-scores between these three models were also found to be different but with the vM and Hicks models being lower than the LR (0.85, 0.81, and 0.89, respectively).

CONCLUSIONS

No clinically relevant differences were found between the use of an unsupervised MLA with complete admission neurologic information compared to the previously validated standards; however, when comparing the performance of the AUROC and F1-score, the AUROC showed inaccurate prognostic performance when there was an imbalance toward a greater amount of false negatives. Importantly, the F1-score did not succumb to this imbalance. As AUROC has been used as the standard when evaluating performance of prediction models, consideration as to whether this is the most appropriate method is warranted. Future work should focus on comparing AUROC and F1-scores with other previously validated models.

Traumatic spinal cord injury in Italy 20 years later: current epidemiological trend and early predictors of rehabilitation outcome

STUDY DESIGN

Multicenter prospective observational study of people with acute traumatic spinal cord injury (TSCI) admitted to rehabilitation.

OBJECTIVES

To update epidemiological characteristics of a TSCI Italian population and verify the impact of patient characteristics at admission on two outcomes: functional gain (SCIM III) and discharge destination.

SETTING

Thirty-one SCI centers for comprehensive rehabilitation in 13 Italian regions.

METHODS

All consecutive individuals admitted with acute TSCI were enrolled from October 1, 2013 to September 30, 2014; data were recorded on rehabilitation admission and discharge. Functional gain and discharge destination were identified as outcome measures and statistically analyzed with patient characteristics at admission to identify early outcome predictors.

RESULTS

Five hundred and ten individuals with TSCI met inclusion criteria; falls represented the most frequent etiology (45%). On admission, AIS A-B-C tetraplegia was reported in 35% of cases; AIS A-B-C paraplegia in 40%; AIS D paraplegia/tetraplegia in 25%. The majority were discharged home (72%). The mean (SD) SCIM gain was 38 ± 26 points. A predictive model was found for discharge setting: individuals with fall-related injuries, severe SCI (AIS A-B-C tetraplegia), tracheal cannula or indwelling catheter on admission, were less likely to be discharged home (OR 95% CI 0.15 [0.06, 0.35]). A model with a lower predictive power was found for SCIM gain, with lower score expected for females, older age, higher severity of SCI, a longer onset of injury admission interval (OAI), and mechanical ventilation on admission.

CONCLUSIONS

Prognostic factors in early rehabilitation are still hard to identify, making it difficult to correctly approach customized rehabilitation.

Prevalence of pressure injury among Chinese community-dwelling older people and its risk factors: A national survey based on Chinese Longitudinal Healthy Longevity Survey

AIM

To investigate the distribution of pressure injuries among older adults in China and to identify the associated risk factors.

DESIGN

Cross-sectional study.

METHODS

The identified subjects were collected from 2012 wave of a national Chinese Longitudinal Healthy Longevity Survey. Older people were defined as being 65 years of age or older. We used chi-square test and binary logistic regression to investigate the risk factors of pressure injury development.

RESULTS

A total of 55 older people were documented as suffering from pressure injuries among 6,961 older Chinese adults, with a prevalence of 0.8%. In the group of disability, the prevalence of pressure injuries from high to low was 3.6% in the highly limited group, 0.4% in the moderately limited group, and 0.3% in the not limited group. The prevalence of pressure injury among older people with stroke, cancer, and dementia were 2%, 4.2%, and 6.6%, respectively. According to the final binary logistic regression analysis, age, disability, incontinence, cancer, and dementia emerged as important risk factors for pressure injury development.

CONCLUSION

Pressure injury among Chinese community-dwelling aged people was shown to be associated with age, disability, incontinence, cancer, and dementia. As the development of pressure injury may distinctly increase the burden on individuals and healthcare systems, the social and related institutions should actively prevent and control the disease.

IMPACT

The results of this study will improve the identification of pressure injury among older Chinese people and contribute to the development of effective pressure injury risk management interventions.

Impact of Admission Imaging Findings on Neurological Outcomes in Acute Cervical Traumatic Spinal Cord Injury

Variable and unpredictable spontaneous recovery can occur after acute cervical traumatic spinal cord injury (tSCI). Despite the critical clinical and interventional trial planning implications of this tSCI feature, baseline measures to predict neurologic recovery accurately are not well defined. In this study, we used data derived from 99 consecutive patients (78 male, 21 female) with acute cervical tSCIs to assess the sensitivity and specificity of various clinical and radiological factors in predicting recovery at one year after injury. Categorical magnetic resonance imaging parameters included maximum canal compromise (MCC), maximum spinal cord compression (MSCC), longitudinal length of intramedullary lesion (IML), Brain and Spinal Injury Center (BASIC) score, and a novel derived Combined Axial and Sagittal Score (CASS). Logistic regression analysis of the area under the receiver operating characteristic curve (AUC) was applied to assess the differential predictive value of individual imaging markers. Admission American Spinal Injury Association Impairment Scale (AIS) grade, presence of a spinal fracture, and central cord syndrome were predictive of AIS conversion at one year. Both BASIC and IML were stronger predictors of AIS conversion compared with MCC and MSCC (p = 0.0002 and p = 0.04). The BASIC score demonstrated the highest overall predictive value for AIS conversion at one year (AUC 0.94). We conclude that admission intrinsic cord signal findings are robust predictive surrogate markers of neurologic recovery after cervical tSCI. Direct comparison of imaging parameters in this cohort of patients indicates that the BASIC score is the single best acute predictor of the likelihood of AIS conversion.

The use of classification tree analysis to assess the influence of surgical timing on neurological recovery following severe cervical traumatic spinal cord injury

STUDY DESIGN

Post hoc analysis of prospectively collected data.

OBJECTIVES

Assess the influence of surgical timing on neurological recovery using classification tree analysis in patients sustaining cervical traumatic spinal cord injury.

SETTING

Hôpital du Sacré-Coeur de Montreal METHODS: 42 patients sustaining cervical SCI were followed for at least 6 months post injury. Neurological status was assessed from the American Spinal Injury Association impairment scale (AIS) and neurological level of injury (NLI) at admission and at follow-up. Age, surgical timing, AIS grade at admission and energy of injury were the four input parameters. Neurological recovery was quantified by the occurrence of improvement by at least one AIS grade, at least 2 AIS grades and at least 2 NLI.

RESULTS

Proportion of patients that improved at least one ASIA grade was higher in the group that received early surgery (75 vs. 41 %). The proportion of patients that improved two AIS grades was also higher in the group that received early surgery (67 vs. 38 %). Finally, 30 % of the patients that received early decompression improved two NLI as compared with 0% in the other group. Early surgery was also associated with a non-statistically significant improvement in functional recovery.

CONCLUSIONS

Neurological recovery of patients sustaining cervical traumatic spinal cord injury can be improved by early decompression surgery performed within 19 h post trauma.

SPONSORSHIP

U.S. Army Medical Research and Material Command, Rick Hansen Institute.