Observational study of the effectiveness of spinal cord injury rehabilitation using the Spinal Cord Injury-Ability Realization Measurement Index

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.

Assessment of ability realization using the 4th version of the Spinal Cord Independence Measure

CONTEXT

Change in ability realization reflects the main contribution of rehabilitation to improvement in the performance of daily activities after spinal cord lesions (SCL).

OBJECTIVE

To adapt a Spinal Cord Ability Realization Measurement Index (SCI-ARMI) formula to the new Spinal Cord Independence Measure version 4 (SCIM4).

METHODS

Using data from 156 individuals for whom American Spinal Injury Association Motor Score (AMS) and SCIM4 scores were collected, we obtained an estimate for the highest possible SCIM4 given the patient's AMS value, using the 95th percentile of SCIM4 values at discharge from rehabilitation (SCIM95) for patients with any given AMS at discharge. We used the statistical software environment R to implement the quantile regression method for linear and quadratic formulas. We also compared the computed model with the SCIM95 model obtained using data from the present study group, positioned in the SCIM95 formula developed for SCIM3.

RESULTS

The coefficients of the computed SCIM95 formula based on SCIM4 scores were statistically non-significant, which hypothetically reflects the small sample relative to the goal of estimating SCIM4 95th percentile. Predicting the ability using SCIM4 scores positioned in the SCIM95 formula used for SCIM3, however, yielded SCIM95 values, which are very close to those of the new SCIM95 formula (Mean difference 2.16, 95% CI = 1.45, 4.90).

CONCLUSION

The SCI-ARMI formula, which is based on the SCIM95 formula developed for SCIM3, is appropriate for estimating SCI-ARMI at present, when SCIM4 scores are available. When sufficient additional data accumulates, it will be appropriate to introduce a modified SCI-ARMI formula.

The role of comprehensive rehabilitation in the care of degenerative cervical myelopathy

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

To find out if comprehensive rehabilitation itself can improve daily performance in persons with DCM.

SETTING

The spinal department of a rehabilitation hospital.

METHODS

Data from 116 DCM inpatients who underwent comprehensive rehabilitation after spinal surgery were retrospectively analyzed. The definitions of the calculated outcome variables made possible analyses that distinguished the effect of rehabilitation from that of spinal surgery. Paired t-tests were used to compare admission with discharge outcomes and functional gains. Spearman's correlations were used to assess relationships between performance gain during rehabilitation and between time from surgery to rehabilitation.

RESULTS

The Spinal Cord Injury Ability Realization Measurement Index (SCI-ARMI) increased during rehabilitation from 57 (24) to 78 (19) (p < 0.001). The Spinal Cord Independence Measure 3rd version (SCIM III) gain attributed to neurological improvement (dSCIM-IIIn) was 6.3 (9.2), and that attributed to rehabilitation (dSCIM-IIIr) 16 (18.5) (p < 0.001). dSCIM-IIIr showed a rather weak negative correlation with time from spinal surgery to rehabilitation (r = -0.42, p < 0.001).

CONCLUSIONS

The study showed, for the first time, that comprehensive rehabilitation can achieve considerable functional improvement for persons with DCM of any degree, beyond that of spinal surgery. Combined with previously published evidence, this indicates that comprehensive rehabilitation can be considered for persons with DCM of any functional degree, before surgery.

The net contribution of rehabilitation to improvement in performance in patients with spinal cord lesions in five countries

CONTEXT

Change in ability realization reflects the main contribution of rehabilitation to improvement in the performance of daily activities in patients with spinal cord lesions (SCL).

OBJECTIVE

To assess the net effect of rehabilitation of patients with SCL and compare it between countries.

METHODS

We calculated the Spinal Cord Ability Realization Measurement Index (SCI-ARMI) and its change from admission to rehabilitation to discharge, for inpatients admitted to SCL units in five countries, between 2016 and 2019. We used chi-square tests, analysis of variance (ANOVA), McNemar's test, Pearson's correlations, and analysis of covariance (ANCOVA) to compare countries and patient groups and assess the relationships of various factors with SCI-ARMI gain during rehabilitation.

RESULTS

The study included 218 inpatients (67% males, age 52 ± 17). In Brazil, Israel, Italy, Portugal, and Turkiye, respectively, SCI-ARMI gain was 2 (SD = 15), 19 (SD = 17), 31 (SD = 23), 13 (SD = 15), and 16 (SD = 12). Yet, after controlling for admission SCI-ARMI and the time from SCL onset to the examination, the effect of the country on ability realization gain was found non-significant (P = 0.086).

CONCLUSION

The study confirmed that rehabilitation makes a net contribution to improvement in performance in patients with SCL, beyond the contribution of neurological recovery. After controlling for affecting factors, this contribution was quite similar in the participating units from different countries.

Ability Realization Improves During Inpatient Rehabilitation for Guillain-Barré Syndrome

OBJECTIVE

The aim of the study was to investigate improvement in ability realization and additional long-term outcomes, during and after inpatient rehabilitation for Guillain-Barré syndrome.

DESIGN

This is a retrospective, longitudinal cohort study, in which outcomes were examined using validated scales, for 47 inpatients with Guillain-Barré syndrome.

RESULTS

Scores improved from 65 on the American Spinal Injury Association Motor Score and 50 on the Spinal Cord Independence Measure, at admission to inpatient rehabilitation, to 81 and 80 at discharge, and to 92 and 95 at the end of 7.5 yrs, on average, at the follow-up ( P = 0.001). The mean Spinal Cord Independence Measure/American Spinal Injury Association Motor Score ratio, which reflects the ability realization, increased during rehabilitation from 50/65 to 80/81 ( P = 0.001), and tended to increase further at follow-up to 95/92 ( P = 0.228). At follow-up, pain did not correlate, and fatigue showed a weak correlation with the American Spinal Injury Association Motor Score, Spinal Cord Independence Measure, and the Adult Subjective Assessment of Participation ( r = -0.363, P = 0.012; r = -0.362, P = 0.012; r = -0.392, P = 0.006).

CONCLUSIONS

Ability realization improved during inpatient rehabilitation for Guillain-Barré syndrome and remained high after discharge, suggesting a likely contribution of rehabilitation to the functional outcome, beyond the contribution of neurological recovery. Despite residual fatigue and pain, there was only minor or no effect on daily function or participation.

Conceptual changes needed to improve outcomes in rehabilitation medicine: A clinical commentary

Rehabilitation medicine has expanded the horizon of all medicine and brought about new human achievements. To facilitate continued advances in achievement, several changes are suggested in customary rehabilitation strategic goals, concepts, and practices. The main rehabilitation goals should focus on prolonged survival, contrary to the opinions of most authors on rehabilitation, and on achievement of maximum ability realization, rather than of independence or any given (including previous) level of functioning. Setting rehabilitation goals should benefit the patient, rather than the caregiver or the insurer. Training should focus on tasks that contribute to the patients' interests and desires, rather than on any task that reduces the burden of care. The main criterion for admission to a rehabilitation ward should be based on expected advantage in prolonging patient survival and maximizing ability realization.

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.

Prediction Model for the Presence of Complications at Admission to Rehabilitation After Traumatic Spinal Cord Injury

Background: Complications frequently occur in patients with spinal cord injury (SCI) during acute care or rehabilitation and have an impact on rehabilitation outcomes. Purpose: The aim of this study was to determine the occurrence and risk factors for complications in recently injured SCI patients. Methods: Two hundred fifty patients with traumatic injuries with and without complications were counted for the following dichotomous parameters: gender (male/female), associated lesions (presence/absence), surgery (yes/no), American Spinal Injury Association Impairment Scale (AIS) grade (A/other categories), lesion level (lumbar/other levels), and lesion-to-admission time (less than/longer than 1 month). The odds ratio (OR) and 95% confidence interval were computed for all the parameters that influenced the presence of complications at admission. These factors have been included in a binary logistic regression analysis (forward stepwise). Results: Complications at admission were observed in 104 patients (41.6%), especially for males, lesion-to-admission time longer than 1 month, presence of associated lesions, AIS grade A, and motor completeness, whereas lumbar lesions were associated with a reduced presence of complications at admission. In the regression analysis, 4 factors entered into the model: motor completeness, lesion-to-admission time, associated lesions, and gender. The final model explained 74% of the variance of data. Conclusions: Despite advances in the acute management of patients with SCI, the study unveiled a high percentage of patients with complications at admission to rehabilitation. The risk factors identified in the study allow determination of the population of subjects who are at higher risk of developing complications and need special management.

Long-term functional outcome in patients with acquired infections after acute spinal cord injury

OBJECTIVE

To investigate whether prevalent hospital-acquired pneumonia and wound infection affect the clinical long-term outcome after acute traumatic spinal cord injury (SCI).

METHODS

This was a longitudinal cohort study within the prospective multicenter National Spinal Cord Injury Database (Birmingham, Alabama). We screened datasets of 3,834 patients enrolled in 20 trial centers from 1995 to 2005 followed up until 2016. Eligibility criteria were cervical SCI and American Spinal Cord Injury Association impairment scale A, B, and C. Pneumonia or postoperative wound infections (Pn/Wi) acquired during acute medical care/inpatient rehabilitation were analyzed for their association with changes in the motor items of the Functional Independence Measure (FIM_motor) using regression models (primary endpoint 5-year follow-up). Pn/Wi-related mortality was assessed as a secondary endpoint (10-year follow-up).

RESULTS

A total of 1,203 patients met the eligibility criteria. During hospitalization, 564 patients (47%) developed Pn/Wi (pneumonia n = 540; postoperative wound infection n = 11; pneumonia and postoperative wound infection n = 13). Adjusted linear mixed models after multiple imputation revealed that Pn/Wi are significantly associated with lower gain in FIM_motor up to 5 years after SCI (-7.4 points, 95% confidence interval [CI] -11.5 to -3.3). Adjusted Cox regression identified Pn/Wi as a highly significant risk factor for death up to 10 years after SCI (hazard ratio 1.65, 95% CI 1.26 to 2.16).

CONCLUSION

Hospital-acquired Pn/Wi are predictive of propagated disability and mortality after SCI. Pn/Wi qualify as a potent and targetable outcome-modifying factor. Pn/Wi prevention constitutes a viable strategy to protect functional recovery and reduce mortality. Pn/Wi can be considered as rehabilitation confounders in clinical trials.