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.

Reliability and validity of the international standards for neurological classification of spinal cord injury in patients with non-traumatic spinal cord lesions.

STUDY DESIGN: Prospective, observational study. OBJECTIVES: The International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) represent the gold standard for the assessment of patients with spinal cord injury (SCI) and their measurement properties have been evaluated in patients with traumatic lesions. Albeit the ISNCSCI are widely used also for the assessment and prognosis of patients with non-traumatic SCI, a validation of this grading system in this sample has never been performed. Therefore, the aim of this study is to evaluate the measurement properties of the ISNCSCI in a population of persons with non-traumatic SCI. SETTING: Three Italian rehabilitation hospitals. METHODS: The sample included 140 patients with non-traumatic SCI of different etiology, level and grade, for a total of 169 evaluations performed by two examiners. Cronbach's Alpha was used to evaluate the internal consistency of the ISNCSCI various components. The agreement between two examiners of each center in the definition of different components was used to assess the inter-rater reliability. The construct validity was evaluated through the correlation of the ISNCSCI with the Spinal Cord Independence Measure (SCIM). RESULTS: The ISNCSCI showed substantial internal consistency, and substantial inter-rater agreement for AIS grade, cumulative motor and sensory scores. The motor scores for upper and lower extremity showed fair to moderate correlation with SCIM self-care and motility subscores, respectively. The ISNCSCI total motor score correlated with the total SCIM score. CONCLUSIONS: Our study demonstrates that the ISNCSCI are a valid and reliable tool for the assessment of patients with non-traumatic SCI.

The efficacy and safety of a combination of glucosamine hydrochloride, chondroitin sulfate and bio-curcumin with exercise in the treatment of knee osteoarthritis: a randomized, double-blind, placebo-controlled study.

BACKGROUND: Knee osteoarthritis (OA) conservative treatment aims to delay cartilage degeneration; chondroprotective agents are a valid approach in this sense. A commercially available dietary supplement, CartiJoint Forte, containing glucosamine hydrochloride (GH), chondroitin sulfate (CS) and Bio-Curcumin BCM-95®, was used in this trial. AIM: The aim of this study was to assess efficacy and safety of CartiJoint Forte combined with physical therapy in treating subjects with knee OA. DESIGN: A multicenter, prospective, randomized, double blind, placebo-controlled clinical trial. SETTING: Outpatients referred to the Rehabilitation Departments of two University Hospitals. POPULATION: Fifty-three patients were randomly assigned to an experimental group (N=26) or a control group (N.=27). Experimental subjects received two tablets of CartiJoint Forte each day for 8 weeks, while those in the control group were provided with a placebo. Three subjects dropped out during the course of the study. METHODS: The two groups both received 20 sessions of physical therapy during the course of the trial. Primary outcome was pain intensity, measured both at motion and at rest, using the Visual Analogue Scale (VAS). A secondary outcome was an assessment of knee function by Western Ontario and McMaster Universities Arthritis Index and Lequesne Index, knee ROM, and two inflammation markers (C-reactive protein and erythrocyte sedimentation rate). Each assessment was carried out at baseline (T0), at 8 weeks (T1) and at 12 weeks (T2). RESULTS: VAS at rest was found to be reduced between T0 and T1, as well as between T0 and T2 (F=13.712; P=0.0001), with no differences between groups (F=1.724; P=0.191). VAS at motion revealed a significant "group × time-check" interaction (F=2.491; P=0.032), with increasing effect of time on VAS reduction (F=17.748; P=0.0001). This was most pronounced in the experimental group at 8 weeks (F=3.437; P=0.045). The Lequesne Index showed reductions at T1 and T2 compared to T0 (F=9.535; P=0.0001), along with group effect, since the experimental group presented a lower score at T2 (F=7.091; P=0.009). No significant changes were found in the knee ROM and inflammation markers. CONCLUSION: CartiJoint Forte, added to physical therapy, may ameliorate pain and help to improve algofunctional score in knee OA patients. CLINICAL REHABILITATION IMPACT: Treatment of knee OA with curcuminoids plus glycosaminoglycans, added to physical therapy, improves VAS at motion and Lequesne Index scores.