The Use of Machine Learning for Inferencing the Effectiveness of a Rehabilitation Program for Orthopedic and Neurological Patients.

Advance assessment of the potential functional improvement of patients undergoing a rehabilitation program is crucial in developing precision medicine tools and patient-oriented rehabilitation programs, as well as in better allocating resources in hospitals. In this work, we propose a novel approach to this problem using machine learning algorithms focused on assessing the modified Barthel index (mBI) as an indicator of functional ability. We build four tree-based ensemble machine learning models and train them on a private training cohort of orthopedic (OP) and neurological (NP) hospital discharges. Moreover, we evaluate the models using a validation set for each category of patients using root mean squared error (RMSE) as an absolute error indicator between the predicted mBI and the actual values. The best results obtained from the study are an RMSE of 6.58 for OP patients and 8.66 for NP patients, which shows the potential of artificial intelligence in predicting the functional improvement of patients undergoing rehabilitation.

Extracorporeal shock-wave therapy for supraspinatus calcifying tendinitis: a randomized clinical trial comparing two different energy levels.

BACKGROUND: Extracorporeal shock-wave therapy (ESWT) represents a valid intervention in the treatment of people with supraspinatus calcifying tendinitis (SCT), but there is limited evidence for the useful range of ESWT doses. OBJECTIVE: The aim of this study was to compare 2 different ranges of energy flux density in treatment of SCT with ESWT. DESIGN: This study was designed as a single-blind randomized clinical trial. SETTING: This study was performed in a university hospital. PATIENTS: Forty-six patients with SCT were randomly assigned to 2 groups that received different therapeutic energy doses of ESWT: (1) group A received ESWT at an energy level of 0.20 mJ/mm², and (2) group B received ESWT at an energy level of 0.10 mJ/mm². INTERVENTION: The treatment protocol consisted of 4 sessions performed once a week. MEASUREMENTS: The change in mean Constant Murley Scale (CMS) scores at 3 and 6 months was the primary endpoint. The change in the mean visual analog scale (VAS) scores from baseline to 3 and 6 months after the intervention and radiographic change in size of calcium deposits were evaluated as secondary endpoints. At 12 months, pain relief was assessed using a numeric rating scale. RESULTS: Significant clinical improvement based on mean CMS scores was observed after 6 months in group A (X=79.43, SD=10.33) compared with group B (X=57.91, SD=6.53). Likewise, after 6 months, a significant decrease in VAS scores was found in group A (X=2.09, SD=1.54) compared with group B (X=5.36, SD=0.78). Calcific deposits disappeared in the same percentage of patients in both groups. LIMITATIONS: The small sample size and lack of a control group were limitations of the study. CONCLUSIONS: In ESWT for SCT, an energy level of 0.20 mJ/mm² appears to be more effective than an energy level of 0.10 mJ/mm² in pain relief and functional improvement.