Photo Credit: SARINYAPINNGAM

The following is a summary of “Personalised decision support in the management of patients with musculoskeletal pain in primary physiotherapy care: a cluster randomised controlled trial (the SupportPrim project),” published in the October 2024 issue of Pain by Granviken et al. 

The SupportPrim PT clinical decision support system (CDSS) was developed using case-based reasoning, an artificial intelligence method, to aid in personalized musculoskeletal pain management.  

Researchers conducted a retrospective study to analyze the effectiveness of the SupportPrim PT CDSS in physiotherapy practice.  

They randomized 44 physiotherapists to use the CDSS with usual or usual care alone. The CDSS furnished personalized treatment recommendations based on 105 cases with positive outcomes. The case base remained unchanged during the study. About 724 patients with neck, shoulder, back, hip, knee, or complex pain were included (CDSS: 358, usual care: 366). Primary outcomes were assessed using multilevel logistic regression with Global Perceived Effect (GPE) and Patient-Specific Functional Scale (PSFS).  

The results showed that at 12 weeks, 165 out of 298 patients (55.4%) in the intervention group and 176 out of 321 patients (54.8%) in the control group reported improvement in GPE (odds ratio(OR), 1.18; CI, 0.50-2.78), for the PSFS, 173 out of 290 patients (59.7%) in the intervention group and 218 out of 310 patients (70.3%) in the control group reported clinically significant improvement in function (OR, 0.41; CI  0.20-0.85), GPE showed no significant differences between the groups , while PSFS favored a substantial difference in the control group, which was less than the prespecified threshold of 15%.  

Investigators concluded that in this cluster randomised trial evaluating the effectiveness of a CBR-driven CDSS in physiotherapy practice, they did not find significant differences in GPE between patients whose physiotherapists had access to the CDSS vs patients receiving usual care alone.  Study limitations were identified, emphasizing the necessity of research for managing musculoskeletal pain by using artificial intelligence applications. 

Source: journals.lww.com/pain/fulltext/9900/personalised_decision_support_in_the_management_of.742.aspx