Exploratory analysis of 5 supervised machine learning models for predicting the efficacy of the endogenous pain inhibitory pathway in patients with musculoskeletal pain.

OBJECTIVES: The identification of factors that influence the efficacy of endogenous pain inhibitory pathways remains challenging due to different protocols and populations. We explored five machine learning (ML) models to estimate the Conditioned Pain Modulation (CPM) efficacy. DESIGN: Exploratory, cross-sectional design. SETTING AND PARTICIPANTS: This study was conducted in an outpatient setting and included 311 patients with musculoskeletal pain. METHODS: Data collection included sociodemographic, lifestyle, and clinical characteristics. CPM efficacy was calculated by comparing the pressure pain thresholds before and after patients submerged their non-dominant hand in a bucket of cold water (cold-pressure test) (1-4 °C). We developed five ML models: decision tree, random forest, gradient-boosted trees, logistic regression, and support vector machine. MAIN OUTCOME MEASURES: Model performance were assessed using receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, recall, F1-score, and the Matthews Correlation Coefficient (MCC). To interpret and explain the predictions, we used SHapley Additive explanation values and Local Interpretable Model-Agnostic Explanations. RESULTS: The XGBoost model presented the highest performance with an accuracy of 0.81 (95% CI = 0.73 to 0.89), F1 score of 0.80 (95% CI = 0.74 to 0.87), AUC of 0.81 (95% CI: 0.74 to 0.88), MCC of 0.61, and Kappa of 0.61. The model was influenced by duration of pain, fatigue, physical activity, and the number of painful areas. CONCLUSIONS: XGBoost showed potential in predicting the CPM efficacy in patients with musculoskeletal pain on our dataset. Further research is needed to ensure the external validity and clinical utility of this model.

Meditation for adults with non-specific low back pain: a systematic review and meta-analysis.

OBJECTIVES: We aim to determine the effectiveness of meditation for adults with non-specific low back pain. METHODS: We searched PubMed, EMBASE, PEDro, Scopus, Web of Science, Cochrane Library, and PsycINFO databases for randomized controlled trials that investigated the effectiveness of meditation in adults with non-specific low back pain. Two reviewers rated risk of bias using the PEDro scale and the certainty of the evidence using the GRADE approach. Primary outcomes were pain intensity and disability. RESULTS: We included eight trials with a total of 1,234 participants. Moderate-certainty evidence shows that meditation is better than usual care for disability at short-term (SMD = -0.22; 95% CI = -0.42 to -0.02). We also found that meditation is better than usual care for pain intensity at long-term (SMD = -0.28; 95% CI = -0.54 to -0.02). There is no significant difference for pain intensity between meditation and minimal intervention or usual care at short and intermediate-term. We did not find differences between meditation and minimal intervention for disability at intermediate-term or usual care in any follow-up period. CONCLUSIONS: We found small effect sizes and moderate-certainty evidence that meditation is slightly better than minimal intervention in the short-term for disability. Low-certainty of evidence suggests that meditation is slightly better than usual care for pain in the long-term. Meditation appears to be safe with most trials reporting no serious adverse events.

Overview of Curricula About Pain in Physical Therapist Education Programs in Brazil: A Faculty Survey.

Background: Educating health professionals about pain (pain education) during undergraduate studies may be an important step in changing ineffective pain management practices. Objective: The objective of this study was to assess the extent of pain education in current accredited physical therapist education programs in Brazil. Design: This study was designed as a cross-sectional survey study. Methods: Brazilian physical therapist education programs accredited by the Ministry of Education participated in this study. The main outcome measures were frequency of a specific curriculum about pain (pain curriculum) in physical therapist education programs and content analysis according to discipline-specific pain curriculum recommendations developed by the International Association for the Study of Pain. Results: A total of 811 physical therapist education programs in Brazil were identified. After duplicates and universities no longer offering a physical therapist education program were removed, a total of 566 physical therapist education programs were left; 399 of the 566 (70.5%) provided information about the curriculum on their websites. Among the identified physical therapist education programs with available curricula, 26 (6.5%) had a specific course about pain (pain course), covering a mean of 44.3 hours. Limitations: Limitations included the inability to cover all the physical therapist education programs in Brazil and the inability to identify whether pain content is distributed in other disciplines such as pediatrics, geriatrics, and neurological and orthopedic physical therapy. Conclusions: Most Brazilian physical therapist education programs do not offer a specific pain course. When a pain course is presented in the curriculum, some content recommended for physical therapist education programs by the International Association for the Study of Pain is not covered. The absence of a pain course in physical therapist education programs may have implications for pain management. To the best of our knowledge, this is the first study about pain education in physical therapist education programs in Brazil.