Prediction of poststroke independent walking using machine learning: a retrospective study.

BACKGROUND: Accurately predicting the walking independence of stroke patients is important. Our objective was to determine and compare the performance of logistic regression (LR) and three machine learning models (eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest (RF)) in predicting walking independence at discharge in stroke patients, as well as to explore the variables that predict prognosis. METHODS: 778 (80% for the training set and 20% for the test set) stroke patients admitted to China Rehabilitation Research Center between February 2020 and January 2023 were retrospectively included. The training set was used for training models. The test set was used to validate and compare the performance of the four models in terms of area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: Among the three ML models, the AUC of the XGBoost model is significantly higher than that of the SVM and RF models (P < 0.001, P = 0.024, respectively). There was no significant difference in the AUCs between the XGBoost model and the LR model (0.891 vs. 0.880, P = 0.560). The XGBoost model demonstrated superior accuracy (87.82% vs. 86.54%), sensitivity (50.00% vs. 39.39%), PPV (73.68% vs. 73.33%), NPV (89.78% vs. 87.94%), and F1 score (59.57% vs. 51.16%), with only slightly lower specificity (96.09% vs. 96.88%). Together, the XGBoost model and the stepwise LR model identified age, FMA-LE at admission, FAC at admission, and lower limb spasticity as key factors influencing independent walking. CONCLUSION: Overall, the XGBoost model performed best in predicting independent walking after stroke. The XGBoost and LR models together confirm that age, admission FMA-LE, admission FAC, and lower extremity spasticity are the key factors influencing independent walking in stroke patients at hospital discharge. TRIAL REGISTRATION: Not applicable.

Efficacy of Multiple Exercise Therapy after Coronary Artery Bypass Graft: A Systematic Review of Randomized Control Trials.

Background: Coronary artery bypass graft (CABG) is intended to restore myocardial perfusion and alleviate morbidity among patients suffering from coronary artery disease. Due to procedural complexity, and anesthetic medications, post-operative complications are more prevalent, requiring the integration of rehabilitation strategies. This review aimed to determine the effect of single and multiple exercise therapy on rehabilitation after CABG surgery. Methods: We conducted a systematic search of databases (EBSCOhost, Scopus, PubMed, and Web of Science) from 01 January 2000 to 15 September 2022. The protocol of this systematic review is registered to PROSPERO. Results: We found nine randomized control trials composed of 599 CABG patients. In-patient cardiac rehabilitation (CR), a combination of inspiratory muscle training, mobilization, active upper and lower limb exercise, and aerobic exercise as multiple exercise therapy, found significant improvement in 6-minute walking distance (6MWD) than single exercise therapy (breathing exercise) at discharge and follow-up (moderate quality evidence). Contrary, multiple exercises group compared to single exercise groups did not improve the peak volume of oxygen ( VO 2 ) at discharge. Still, significant improvement was found at follow-up (moderate quality of evidence). On the other hand, the out-patient CR made up of high-intensity inspiratory muscle training, upper and lower limbs resistance training, and aerobic exercise as multiple exercise therapy significantly improved 6MWD and peak VO 2 at discharge (High-quality evidence). Conclusions: Our review revealed that multiple exercise therapy significantly improves functional and exercise capacity in in-patient and out-patient cardiac rehabilitation settings than single exercise therapy, but more than double exercise therapy protocol may be inefficient for improvement of quality of life. Inspiratory muscle training and resistance training in exercise therapy protocols significantly supplant the outcome, which requires further investigation.

Optogenetic Neuromodulation in Inflammatory Pain.

Inflammatory pain is one of the most prevalent forms of pain and negatively influences the quality of life. Neuromodulation has been an expanding field of pain medicine and is accepted by patients who have failed to respond to several conservative treatments. Despite its effectiveness, neuromodulation still lacks clinically robust evidence on inflammatory pain management. Optogenetics, which controls particular neurons or brain circuits with high spatiotemporal accuracy, has recently been an emerging area for inflammatory pain management and studying its mechanism. This review considers the fundamentals of optogenetics, including using opsins, targeting gene expression, and wavelength-specific light delivery techniques. The recent evidence on application and development of optogenetic neuromodulation in inflammatory pain is also summarised. The current limitations and challenges restricting the progression and clinical transformation of optogenetics in pain are addressed. Optogenetic neuromodulation in inflammatory pain has many potential targets, and developing strategies enabling clinical application is a desirable therapeutic approach and outcome.

Interactions between circulating inflammatory factors and autism spectrum disorder: a bidirectional Mendelian randomization study in European population.

Background: Extensive observational studies have reported an association between inflammatory factors and autism spectrum disorder (ASD), but their causal relationships remain unclear. This study aims to offer deeper insight into causal relationships between circulating inflammatory factors and ASD. Methods: Two-sample bidirectional Mendelian randomization (MR) analysis method was used in this study. The genetic variation of 91 circulating inflammatory factors was obtained from the genome-wide association study (GWAS) database of European ancestry. The germline GWAS summary data for ASD were also obtained (18,381 ASD cases and 27,969 controls). Single nucleotide polymorphisms robustly associated with the 91 inflammatory factors were used as instrumental variables. The random-effects inverse-variance weighted method was used as the primary analysis, and the Bonferroni correction for multiple comparisons was applied. Sensitivity tests were carried out to assess the validity of the causal relationship. Results: The forward MR analysis results suggest that levels of sulfotransferase 1A1, natural killer cell receptor 2B4, T-cell surface glycoprotein CD5, Fms-related tyrosine kinase 3 ligand, and tumor necrosis factor-related apoptosis-inducing ligand are positively associated with the occurrence of ASD, while levels of interleukin-7, interleukin-2 receptor subunit beta, and interleukin-2 are inversely associated with the occurrence of ASD. In addition, matrix metalloproteinase-10, caspase 8, tumor necrosis factor-related activation-induced cytokine, and C-C motif chemokine 19 were considered downstream consequences of ASD. Conclusion: This MR study identified additional inflammatory factors in patients with ASD relative to previous studies, and raised a possibility of ASD-caused immune abnormalities. These identified inflammatory factors may be potential biomarkers of immunologic dysfunction in ASD.

Benefits and Risks Associated with Long-term Oral Anticoagulation after Successful Atrial Fibrillation Catheter Ablation: Systematic Review and Meta-analysis.

Oral anticoagulation (OAC) prevents thromboembolism yet greatly increases the risk of bleeding, inciting concern among clinicians. Current guidelines lack sufficient evidence supporting long-term OAC following successful atrial fibrillation catheter ablation (CA). A literature search was performed in PubMed, Google Scholar, Medline, and Scopus to seek out studies that compare continued and discontinued anticoagulation in post-ablation Atrial fibrillation (AF) patients. Funnel plots and Egger's test examined potential bias. Via the random-effects model, summary odds ratios (OR) with 95% confidence intervals (CI) were calculated using RevMan (5.4) and STATA (17.0). Twenty studies, including 22 429 patients (13 505 off-OAC) were analyzed. Stratified CHA2DS2-VASc score ≥2 examining thromboembolic events (TE) favored OAC continuation (OR 1.86; 95% CI: 1.02-3.40; P = .04). Sensitivity analysis demonstrated this association was attenuated. The on-OAC arm had greater incidence of major bleeding (MB) (OR 0.16; 95% CI: 0.08-0.95; P < .00001), particularly intracranial hemorrhage (ICH) and gastrointestinal bleeding (GI); (OR 0.17; 95% CI: 0.08-0.36; P < .00001) and (OR 0.12; 95% CI: 0.04-0.32; P < .0001), respectively. Our findings support sustained anticoagulation in patients with a CHA2DS2-VASc score of ≥2. Due to reduced outcome robustness, physician discretion is still advised.

Stem Cell Therapy for Diabetic Foot Ulcers: Theory and Practice.

Diabetic foot ulcers are associated with increases in limb amputation, morbidity, and mortality. Recently, a stem cell application is emerging as promising adjuvant therapy. We presented available remedies by conducting a literature review on the application, safety, and efficacy of stem cell therapy. Relevant literature, including randomized control trials and article journals, was obtained from reputable search engines (PubMed, Scopus, and Web of Science). We analyzed five credible cohorts, with variable sources of stem cells, in a total of 216 participants, 151 males and 65 females, age (mean ± SD) of 64.5 ± 9.6 years. With an average success of 86.41% in all Wagner-II lesions, mesenchymal SCA (stem cell application) is safe and effective, hence can significantly prevent limb amputation.