A multiview deep learning-based prediction pipeline augmented with confident learning can improve performance in determining knee arthroplasty candidates.

PURPOSE: Preoperative prudent patient selection plays a crucial role in knee osteoarthritis management but faces challenges in appropriate referrals such as total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA) and nonoperative intervention. Deep learning (DL) techniques can build prediction models for treatment decision-making. The aim is to develop and evaluate a knee arthroplasty prediction pipeline using three-view X-rays to determine the suitable candidates for TKA, UKA or are not arthroplasty candidates. METHODS: A study was conducted using three-view (anterior-posterior, lateral and patellar) X-rays and surgical data of patients undergoing TKA, UKA or nonarthroplasty interventions from sites A and B. Data from site A were used to derive and validate models. Data from site B were used as external test set. A DL pipeline combining YOLOv3 and ResNet-18 with confident learning (CL) was developed. Multiview Convolutional Neural Network, EfficientNet-b4, ResNet-101 and the proposed model without CL were also trained and tested. The models were evaluated using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivity and F1 score. RESULTS: The data set comprised a total of 1779 knees. Of which 1645 knees were from site A as a derivation set and an internal validation cohort. The external validation cohort consisted of 134 knees. The internal validation cohort demonstrated superior performance for the proposed model augmented with CL, achieving an AUC of 0.94 and an accuracy of 85.9%. External validation further confirmed the model's generalisation, with an AUC of 0.93 and an accuracy of 82.1%. Comparative analysis with other neural network models showed the proposed model's superiority. CONCLUSIONS: The proposed DL pipeline, integrating YOLOv3, ResNet-18 and CL, provides accurate predictions for knee arthroplasty candidates based on three-view X-rays. This prediction model could be useful in performing decision making for the type of arthroplasty procedure in an automated fashion. LEVEL OF EVIDENCE: Level III, diagnostic study.

The causal relationship between psoriasis and artificial joint re-operation after arthroplasty: A two-sample Mendelian randomization study.

BACKGROUND: Psoriasis is observationally associated with a higher risk of complications of arthroplasty; however, the causal effects of psoriasis on complications of arthroplasty are yet to be established. This study was to explore the causal effect of psoriasis on artificial joint re-operation after arthroplasty through two-sample Mendelian randomization (MR). METHODS: In the MR analysis, psoriasis was selected as the exposure in this study while single-nucleotide polymorphisms (SNPs) from a genome-wide association study (GWAS) were selected as the instrumental variables (IVs). Summary statistics data on artificial joint re-operation was extracted from publicly available GWAS data, including 218 792 European descent individuals. MR analysis was performed using the standard inverse variance weighted method (IVW). Furthermore, MR Egger, weighted median, simple mode, weighted mode, and the MR-PRESSO (Mendelian Randomization Pleiotropy Residual Sum and Outlier) test were also done to verify the results. Finally, the sensitivity analysis was executed. RESULTS: The IVW showed that psoriasis increases the risk of artificial joint re-operation (OR = 1.12; 95% CI = (1.01, 1.25); p = 0.036). This outcome was also verified by other methods including weighted median (OR = 1.16; 95% CI = (1.03, 1.31); p = 0.015), MR Egger (OR = 1.22; 95% CI = (1.03, 1.44); p = 0.038), and weighted mode (OR = 1.16; 95% CI = (1.03, 1.30); p = 0.025). No heterogeneity and directional pleiotropy were observed upon sensitivity analysis. CONCLUSION: The present study showed that psoriasis has a potential causal effect on artificial joint re-operation after arthroplasty. Further studies are warranted to elucidate the underlying mechanisms of causal associations between psoriasis on re-operation.

Femoral Nerve Block and Local Instillation Analgesia Associated With More Reliable Efficacy in Regional Anesthesia Interventions Within 24 Hours Following Anterior Cruciate Ligament Reconstruction: A Network Meta-analysis.

PURPOSE: To assess the relative effectiveness of different regional anesthetic techniques (peripheral nerve blocks, local instillation analgesia, including intra-articular, subcutaneous, and periarticular infiltration) in patients undergoing anterior cruciate ligament reconstruction (ACLR). METHODS: PubMed, Embase, Cochrane Library, and Web of Science databases were searched from their inception to December 31, 2020. The search was supplemented by manual review of relevant reference lists. Randomized controlled trials of participants after ACLR that compared regional anesthesia interventions were selected. The 2 coprimary outcomes were (1) rest pain scores and (2) cumulative oral morphine equivalent consumption on day 1 (24 hours) post-ACLR. Data were pooled using a Bayesian framework. RESULTS: Of 759 records identified, 46 trials were eligible, evaluating 9 interventions in 3,171 patients. Local instillation analgesia (LIA), including intra-articular, subcutaneous, and periarticular infiltration, had significant improvement in pain relief as compared with placebo (-0.91; 95% CrI -1.45 to -0.37). Femoral nerve block (FNB) also showed significant effects in relieving pain as compared with placebo (-0.70; 95% 95% credible interval [CrI] -1.28 to -0.12). Compared with placebo, a significant reduction in opioid consumption was found in LIA (mean difference -13.29 mg; 95% CrI -21.77 to -4.91) and FNB (mean difference -13.97 mg; 95% CrI -24.71 to -3.04). Femoral and sciatic nerve block showed the greatest ranking for pain relief and opioid consumption without significant evidence (P > .05) to support superiority in comparison with placebo, respectively. CONCLUSIONS: Our meta-analysis shows that FNB and LIA can significantly diminish postoperative pain and reduce opioid consumption following ACLR compared with placebo in the setting of regional anesthesia, and femoral and sciatic nerve block may be the number 1 top-ranked analgesic technique despite high uncertainty. LEVEL OF EVIDENCE: I, Systematic review of Level I studies.