In an attempt to standardize the X-ray analysis and to create relevant correlations between it and the functional results, we present a pilot model of an artificial neural network based on a Bayesian belief network (BNN) designed for the automatic analysis of anteroposterior X-ray of the knee following total knee arthroplasty and more precisely the analysis of the tibial component. A prospective analysis was conducted in which 30 patients were analyzed and two groups resulted: the first was made up of 12 cases considered “normal” by the examiners (optimal positioning and cementation) and the second one, which was considered “pathological” (incorrect positioning or cementation) and included 16 cases. Based on 22 points established on the tibial component several geometric sizes (calculated parameters) were computed. Several parameters were compared and the results were up to 75% accuracy, 81.25% sensitivity, and 66.7% specificity. BBNs can be a solution for X-ray evaluation of total knee arthroplasty and can improve the understanding of its evolution. It needs confirmation in time, its accuracy rising with the number of patients introduced in the analysis algorithm.
Background: Although locoregional anesthesia techniques in total knee arthroplasty (TKA) have progressed steadily, the emergence of the adductor canal block representing a step forward for postoperative evolution in preservation of the quadriceps muscle strength, analgesia of the posterior territory of the knee still remains a challenge. The emergence of IPACK, in association with earlier techniques, offers promising preliminary results in terms of its contribution to a favourable evolution and to the satisfaction of TKA patients. Materials and methods: Prospective trial performed on a group of 28 patients undergoing a total knee arthroplasty intervention; analgesia control in the postoperative period was performed either with opioid and nonopioid systemic analgesics, or by associating the continuous adductor canal block with IPACK and systemic analgesics. The primary objective is pain control at rest/on mobilization, while the secondary purpose is analysis of opioid use, their side effects and recovery of joint mobility. Results: There is a significantly better pain control in the group of patients with locoregional anesthesia, both at rest and on mobilization (p<0.005), accompanied by a decrease in opioid use (p<0.00001) and the related adverse reactions; at the same time, there is an improvement in the functional recovery of the knee joint, quantified by the flexion degree at 24 and 48 hours after surgery ( 61.5/71.12 degrees for continuous adductor canal block with IPACK versus 45.14/55.42 degrees for general anaesthesia) Conclusions: The introduction of peripheral nerve blocks in the multimodal analgesia regimen after TKA results in better control of postoperative pain, both at rest and on mobilization, in a decrease in opioid use and their related adverse reactions and in an improved recovery of joint range of motion, as well.
