Comparison of artificial intelligence-assisted or CT-based 3-dimensional preoperative planning with conventional 2-dimensional templating in total hip arthroplasty.

Résumé de l'étude

12 studies involving adults undergoing total hip arthroplasty (THA) were included in this systematic review and meta-analysis comparing artificial intelligence (AI)-assisted or computed tomography (CT)-based 3-dimensional (3D) preoperative planning with conventional 2-dimensional (2D) templating. Because several studies used paired comparisons or reported hips, implant components, or planning observations rather than independent patients, a single overall patient total could not be reliably calculated. Pooled outcomes included exact-match acetabular cup and femoral stem size prediction, prediction accuracy within 1 implant size, operative time, intraoperative blood loss, and postoperative limb length discrepancy (LLD). Overall, 3D planning improved exact and within-1-size implant prediction accuracy and was associated with shorter operative time, less blood loss, and smaller postoperative LLD compared with 2D templating. However, the evidence supported 3D planning strategies broadly rather than demonstrating the independent superiority of AI, as several included systems did not explicitly incorporate AI algorithms.