Comparison of Artificial Intelligence and Traditional Methods in Preoperative Planning for Primary Total Hip...

Although the application of artificial intelligence in orthopedics is becoming increasingly widespread, and initial progress has been made particularly in total hip arthroplasty (THA), its use in preoperative planning remains in the exploratory stage. Most existing studies are small-scale observational studies with inconsistent results, making it difficult to establish a unified clinical consensus. Therefore, our study aims to explore the latest research developments and potential unique advantages of artificial intelligence in preoperative planning for THA. We conducted a comprehensive literature search in PubMed, Embase, Web of Science, and the Cochrane Library, covering all publications up to April 23, 2025. To evaluate study quality, we applied the revised Cochrane Risk of Bias tool for randomized controlled trials and the Newcastle-Ottawa Scale (NOS) for non-randomized studies. For the statistical analysis, odds ratios (OR) were used to assess categorical variables, while mean differences (MD) were calculated for continuous outcomes. Depending on the level of heterogeneity, a random-effects model was adopted when substantial heterogeneity was detected (I² > 50%); otherwise, a fixed-effects model was applied. Through this process, a total of 518 studies were initially identified, of which 16 met the predefined inclusion criteria. The pooled analysis demonstrated that, in comparison to traditional methods, artificial intelligence achieved significantly superior outcomes in several key areas: acetabular-side matching accuracy (OR = 0.24), femoral-side matching accuracy (OR = 0.24), postoperative leg length discrepancy (MD = -1.02), operative time (MD = -12.18 min), intraoperative blood loss (MD = -50.82 mL), and postoperative Harris hip score (MD = 1.42). Notably, the overall methodological quality of the included studies was generally high. The final results of the study indicate that, compared to traditional preoperative planning, artificial intelligence in preoperative planning for THA can provide more precise surgical guidance, reduce surgical risks, and improve the overall success rate of the procedure. Trial Registration: PROSPERO registration number: CRD42024619714.