Severity-dependent benefits of AI-assisted 3D planning in total hip arthroplasty: a Crowe I-IV subgroup and trend analysis.
Authors
Affiliations (3)
Affiliations (3)
- Department of Orthopedics, Affiliated Mindong Hospital, Fujian Medical University, Ningde, Fujian, China.
- School of New Energy and Intelligent Manufacturing, Ningde Vocational and Technical College, Ningde, Fujian, China. [email protected].
- Department of Orthopedics, Affiliated Mindong Hospital, Fujian Medical University, Ningde, Fujian, China. [email protected].
Abstract
To compare AI-assisted 3D (AI-3D) preoperative planning versus two-dimensional (2D) X-ray preoperative planning for total hip arthroplasty (THA) using subgroup analyses (Crowe I-II vs. III-IV), and to examine associations between deformity severity and both planning accuracy and clinical outcomes via ordered trend analyses. Single-centre retrospective cohort including 116 consecutive patients undergoing THA (May 2020-July 2023; AI-3D n = 61; 2D X-ray n = 55). Co-primary endpoints were exact implant size-match (cup/stem) and acetabular safe-zone attainment (Lewinnek/Callanan); Secondary endpoints included operative time, estimated blood loss, postoperative leg-length discrepancy (LLD), and 24-month functional scores-Harris Hip Score (HHS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and pain on a visual analog scale (VAS)-plus implant survivorship. Analyses compared AI-3D versus 2D within prespecified Crowe subgroups; ordered trend tests across I-IV were performed in the pooled cohort. Overall comparisons showed that AI-3D demonstrated significantly higher accuracy in sizing prediction and acetabular cup positioning in this study: cup size-match 63.9% versus 41.8% (P = 0.017), stem size-match 65.6% versus 47.3% (P = 0.047), and Lewinnek/Callanan safe-zone attainment 91.8% versus 76.4% (P = 0.021); by contrast, operative time and blood loss did not differ significantly. Subgroup analyses suggested that this benefit was mainly confined to Crowe I-II, while in Crowe III-IV the differences were not significant. At the 24-month follow-up, HHS, WOMAC, VAS, and implant survivorship (≈ 98%) were comparable between groups. In trend analyses pooling both cohorts, cup match rates decreased as Crowe grade increased (P = 0.004), the extent of functional improvement (change in HHS (ΔHHS), change in WOMAC (ΔWOMAC)) rose with greater deformity severity (both P ≤ 0.001), and safe-zone attainment remained high without a clear monotonic trend. AI-3D preoperative planning provides measurable gains in implant sizing and acetabular cup positioning for THA, with benefits most evident in mild-to-moderate deformities (Crowe I-II). In severe deformities (Crowe III-IV), anatomical and reconstructive challenges appear to limit these advantages, emphasizing the continued importance of surgical expertise. Functional outcomes were comparable between AI-3D and conventional 2D planning. Overall, AI-3D may serve as a useful adjunct in complex cases, pending confirmation in larger multicentre and long-term studies.