Severity-dependent benefits of AI-assisted 3D planning in total hip arthroplasty: a Crowe I–IV subgroup and trend analysis
Bibliographic record
Abstract
PURPOSE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".