Objectives.
Aims
While internet search engines have been the primary information source for patients’ questions, artificial intelligence large language models like ChatGPT are trending towards becoming the new primary source. The purpose of this study was to determine if ChatGPT can answer patient questions about total hip (THA) and knee arthroplasty (TKA) with consistent accuracy, comprehensiveness, and easy readability.
Methods
We posed the 20 most Google-searched questions about THA and TKA, plus ten additional postoperative questions, to ChatGPT. Each question was asked twice to evaluate for consistency in quality. Following each response, we responded with, “Please explain so it is easier to understand,” to evaluate ChatGPT’s ability to reduce response reading grade level, measured as Flesch-Kincaid Grade Level (FKGL). Five resident physicians rated the 120 responses on 1 to 5 accuracy and comprehensiveness scales. Additionally, they answered a “yes” or “no” question regarding acceptability. Mean scores were calculated for each question, and responses were deemed acceptable if ≥ four raters answered “yes.”
We reviewed the outcome of 69 uncemented, custom-made, distal femoral endoprosthetic replacements performed in 69 patients between 1994 and 2006. There were 31 women and 38 men with a mean age at implantation of 16.5 years (5 to 37). All procedures were performed for primary malignant bone tumours of the distal femur. At a mean follow-up of 124.2 months (4 to 212), 53 patients were alive, with one patient lost to follow-up. All nine implants (13.0%) were revised due to aseptic loosening at a mean of 52 months (8 to 91); three implants (4.3%) were revised due to fracture of the shaft of the prosthesis and three patients (4.3%) had a peri-prosthetic fracture. Bone remodelling associated with periosteal cortical thinning adjacent to the uncemented intramedullary stem was seen in 24 patients but this did not predispose to failure. All aseptically loose implants in this series were diagnosed to be loose within the first five years.
The results from this study suggest that custom-made uncemented distal femur replacements have a higher rate of aseptic loosening compared to published results for this design when used with cemented fixation. Loosening of uncemented replacements occurs early indicating that initial fixation of the implant is crucial.
Cite this article: