Observational Study on AI Accuracy in Diagnosing and Treating Failed or Painful Hip Arthroplasty

Launched by ISTITUTO ORTOPEDICO RIZZOLI · May 31, 2025

Keywords

ClinConnect Summary

This clinical trial is studying how well an advanced artificial intelligence (AI) program called GPT-4 can diagnose and suggest treatments for patients who are experiencing problems after total hip replacements, which can be painful or have failed. The goal is to see if GPT-4 can match or even outperform orthopedic surgeons with different levels of experience when it comes to understanding these complex cases. The study will look at 20 patient cases from a hospital in Italy, focusing on those who have clear problems with their hip replacements documented between 2004 and 2024.

To be eligible for this study, participants must be adults aged 18 to 80 who have documented issues with their hip replacements that need evaluation. This means that their medical records should clearly show details about their condition and any treatments they have undergone. During the study, GPT-4 and three orthopedic doctors will review the same patient cases, providing their diagnoses and treatment recommendations. These will then be assessed for accuracy and completeness by independent evaluators. Importantly, the trial will use only anonymized patient data to protect privacy, and the results will be shared publicly, regardless of whether the AI performs better or worse than the doctors. This study could pave the way for AI to assist in making medical decisions in the future.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • Adults (≥18 and ≤80 years old).
• • Documented painful or failed total hip arthroplasty requiring clinical/radiological evaluation (2004-2024).
• • Complete pre-operative clinical history, imaging (X-ray/tomography), and surgical reports.
• • Clear diagnosis of failure mode (e.g., aseptic loosening, infection, fracture, wear).
• • Treatment and outcomes fully documented in the institutional database.
• • "Exemplary" cases with minimal diagnostic ambiguity (per Engh/MusculoSkleletal Infection Society criteria, etc.).
• Exclusion Criteria:
• • total hip arthroplasty with no documented failure/pain (well-functioning implants).
• • Incomplete clinical/radiological records (e.g., missing pre-operative imaging or surgical notes).
• • Complex/multifactorial failures (e.g., concurrent infection + loosening + fracture).
• • Radiographs/images non-interpretable (poor quality, missing views).
• • Cases with conflicting diagnoses/treatments in original records.