Related Experiment Video
Updated: Oct 25, 2025
14:31
Bioelectric Analyses of an Osseointegrated Intelligent Implant Design System for Amputees
Published on: July 15, 2009
14.2K
Artificial intelligence in orthopedic implant model classification: a systematic review.
1Department of Orthopedic Surgery, Columbia University Irving Medical Center, New York, NY, USA.
Skeletal Radiology
|August 5, 2021
Summary
Artificial intelligence (AI) models show high accuracy in identifying orthopedic implants from images. Further research is needed to compare AI performance against human experts for optimal clinical use.
Area of Science:
- Orthopedic surgery
- Medical imaging
- Artificial intelligence
Background:
- Identifying orthopedic implant models from radiographs is crucial but time-consuming.
- Previous artificial intelligence (AI) research has shown promise, but scope and performance require evaluation.
Purpose of the Study:
- To systematically review the scope, methodology, and performance of AI algorithms in classifying orthopedic implant models.
Main Methods:
- A systematic literature search was conducted in PubMed, EMBASE, and Cochrane Library up to March 10, 2021.
- Studies were assessed using a modified Methodologic Index for Non-Randomized Studies.
- Key outcomes included area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.
Main Results:
- Eleven studies were included, evaluating 2 to 27 implant models.
- Reported overall AUC ranged from 0.94 to 1.0, with accuracy from 0.804 to 1.0.
- One study found AI performance comparable to that of three orthopedic surgeons.
Conclusions:
- AI algorithms demonstrate strong performance in classifying orthopedic implant models from radiographs.
- Significant variation exists in AI study methodologies and reporting quality.
- Further research should compare AI versus human experts and promote rigorous, transparent AI development and reporting.
