Research lane 03
AI & Imaging
Machine-learning and generative-AI studies in orthopaedics, from fracture and meniscus detection on radiographs, CT, and MRI to models that predict complications after surgery. We also test how accurate and readable chatbot answers to patient questions are.
- Publications
- 7
- Presentations
- 13
Guiding questions
What this lane asks
Detection
Can a model find and classify fractures and meniscus tears on radiographs, CT, or MRI?
Prediction
Can routinely collected data predict who will have a complication after surgery?
Patient answers
How accurate and readable are chatbot answers to a real patient question?
Selected work
Key publications
Journal Article
Meta-analysis and Systematic Review of Diagnostic Performance of Machine Learning Algorithms on Skeletally Mature Wrist Fractures
Show all 10 authors
Wrist fractures are prevalent, and the diagnostic performance of artificial intelligence for their detection requires clarification. This study aims to determine the diagnostic accuracy of machine learning in detection of scaphoid fractures, distal radius fractures, and other types of wrist fractures on skeletally mature wrist radiographs through a meta-analysis while accounting for heterogeneity of studies using a random-effects model. In addition, this study will compare the results of machine learning to those of experts, including orthopedic surgeons, hand surgeons, and radiologists.
Journal Article
Diagnostic Accuracy of Artificial Intelligence for Detection of Meniscus Pathology on Magnetic Resonance Imaging: A Systematic Review
Meniscus tears can be difficult to diagnose on magnetic resonance imaging (MRI) due to the various types of tears. As artificial intelligence (AI) continues to advance, it could serve as a valuable tool that assists physicians with diagnostic accuracy and efficiency. The purpose of this study was to analyze the performance of AI in diagnosing meniscus tears on MRI using an array of studies and to compare the performance of AI to that of physicians. A literature search was conducted on PubMed and Embase for articles regarding the use of AI for the detection of meniscus tears. AI model, number of MRI studies, sensitivity, specificity, accuracy, AUC, and comparison to physicians encompassed the data that was extracted. A total of 18 studies, comprising 47,621 MRIs, were included in this review. The AUC of these AI models ranged from 0.781 to 0.984, averaging 0.912±0.053. The pooled sensitivity and specificity were 0.831±0.097 and 0.868±0.088, respectively. Three of these studies compared their results to those of 10 radiologists and two orthopedic surgeons. When comparing the sensitivity and specificity of AI models to those of physicians, Cochrane's Q was statistically significant (p < 0.01) with large heterogeneity amongst the two groups (I2 = 84.72%). The results suggest that AI's ability to detect meniscus lesions on MRI was relatively strong. When this performance was compared to that of physicians, the results were comparable, highlighting the potential benefits in a clinical setting.
Credited on this lane
Investigators & contributors
Publications
2026, 2 publications
2025, 3 publications
Show 2 more publications
2025, 1 publication
2024, 1 publication
Presentations
Poster presentation · 2025
Evaluating Quality and Readability of Information Provided by Generative Artificial Intelligence Chatbots on Clavicle Fracture Treatment Options
Poster presentation · 2025
Meta-Analysis and Systematic Review of Diagnostic Performance of Machine Learning Algorithms on Adult Wrist Fractures
Poster presentation · 2024
A Comparison of Convolutional Neural Networks Versus Orthopedic Physicians in Diagnosing Knee Osteoarthritis Severity
Show 10 more
Podium presentation · 2024
Assessing Quality and Readability of AI Responses on Patellar Tendon Repair
Podium presentation · 2024
Comparing Diagnostic Metrics of Osteoarthritis Severity between AI Neural Networks and Orthopaedic Physicians
Poster presentation · 2024
Comparing Diagnostic Metrics of Osteoarthritis Severity Between AI Neural Networks and Orthopedic Physicians
Poster presentation · 2024
Evaluating AI Language Model Quality of Information Regarding Achilles Rupture
Poster presentation · 2024
Evaluating Quality and Readability of Information Provided by Generative Artificial Intelligence Chatbots on Clavicle Fracture Treatment Options
Podium presentation · 2024
Evaluating the Quality and Readability of Generative AI Chatbots Responses in the Management of Achilles Tendon Rupture
Podium presentation · 2024
Machine Learning Algorithms Predict Deleterious Outcomes after Elective Trimalleolar ORIF
Poster presentation · Podium presentation · 2024
Machine Learning Predicts Complications Following Cephalomedullary Osteosynthesis of Intertrochanteric Fractures
Podium presentation · 2024
The Diagnostic Accuracy of Machine Learning on Adult Wrist Radiographs
Poster presentation · 2024
The Role of AI in Patient Education: Assessing Quality and Readability of Responses on Patella Tendon Repair
Collaborate
Working on a related question?
Propose a project in this lane, or join the group and take part in ongoing work.