Ferrum Health partners with best-in-class AI providers offering solutions designed to reduce radiology workload and improve patient care.
ImageBiopsy Case Study: AI Increases Physician Accuracy in Knee Osteoarthritis Assessment
Overview
Visual cues of early stages of osteoarthritis often elude radiographs which can lead to misdiagnosis, unnecessary examinations, and lack of treatment. Artificial intelligence (AI) has proven efficient in recognizing the complex visual patterns of osteoarthritis.
Intervention
IB Lab KOALA™(Knee Osteoarthritis Labeling Assistant), an AI system trained on a large dataset of radiographs has proven to statistically increase the accuracy rate of osteoarthritis diagnosis. KOALA analyzes anterior-posterior knee radiographs for the detection of features relevant to the diagnosis of osteoarthritis and provides readings for KL, JSN, sclerosis, and osteophyte OARSI grades.
In a study assessing diagnosis accuracy between unaided and AI-aided osteoarthritis diagnosis, KOALA reduced the false positive rate with little to no loss of true positive rate. Results show that the increase in accuracy of physicians is driven by an increase in specificity and sensitivity allowing physicians to better recognize the early stages of osteoarthritis.
Results
The ImageBiopsy study suggests the use of a computer-assisted detection system, such as KOALA, improves accuracy when assessing radiographic features relevant for the diagnosis of knee osteoarthritis.
These results argue for the use of this type of software as a way to improve the standard of care when diagnosing knee osteoarthritis.
Interested in deploying IB Lab KOALA™at your health facility?