TY - JOUR

T1 - External validation of an artificial intelligence tool for radiographic knee osteoarthritis severity classification

AU - Brejnebøl, Mathias Willadsen

AU - Hansen, Philip

AU - Nybing, Janus Uhd

AU - Bachmann, Rikke

AU - Ratjen, Ulrik

AU - Hansen, Ida Vibeke

AU - Lenskjold, Anders

AU - Axelsen, Martin

AU - Lundemann, Michael

AU - Boesen, Mikael

N1 - Publisher Copyright: © 2022 The Authors

PY - 2022

Y1 - 2022

N2 - Purpose: To externally validate an artificial intelligence (AI) tool for radiographic knee osteoarthritis severity classification on a clinical dataset. Method: This retrospective, consecutive patient sample, external validation study used weight-bearing, non-fixed-flexion posterior-anterior knee radiographs from a clinical production PACS. The index test was ordinal Kellgren-Lawrence grading by an AI tool, two musculoskeletal radiology consultants, two reporting technologists, and two resident radiologists. Grading was repeated by all readers after at least four weeks. Reference test was the consensus of the two consultants. The primary outcome was quadratic weighted kappa. Secondary outcomes were ordinal weighted accuracy, multiclass accuracy and F1-score. Results: 50 consecutive patients between September 24, 2019 and October 22, 2019 were retrospectively included (3 excluded) totaling 99 knees (1 excluded). Quadratic weighted kappa for the AI tool and the consultant consensus was 0.88 CI95% (0.82–0.92). Agreement between the consultants was 0.89 CI95% (0.85–0.93). Intra-rater agreements for the consultants were 0.96 CI95% (0.94–0.98) and 0.94 CI95% (0.91–0.96) respectively. For the AI tool it was 1 CI95% (1–1). For the AI tool, ordinal weighted accuracy was 97.8% CI95% (96.9–98.6 %). Average multiclass accuracy and F1-score were 84% (83/99) CI95% (77–91%) and 0.67 CI95% (0.51–0.81). Conclusions: The AI tool achieved the same good-to-excellent agreement with the radiology consultant consensus for radiographic knee osteoarthritis severity classification as the consultants did with each other.

AB - Purpose: To externally validate an artificial intelligence (AI) tool for radiographic knee osteoarthritis severity classification on a clinical dataset. Method: This retrospective, consecutive patient sample, external validation study used weight-bearing, non-fixed-flexion posterior-anterior knee radiographs from a clinical production PACS. The index test was ordinal Kellgren-Lawrence grading by an AI tool, two musculoskeletal radiology consultants, two reporting technologists, and two resident radiologists. Grading was repeated by all readers after at least four weeks. Reference test was the consensus of the two consultants. The primary outcome was quadratic weighted kappa. Secondary outcomes were ordinal weighted accuracy, multiclass accuracy and F1-score. Results: 50 consecutive patients between September 24, 2019 and October 22, 2019 were retrospectively included (3 excluded) totaling 99 knees (1 excluded). Quadratic weighted kappa for the AI tool and the consultant consensus was 0.88 CI95% (0.82–0.92). Agreement between the consultants was 0.89 CI95% (0.85–0.93). Intra-rater agreements for the consultants were 0.96 CI95% (0.94–0.98) and 0.94 CI95% (0.91–0.96) respectively. For the AI tool it was 1 CI95% (1–1). For the AI tool, ordinal weighted accuracy was 97.8% CI95% (96.9–98.6 %). Average multiclass accuracy and F1-score were 84% (83/99) CI95% (77–91%) and 0.67 CI95% (0.51–0.81). Conclusions: The AI tool achieved the same good-to-excellent agreement with the radiology consultant consensus for radiographic knee osteoarthritis severity classification as the consultants did with each other.

KW - Artificial intelligence

KW - Conventional radiography

KW - External validation

KW - Inter-rater agreement

KW - Knee osteoarthritis

U2 - 10.1016/j.ejrad.2022.110249

DO - 10.1016/j.ejrad.2022.110249

M3 - Journal article

C2 - 35338955

AN - SCOPUS:85126866648

VL - 150

JO - European Journal of Radiology

JF - European Journal of Radiology

SN - 0720-048X

M1 - 110249

ER -