TY - JOUR
T1 - Constructing a Clinical Radiographic Knee Osteoarthritis Database Using Artificial Intelligence Tools with Limited Human Labor
T2 - A Proof of Principle
AU - Lenskjold, Anders
AU - Brejnebøl, Mathias W
AU - Nybing, Janus U
AU - Rose, Martin H
AU - Gudbergsen, Henrik
AU - Troelsen, Anders
AU - Moller, Anne
AU - Raaschou, Henriette
AU - Boesen, Mikael
N1 - Copyright © 2023 The Authors. Published by Elsevier Ltd.. All rights reserved.
PY - 2024/3
Y1 - 2024/3
N2 - OBJECTIVE: To create a scalable and feasible retrospective consecutive knee osteoarthritis (OA) radiographic database with limited human labor using commercial and custom-built artificial intelligence (AI) tools.METHODS: We applied four AI tools, two commercially available and two custom-built tools, to analyze 6 years of clinical consecutive knee radiographs from patients aged 35-79 at the University of Copenhagen Hospital, Bispebjerg-Frederiksberg Hospital, Denmark. The tools provided Kellgren-Lawrence (KL) grades, joint space widths, patella osteophyte detection, radiographic view detection, knee joint implant detection, and radiographic marker detection.RESULTS: In total, 25,778 knee radiographs from 8575 patients were included in the database after excluding inapplicable radiographs, and 92.5% of the knees had a complete OA dataset. Using the four AI tools, we saved about 800 hours of radiologist reading time and only manually reviewed 16.0% of the images in the database.CONCLUSIONS: This study shows that clinical knee OA databases can be built using AI with limited human reading time for uniform grading and measurements. The concept is scalable temporally and across geographic regions and could help diversify further OA research by efficiently including radiographic knee OA data from different populations globally. We can prevent data dredging and overfitting OA theories on existing trite cohorts by including various gene pools and continuous expansion of new clinical cohorts. Furthermore, the suggested tools and applied approaches provide an ability to retest previous hypotheses and test new hypotheses on real-life clinical data with current disease prevalence and trends.
AB - OBJECTIVE: To create a scalable and feasible retrospective consecutive knee osteoarthritis (OA) radiographic database with limited human labor using commercial and custom-built artificial intelligence (AI) tools.METHODS: We applied four AI tools, two commercially available and two custom-built tools, to analyze 6 years of clinical consecutive knee radiographs from patients aged 35-79 at the University of Copenhagen Hospital, Bispebjerg-Frederiksberg Hospital, Denmark. The tools provided Kellgren-Lawrence (KL) grades, joint space widths, patella osteophyte detection, radiographic view detection, knee joint implant detection, and radiographic marker detection.RESULTS: In total, 25,778 knee radiographs from 8575 patients were included in the database after excluding inapplicable radiographs, and 92.5% of the knees had a complete OA dataset. Using the four AI tools, we saved about 800 hours of radiologist reading time and only manually reviewed 16.0% of the images in the database.CONCLUSIONS: This study shows that clinical knee OA databases can be built using AI with limited human reading time for uniform grading and measurements. The concept is scalable temporally and across geographic regions and could help diversify further OA research by efficiently including radiographic knee OA data from different populations globally. We can prevent data dredging and overfitting OA theories on existing trite cohorts by including various gene pools and continuous expansion of new clinical cohorts. Furthermore, the suggested tools and applied approaches provide an ability to retest previous hypotheses and test new hypotheses on real-life clinical data with current disease prevalence and trends.
KW - Artificial Intelligence
KW - Humans
KW - Knee
KW - Knee Joint/diagnostic imaging
KW - Osteoarthritis, Knee/diagnostic imaging
KW - Retrospective Studies
KW - Database creation
KW - Feasibility study
KW - Knee OA
KW - Data diversity
KW - Artificial intelligence
KW - Proof of concept
UR - http://www.scopus.com/inward/record.url?scp=85179821464&partnerID=8YFLogxK
U2 - 10.1016/j.joca.2023.11.014
DO - 10.1016/j.joca.2023.11.014
M3 - Journal article
C2 - 38043857
SN - 1063-4584
VL - 32
SP - 310
EP - 318
JO - Osteoarthritis and Cartilage
JF - Osteoarthritis and Cartilage
IS - 3
ER -