Predicting total knee arthroplasty from ultrasonography using machine learning

Aleksei Tiulpin; Simo Saarakkala; Alexander Mathiessen; Hilde Berner Hammer; Ove Furnes; Lars Nordsletten; Martin Englund; Karin Magnusson

doi:10.1016/j.ocarto.2022.100319

Predicting total knee arthroplasty from ultrasonography using machine learning

Osteoarthr Cartil Open. 2022 Nov 6;4(4):100319. doi: 10.1016/j.ocarto.2022.100319. eCollection 2022 Dec.

Authors

Aleksei Tiulpin¹, Simo Saarakkala^{1

2}, Alexander Mathiessen^{3

4}, Hilde Berner Hammer^{3

4}, Ove Furnes^{5

6}, Lars Nordsletten^{4

7}, Martin Englund⁸, Karin Magnusson^{3

8

9}

Affiliations

¹ Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland.
² Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland.
³ Center for treatment of Rheumatic and Musculoskeletal Diseases (REMEDY), Diakonhjemmet Hospital, Oslo, Norway.
⁴ Faculty of Medicine, University of Oslo, Oslo, Norway.
⁵ The Norwegian Arthroplasty Register, Department of Orthopaedic Surgery, Haukeland University Hospital, Bergen, Norway.
⁶ Department of Clinical Medicine, University of Bergen, Bergen, Norway.
⁷ Division of Orthopaedic Surgery, Oslo University Hospital, Oslo, Norway.
⁸ Clinical Epidemiology Unit, Orthopaedics, Department of Clinical Sciences Lund, Faculty of Medicine, Lund University, Lund, Sweden.
⁹ Norwegian Institute of Public Health, Cluster for Health Services Research, Oslo, Norway.

Abstract

Objective: To investigate the value of ultrasonographic data in predicting total knee replacement (TKR).

Design: Data from the Musculoskeletal Pain in Ullensaker study (MUST) was linked to the Norwegian Arthroplasty Register to form a 5-7 year prospective cohort study of 630 persons (69% women, mean (SD) age 64 (8.7) years). We examined the predictive power of ultrasound (US) features, i.e. osteophytes, meniscal extrusion, synovitis in the suprapatellar recess, femoral cartilage thickness, and quality for future knee osteoarthritis (OA) surgery. We investigated 4 main settings for multivariate predictive modeling: 1) clinical predictors (age, sex, body mass index, knee injury, familial OA and workload), 2) radiographic data (assessed by the Kellgren Lawrence grade, KL) with clinical predictors, 3) US features and clinical predictors. Finally, we also considered an ensemble of models 2) and 3) and used it as our fifth model. All models were compared using the Average Precision (AP) and the Area Under Receiver Operating Characteristic Curve (AUC) metrics.

Results: Clinical predictors yielded AP of 0.11 (95% confidence interval [CI] 0.05-0.23) and AUC of 0.69 (0.58-0.79). Clinical predictors with KL grade yielded AP of 0.20 (0.12-0.33) and AUC of 0.81 (0.67-0.90). The clinical variables with ultrasound yielded AP of 0.17 (0.08-0.30) and AUC of 0.79 (0.69-0.86).

Conclusion: Ultrasonographic examination of the knee may provide added value to basic clinical and demographic descriptors when predicting TKR. While it does not achieve the same predictive performance as radiography, it can provide additional value to the radiographic examination.

Keywords: Machine learning; Multivariate predictive modeling; Total knee replacement; Ultrasonography.