Knie-artrose

Fietsen verstandig?

Feit

Bij hardlopen wordt de knie belast met 6x uw lichaamsgewicht bij elke stap

Máxima Medisch Centrum

Value-Based Health Care

ESSKA Accredited Teacher

Orthopedie Groot Eindhoven

Goede uitleg is essentieel voor juiste keuze behandeling

Meniscus-scheur

Voorste kruisbandreconstructie

Achterste kruisbandletsel

Zorg op maat

YouTube kanaal dr RPA Janssen

Internationaal wetenschappelijk onderzoek

Kruisbandoperaties knie

RPA Janssen MD PhD

Kruisbandoperaties

Waardegedreven zorg

Last van knie-artrose?

Spreekuur / Policlinique / Outpatient clinic

Nederlandse Vereniging voor Arthroscopie

Máxima Medisch Centrum

Kruisbandoperaties bij kinderen

Veel pijn bij ernstige knie-artrose?

Samen met uw arts gekozen voor een knie-operatie?

Eenzijdige knie-artrose knie en actief leven?

Máxima Medisch Centrum Eindhoven-Veldhoven

Kwaliteit van leven

Samen kiezen voor de beste behandeling

Sporten met plezier

Oplossingen voor de lange termijn

Associate Professor Knee Reconstruction

Fact

Kneecap pain is a regular occurrence in fitness knee rehabilitation

Knee osteoarthritis

Cycling wise?

Fact

When running, the knee is loaded with 6x your body weight with each step

A machine learning approach reveals features related to clinicians’ diagnosis of clinically relevant knee osteoarthritis

Qiuke Wang, Jos Runhaar, Margreet Kloppenburg, Maarten Boers, Johannes W J Bijlsma, Jaume Bacardit, Sita M A Bierma-Zeinstra, Rob P.A. Janssen as member of the CREDO experts group
Rheumatology (Oxford). 2022 Dec 19;keac707. doi: 10.1093/rheumatology/keac707. Online ahead of print.

Abstract

Objectives To identify highly-ranked features related to clinicians’ diagnosis of clinically relevant knee osteoarthritis (OA). Methods General practitioners (GPs) and secondary care physicians (SPs) were recruited to evaluate 5-10 years follow-up clinical and radiographic data of knees from the CHECK cohort for the presence of clinically relevant OA. GPs and SPs were gathered in pairs; each pair consisted of 1 GP and 1 SP, and the paired clinicians independently evaluated the same subset of knees. A diagnosis was made for each knee by the GP and SP before and after viewing radiographic data. Nested 5-fold cross-validation enhanced random forest models were built to identify the top 10 features related to the diagnosis. Results 17 clinician pairs evaluated 1106 knees with 139 clinical and 36 radiographic features. GPs diagnosed clinically relevant OA in 42% and 43% knees, before and after viewing radiographic data, respectively. SPs diagnosed in 43% and 51% knees, respectively. Models containing top 10 features had good performance for explaining clinicians’ diagnosis with area under the curve ranging from 0.76-0.83. Before viewing radiographic data, quantitative symptomatic features (i.e. WOMAC scores) were the most important ones related to the diagnosis of both GPs and SPs; after viewing radiographic data, radiographic features appeared in the top lists for both, but seemed to be more important for SPs than GPs. Conclusions Random forest models presented good performance in explaining clinicians’ diagnosis, which helped to reveal typical features of patients recognized as clinically relevant knee OA by clinicians from two different care settings.

Keywords: CHECK cohort; Knee osteoarthritis; clinician’s diagnosis; machine learning.