Background and purpose — Machine learning (ML) techniques are a form of artificial intelligence able to analyze big data. Analyzing the outcome of (digital) questionnaires, ML might recognize... Show moreBackground and purpose — Machine learning (ML) techniques are a form of artificial intelligence able to analyze big data. Analyzing the outcome of (digital) questionnaires, ML might recognize different patterns in answers that might relate to different types of pathology. With this study, we investigated the proof-of-principle of ML-based diagnosis in patients with hip complaints using a digital questionnaire and the Kellgren and Lawrence (KL) osteoarthritis score.Patients and methods — 548 patients (> 55 years old) scheduled for consultation of hip complaints were asked to participate in this study and fill in an online questionnaire. Our questionnaire consists of 27 questions related to general history-taking and validated patient-related outcome measures (Oxford Hip Score and a Numeric Rating Scale for pain). 336 fully completed questionnaires were related to their classified diagnosis (either hip osteoarthritis, bursitis or tendinitis, or other pathology). Different AI techniques were used to relate questionnaire outcome and hip diagnoses. Resulting area under the curve (AUC) and classification accuracy (CA) are reported to identify the best scoring AI model. The accuracy of different ML models was compared using questionnaire outcome with and without radiologic KL scores for degree of osteoarthritis.Results — The most accurate ML model for diagnosis of patients with hip complaints was the Random Forest model (AUC 82%, 95% CI 0.78–0.86; CA 69%, CI 0.64–0.74) and most accurate analysis with addition of KL scores was with a Support Vector Machine model (AUC 89%, CI 0.86–0.92; CA 83%, CI 0.79–0.87).Interpretation — Analysis of self-reported online questionnaires related to hip complaints can differentiate between basic hip pathologies. The addition of radiological scores for osteoarthritis further improves these outcomes. Show less
Siebelt, M.; Vos-Jakobs, S. de; Koenrades, N.; Nieuwenhoven, C.A.V. van; Oostenbrink, R.; Bramer, W.M.; ... ; Kempink, D.R.J. 2020
Background: A congenital forearm pseudarthrosis is a rare condition and is strongly associated with neurofibromatosis type 1. Several surgical techniques are described in the literature, but the... Show moreBackground: A congenital forearm pseudarthrosis is a rare condition and is strongly associated with neurofibromatosis type 1. Several surgical techniques are described in the literature, but the most optimal treatment strategy remains unclear. This systematic review aims to develop a treatment algorithm that may aid in clinical decision making. Methods: The PROSPERO registration number for this study was CRD42018099602 and adheres to the PRISMA guidelines for systematic reviews. Embase, MEDLINE, Cochrane Central, Web of Science, and Google Scholar databases were searched for published studies reporting on congenital forearm pseudarthrosis not related to other underlying pathologies like bacterial infection or fibrous dysplasia. Results were not restricted by date or study type, only English literature was allowed. Studies were assessed for quality using the critical appraisal checklist for case reports from the Joanna Briggs Institute. Patient characteristics, underlying disease, type of surgery, union rate, and functional outcome were extracted from included studies. Results: Of 829 studies identified, 47 were included in this review (17 case series and 30 case reports, a total of 84 cases). A one-bone forearm procedure showed highest union rates (92%), however, it results in loss of forearm rotation. Free vascularized fibula grafting showed high union rates (87%) and was related to good functional outcome of elbow flexion and forearm rotations. Other procedures showed disappointing outcomes. Conclusions: Congenital forearm pseudarthrosis is best treated with a free vascularized fibula grafting, a one-bone forearm procedure should be used as a salvage procedure. Evidence extracted from the case reports was sufficient to generate a treatment algorithm to be used in clinical pediatric practice. Show less
Aleksinskaya, M.A.; Monge, M.; Siebelt, M.; Slot, E.M.; Koekkoek, K.M.; Bruin, R.G. de; ... ; Pel, M. van 2018
OBJECTIVE In the past years, the canonical Wnt/β-catenin signaling pathway has emerged as a critical regulator of cartilage development and homeostasis. In this pathway, glycogen synthase kinase-3β... Show moreOBJECTIVE In the past years, the canonical Wnt/β-catenin signaling pathway has emerged as a critical regulator of cartilage development and homeostasis. In this pathway, glycogen synthase kinase-3β (GSK3β) down-regulates transduction of the canonical Wnt signal by promoting degradation of β-catenin. In this study we wanted to further investigate the role of Gsk3β in cartilage maintenance. DESIGN Therefore, we have treated chondrocytes ex vivo and in vivo with GIN, a selective GSK3β inhibitor. RESULTS In E17.5 fetal mouse metatarsals, GIN treatment resulted in loss of expression of cartilage markers and decreased chondrocyte proliferation from day 1 onward. Late (3 days) effects of GIN included cartilage matrix degradation and increased apoptosis. Prolonged (7 days) GIN treatment resulted in resorption of the metatarsal. These changes were confirmed by microarray analysis showing a decrease in expression of typical chondrocyte markers and induction of expression of proteinases involved in cartilage matrix degradation. An intra-articular injection of GIN in rat knee joints induced nuclear accumulation of β-catenin in chondrocytes 72 h later. Three intra-articular GIN injections with a 2 days interval were associated with surface fibrillation, a decrease in glycosaminoglycan expression and chondrocyte hypocellularity 6 weeks later. CONCLUSIONS These results suggest that, by down-regulating β-catenin, Gsk3β preserves the chondrocytic phenotype, and is involved in maintenance of the cartilage extracellular matrix. Short term β-catenin up-regulation in cartilage secondary to Gsk3β inhibition may be sufficient to induce osteoarthritis-like features in vivo. Show less
Miclea, R.L.; Siebelt, M.; Finos, L.; Goeman, J.J.; Lowik, C.W.G.M.; Oostdijk, W.; ... ; Karperien, M. 2011
