Objectives: In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is... Show moreObjectives: In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is clinically relevant for surgeon and patient to anticipate unplanned secondary procedures, other than operations that can be readily expected such as reconstructive procedures for soft tissue defects. Therefore, the objective of this study was to develop a machine learning (ML) prediction model using the SPRINT data that can give individual patients and their care team an estimate of their particular probability of an unplanned second surgery. Methods: Patients from the SPRINT trial with unilateral TSFs were randomly divided into a training set (80%) and test set (20%). Five ML algorithms were trained in recognizing patterns associated with subsequent surgery in the training set based on a subset of variables identified by random forest algorithms. Performance of each ML algorithm was evaluated and compared based on (1) area under the ROC curve, (2) calibration slope and intercept, and (3) the Brier score. Results: Total data set comprised 1198 patients, of whom 214 patients (18%) underwent subsequent surgery. Seven variables were used to train ML algorithms: (1) Gustilo-Anderson classification, (2) Tscherne classification, (3) fracture location, (4) fracture gap, (5) polytrauma, (6) injury mechanism, and (7) OTA/AO classification. The best-performing ML algorithm had an area under the ROC curve, calibration slope, calibration intercept, and the Brier score of 0.766, 0.954, -0.002, and 0.120 in the training set and 0.773, 0.922, 0, and 0.119 in the test set, respectively. Conclusions: An ML algorithm was developed to predict the probability of subsequent surgery after IMN for TSFs. This ML algorithm may assist surgeons to inform patients about the probability of subsequent surgery and might help to identify patients who need a different perioperative plan or a more intensive approach. Show less
Kviatkovsky, M.J.; Ramiro, S.; Landewe, R.; Dougados, M.; Tubach, F.; Bellamy, N.; ... ; Heijde, D. van der 2016
Objective. To develop an algorithm for identification of undifferentiated peripheral inflammatory arthritis (UPIA). Methods. An algorithm for identification of UPIA was developed by consensus... Show moreObjective. To develop an algorithm for identification of undifferentiated peripheral inflammatory arthritis (UPIA). Methods. An algorithm for identification of UPIA was developed by consensus during a roundtable meeting with an expert panel. It was informed by systematic reviews of the literature used to generate 10 recommendations for the investigation and followup of UPIA through the 3e initiative. The final recommendations from the 3e UPIA Initiative were made available to the panel to guide development of the algorithm. The algorithm drew on the clinical experience of the consensus panel and evidence from the literature where available. Results. In patients presenting with joint swelling a thorough evaluation is required prior to diagnosing UPIA. After excluding trauma, the differential diagnosis should be formulated based on history and physical examination. A minimum set of investigations is suggested for all patients, with additional ones dependent on the most probable differential diagnoses. The diagnosis of UPIA can be made if, following these evaluations, a more specific diagnosis is not reached. Once a diagnosis of UPIA is established, patients should be closely followed as they may progress to a specific diagnosis, remit, or persist as UPIA, and additional investigations may be required over time. Conclusion. Our algorithm presents a diagnostic approach to identifying UPIA in patients presenting with joint swelling, incorporating the dynamic nature of the condition with the potential to evolve over time. (J Rheumatol 2011;38 Suppl 87:54-58; doi:10.3899/jrheum.101076) Show less
Objective. To perform a systematic literature review of the diagnostic and prognostic value of magnetic resonance imaging (MRI) and ultrasound (US) in patients with undifferentiated peripheral... Show moreObjective. To perform a systematic literature review of the diagnostic and prognostic value of magnetic resonance imaging (MRI) and ultrasound (US) in patients with undifferentiated peripheral inflammatory arthritis (UPIA), and to assess if MRI and US should be done at baseline and repeated, and if so, at what interval. Methods. Medline, Embase, the Cochrane Library, and abstracts presented at the 2007 and 2008 meetings of the American College of Rheumatology and European League Against Rheumatism meetings were searched for diagnostic and prognostic studies of any duration examining the ability of MRI/US to predict outcome of patients with UPIA. Sensitivity, specificity, predictive values, and positive/negative likelihood ratios (LR+/LR-) were calculated. When available, odds ratios were extracted. Quality was appraised using validated scales. Results. Regarding MRI, 11 out of 2595 screened references were included: 2 described pure undifferentiated arthritis (UA) populations and 9, mixed populations. Bone edema (LR+4.5) and combination of a distinct MRI synovitis and erosion pattern (LR+4.8) increased probability of developing rheumatoid arthritis (RA). Absence of MRI synovitis (LR-0.2) and absence of a distinct synovitis pattern (LR-0) decreased probability of developing RA. Regarding US, 2 out of 2111 references were included, both mixed populations; no data could be extrapolated for UPIA. Conclusion. MRI bone edema and combined synovitis and erosion pattern seem useful in predicting development of RA from UPIA. The value of US in UPIA remains to be determined. The absence of MRI synovitis seems useful in excluding development of RA. No data were found about the value of repeating MRI/US. Studies evaluating MRI/US in UPIA are scarce, but current knowledge strongly encourages further testing in UA. (J Rheumatol 2010;38 Suppl 87:31-37; doi:10.3899/jrheum.101072) Show less
Koevoets, R.; Machado, P.; Bombardier, C.; Heijde, D.M. van der 2011
Objective. To perform a systematic literature review on the diagnostic and predictive value of conventional radiographs (CR) in patients with undifferentiated arthritis (UA). Methods. We performed... Show moreObjective. To perform a systematic literature review on the diagnostic and predictive value of conventional radiographs (CR) in patients with undifferentiated arthritis (UA). Methods. We performed an extended search using Medline. Embase, the Cochrane Library, and abstracts from the 2007 and 2008 meetings of the American College of Rheumatology and the European League Against Rheumatism. Articles were included based on predefined inclusion criteria, and quality was assessed by using validated quality scales. Results. In total, 25 articles were included from 6003 retrieved references. Five articles described a pure UA population, 20 articles described a mixed population [mostly rheumatoid arthritis (RA) and UA]. In studies on UA, erosions on CR were strong predictors of RA diagnosis [positive likelihood ratio (LR+) 3.5-10.9; odds ratio 7.6 and 8.7). In a more heterogeneous mixed population, 20 studies reporting on 11 cohorts found a relationship between CR findings and subsequent diagnosis of RA. LR+ for erosions and/or bony decalcifications ranged from 1.8 to 9.7, and there was greater prevalence of erosions and higher Sharp-van der Heijde score in the RA group at followup. With regard to prognosis in both UA and mixed populations, an association was found between number of abnormalities on CR and poor outcome. Conclusion. Several studies, in pure UA and mixed populations, clearly demonstrate that CR are helpful in predicting future diagnosis of RA or worse prognosis. However, absence of abnormalities on CR does not sufficiently exclude RA or other unfavorable outcome. (J Rheumatol 2010;38 Suppl 87:26-30; doi:10.3899/jrheum.101071) Show less
Machado, P.; Castrejon, I.; Katchamart, W.; Koevoets, R.; Kuriya, B.; Schoels, M.; ... ; Bombardier, C. 2011
Objective To develop evidence-based recommendations on how to investigate and follow-up undifferentiated peripheral inflammatory arthritis (UPIA). Methods 697 rheumatologists from 17 countries... Show moreObjective To develop evidence-based recommendations on how to investigate and follow-up undifferentiated peripheral inflammatory arthritis (UPIA). Methods 697 rheumatologists from 17 countries participated in the 3E (Evidence, Expertise, Exchange) Initiative of 2008-9 consisting of three separate rounds of discussions and modified Delphi votes. In the first round 10 clinical questions were selected. A bibliographic team systematically searched Medline, Embase, the Cochrane Library and ACR/EULAR 2007-2008 meeting abstracts. Relevant articles were reviewed for quality assessment, data extraction and synthesis. In the second round each country elaborated a set of national recommendations. Finally, multinational recommendations were formulated and agreement among the participants and the potential impact on their clinical practice was assessed. Results A total of 39 756 references were identified, of which 250 were systematically reviewed. Ten multinational key recommendations about the investigation and follow-up of UPIA were formulated. One recommendation addressed differential diagnosis and investigations prior to establishing the operational diagnosis of UPIA, seven recommendations related to the diagnostic and prognostic value of clinical and laboratory assessments in established UPIA (history and physical examination, acute phase reactants, autoantibodies, radiographs, MRI and ultrasound, genetic markers and synovial biopsy), one recommendation highlighted predictors of persistence (chronicity) and the final recommendation addressed monitoring of clinical disease activity in UPIA. Conclusions Ten recommendations on how to investigate and follow-up UPIA in the clinical setting were developed. They are evidence-based and supported by a large panel of rheumatologists, thus enhancing their validity and practical use. Show less
