Computer-aided diagnosis based on hand thermal, RGB images, and grip force using artificial intelligence as screening tool for rheumatoid arthritis in women.

Rheumatoid arthritis (RA) is an autoimmune disorder that typically affects people between 23 and 60 years old causing chronic synovial inflammation, symmetrical polyarthritis, destruction of large and small joints, and chronic disability. Clinical diagnosis of RA is stablished by current ACR-EULAR criteria, and it is crucial for starting conventional therapy in order to minimize damage progression. The 2010 ACR-EULAR criteria include the presence of swollen joints, elevated levels of rheumatoid factor or anti-citrullinated protein antibodies (ACPA), elevated acute phase reactant, and duration of symptoms. In this paper, a computer-aided system for helping in the RA diagnosis, based on quantitative and easy-to-acquire variables, is presented. The participants in this study were all female, grouped into two classes: class I, patients diagnosed with RA (n = 100), and class II corresponding to controls without RA (n = 100). The novel approach is constituted by the acquisition of thermal and RGB images, recording their hand grip strength or gripping force. The weight, height, and age were also obtained from all participants. The color layout descriptors (CLD) were obtained from each image for having a compact representation. After, a wrapper forward selection method in a range of classification algorithms included in WEKA was performed. In the feature selection process, variables such as hand images, grip force, and age were found relevant, whereas weight and height did not provide important information to the classification. Our system obtains an AUC ROC curve greater than 0.94 for both thermal and RGB images using the RandomForest classifier. Thirty-eight subjects were considered for an external test in order to evaluate and validate the model implementation. In this test, an accuracy of 94.7% was obtained using RGB images; the confusion matrix revealed our system provides a correct diagnosis for all participants and failed in only two of them (5.3%). Graphical abstract.

Myositis-Specific Antibodies and Myositis-Associated Antibodies in Patients With Idiopathic Inflammatory Myopathies From the PANLAR Myositis Study Group.

BACKGROUND: Dermatomyositis (DM) and polymyositis (PM) are forms of idiopathic inflammatory myopathies (IIMs), which are associated with the production of autoantibodies that are useful in the diagnosis and prognosis of the disease. OBJECTIVE: The aim of this study was to determine the frequency of antinuclear autoantibodies (ANAs), myositis-specific autoantibodies (MSAs), and myositis-associated autoantibodies (MAAs) in 6 Latin American countries. METHODS: Two hundred ten patients with IIM were included in this cross-sectional study from 2014 to 2017: 112 from Mexico, 46 from Colombia, 20 from Peru, 16 from the Dominican Republic, 10 from Argentina, and 6 from Guatemala. Antinuclear autoantibodies were detected by indirect immunofluorescence on HEp-2 cells. MSAs and MAAs were tested by a line immunoassay method. Mann-Whitney U and χ2 tests were used for statistical analysis. RESULTS: Of the 210 IIM patients, 139 (66.2%) had DM, 59 (28%) PM, and 12 (5.7%) juvenile DM. The mean age was 43.5 (6-79 years); 158 (75.2%) were female, and 52 (24.8%) were male. The overall frequency of ANA was 60%. The most frequent patterns were fine speckled (AC-4) (78.3%) and cytoplasmic (AC-19) (6.45%). The most frequent MSA were anti-Mi-2 (38.5%) and anti-Jo-1 (11.9%). Anti-Mi-2 was more frequent in patients from Colombia (40.1%). The MAA more frequent were anti-Ro-52/TRIM21 (17.6%) and anti-PM-Scl75 (7.5%). CONCLUSIONS: This is the first study of ANA, MSA, and MAA in patients from 6 countries from the Panamerican League against Rheumatism myositis study group. We observed a general prevalence of 60% of ANA. In relation to MSA and MAA, anti-Mi-2 was the more frequent (38.5%).

Association of extrapituitary prolactin promoter polymorphism with disease susceptibility and anti-RNP antibodies in Mexican patients with systemic lupus erythematosus.

Introduction: Prolactin (PRL) is a 23-kDa protein that can be synthesized and secreted by pituitary and extrapituitary tissues such as immune cells due to its expression being regulated by two independent promoter regions. The promoter which is responsible for extrapituitary expression contains the single nucleotide polymorphism (SNP) -1149 G/T previously associated with autoimmune diseases in various populations. This study evaluates the relationship of PRL -1149 G/T polymorphism with PRL serum levels and clinical characteristics in systemic lupus erythematosus (SLE) patients from western Mexico. Material and methods: One hundred and sixty-three SLE patients classified according to the 1982 American College of Rheumatology (ACR) SLE classification criteria and 326 unrelated control subjects (CS), both from western Mexico, were included. The PRL -1149 G/T polymorphism was genotyped using the polymerase chain reaction restriction fragment length polymorphism technique, and both PRL serum levels and autoantibodies were measured by enzyme-linked immunosorbent assay (ELISA). Results: We found an association between the PRL -1149 TT genotype and SLE according to the recessive genetic model (OR = 2.26, 95% CI: 1.01-5.08, p = 0.04). The TT genotype was associated with anti-RNP antibodies (p = 0.04) and with higher scores of the Mex-SLEDAI (p = 0.02). Moreover, SLE patients showed elevated PRL serum levels (12.4 ng/ml; p < 0.01), and this condition was associated with renal activity and the presence of anti-RNP antibodies. Conclusions: PRL -1149 TT genotype is associated with susceptibility to SLE in a Mexican-Mestizo population, and high PRL serum levels are associated with anti-RNP antibodies and renal activity.

Self-assessed efficacy of a clinical musculoskeletal anatomy workshop: a preliminary survey / Eficacia autoevaluada de un taller de anatomía clínica musculoesquelética: una encuesta preliminar

Objective. To survey the efficacy of a practical workshop on clinical musculoskeletal anatomy held in five American countries. Methods. A self-assessment competence questionnaire sent to participants 1–3 months after the workshop. Results were compared to the results of a practical, instructor-assessed, pre-workshop test. Results. The response rate of participants was 76.4%. The overall, self-assessed competence score for anatomical items that had been included in the pre-test was 76.9 (scale 0–100) as compared to an overall score of 48.1 in the practical, pre-workshop test (p < 0.001). For items that were addressed in the workshop, but not included in the pre-test, self-assessed competence was rated at 62.9. Differences in anatomical knowledge between individuals from different countries and professional groups noted in the practical pre-test were no longer present in the post-test self-assessment. Conclusions. From this preliminary data and supporting evidence from the literature we believe that our anatomy workshop provides an effective didactic tool for increasing competence in musculoskeletal anatomy (AU)

Objetivo. Estudiar la eficacia de un taller práctico de anatomía musculoesquelética realizado en 5 países de América. Métodos. Un cuestionario de autoevaluación de competencias se envió por correo electrónico a los participantes en un taller práctico de anatomía clínica musculoesquelética 1–3 meses después de concluido el taller. Los resultados de este cuestionario se compararon con los resultados de un examen práctico tomado por un instructor, previo al taller práctico. Resultados. La tasa de respuesta de los participantes fue del 76,4%. La puntuación de la competencia autoevaluada global de los temas anatómicos incluidos en el examen práctico previo fue 76,9 (escala de 0 a 100) en comparación con una puntuación total de 48,1 obtenida en la evaluación práctica previa al taller (p < 0,001). Para los temas que se abordaron en el taller, pero no incluidos en la competencia previa a la autoevaluación, la calificación fue de 62,9. Las diferencias en el conocimiento anatómico entre personas de diferentes países y grupos de profesionales que se observaron en el examen práctico previo ya no se vieron en el cuestionario de autoevaluación. Conclusiones. A partir de estos datos preliminares y apoyados en la literatura creemos que nuestro taller de anatomía clínica práctica proporciona una herramienta didáctica eficaz para aumentar la competencia en anatomía musculo-esquelética (AU)

Self-assessed efficacy of a clinical musculoskeletal anatomy workshop: A preliminary survey.

OBJECTIVE: To survey the efficacy of a practical workshop on clinical musculoskeletal anatomy held in five American countries. METHODS: A self-assessment competence questionnaire sent to participants 1-3 months after the workshop. Results were compared to the results of a practical, instructor-assessed, pre-workshop test. RESULTS: The response rate of participants was 76.4%. The overall, self-assessed competence score for anatomical items that had been included in the pre-test was 76.9 (scale 0-100) as compared to an overall score of 48.1 in the practical, pre-workshop test (p<0.001). For items that were addressed in the workshop, but not included in the pre-test, self-assessed competence was rated at 62.9. Differences in anatomical knowledge between individuals from different countries and professional groups noted in the practical pre-test were no longer present in the post-test self-assessment. CONCLUSIONS: From this preliminary data and supporting evidence from the literature we believe that our anatomy workshop provides an effective didactic tool for increasing competence in musculoskeletal anatomy.

Preworkshop knowledge of musculoskeletal anatomy of rheumatology fellows and rheumatologists of seven North, Central, and South American countries.

OBJECTIVE: To report the baseline knowledge of clinical anatomy of rheumatology fellows and rheumatologists from Argentina, Chile, Ecuador, El Salvador, Mexico, the US, and Uruguay. METHODS: The invitation to attend a workshop in clinical anatomy was an open call by national rheumatology societies in 4 countries or by invitation from teaching program directors in 3 countries. Prior to the workshop, a practical test of anatomic structures commonly involved in rheumatic diseases was administered. The test consisted of the demonstration of these structures or their function in the participant's or instructor's body. At one site, a postworkshop practical test was administered immediately after the workshop. RESULTS: There were 170 participants (84 rheumatology fellows, 61 rheumatologists, and 25 nonrheumatologists). The overall mean ± SD number of correct answers was 46.6% ± 19.9% and ranged from 32.5-67.0% by country. Rheumatology fellows scored significantly higher than nonrheumatologists. Questions related to anatomy of the hand scored the lowest of the regions surveyed. CONCLUSION: Rheumatology fellows and rheumatologists showed a deficit in knowledge of musculoskeletal anatomy that is of central importance in rheumatologic assessment and diagnosis. This gap may hinder accurate and cost-effective rheumatologic diagnosis, particularly in the area of regional pain syndromes. Presently, widespread use of musculoskeletal ultrasound (MSUS) by rheumatologists may be premature, since a key component of expert-level MSUS is the integration of an accurate knowledge of anatomy with the views obtained with the ultrasound probe.