Chronic Pain Diagnosis Using Machine Learning, Questionnaires, and QST: A Sensitivity Experiment.

In the last decade, machine learning has been widely used in different fields, especially because of its capacity to work with complex data. With the support of machine learning techniques, different studies have been using data-driven approaches to better understand some syndromes like mild cognitive impairment, Alzheimer's disease, schizophrenia, and chronic pain. Chronic pain is a complex disease that can recurrently be misdiagnosed due to its comorbidities with other syndromes with which it shares symptoms. Within that context, several studies have been suggesting different machine learning algorithms to classify or predict chronic pain conditions. Those algorithms were fed with a diversity of data types, from self-report data based on questionnaires to the most advanced brain imaging techniques. In this study, we assessed the sensitivity of different algorithms and datasets classifying chronic pain syndromes. Together with this assessment, we highlighted important methodological steps that should be taken into account when an experiment using machine learning is conducted. The best results were obtained by ensemble-based algorithms and the dataset containing the greatest diversity of information, resulting in area under the receiver operating curve (AUC) values of around 0.85. In addition, the performance of the algorithms is strongly related to the hyper-parameters. Thus, a good strategy for hyper-parameter optimization should be used to extract the most from the algorithm. These findings support the notion that machine learning can be a powerful tool to better understand chronic pain conditions.

Using Deep Learning and Resting-State fMRI to Classify Chronic Pain Conditions.

Chronic pain is known as a complex disease due to its comorbidities with other symptoms and the lack of effective treatments. As a consequence, chronic pain seems to be under-diagnosed in more than 75% of patients. At the same time, the advance in brain imaging, the popularization of machine learning techniques and the development of new diagnostic tools based on these technologies have shown that these tools could be an option in supporting decision-making of healthcare professionals. In this study, we computed functional brain connectivity using resting-state fMRI data from one hundred and fifty participants to assess the performance of different machine learning models, including deep learning (DL) neural networks in classifying chronic pain patients and pain-free controls. The best result was obtained by training a convolutional neural network fed with data preprocessed using the MSDL probabilistic atlas and using the dynamic time warping (DTW) as connectivity measure. DL models had a better performance compared to other less costly models such as support vector machine (SVM) and RFC, with balanced accuracy ranged from 69 to 86%, while the area under the curve (ROC) ranged from 0.84 to 0.93. Also, DTW overperformed correlation as connectivity measure. These findings support the notion that resting-state fMRI data could be used as a potential biomarker of chronic pain conditions.

Icterícia colestática por lesões de natureza maligna: ensaio iconográfico / Cholestatic jaundice by malignant lesions: pictorial essay

A icterícia colestática de natureza tumoral maligna tem como causas mais frequentes o tumor da cabeça do pâncreas, o tumor da papila, o colangiocarcinoma e os quadros obstrutivos biliares determinadospor lesão secundária hepática parenquimatosa ou linfonodal. Os pacientes geralmente se apresentam com perda ponderal, dor abdominal, icterícia progressiva e aumento de bilirrubina direta, sendo fundamental a avaliação pelos métodos de imagem para o adequado diagnóstico, estadiamento e planejamento terapêutico. O presente ensaio ilustra, com correlação anatomocirúrgica, os aspectos de imagem da ultrassonografia, tomografia computadorizada e, em situaçõesespecíficas, colangiorressonância, das principais neoplasias malignas que cursam com icterícia colestática.

Malignant obstructive jaundice is most commonly caused by cancerof pancreatic head, papilla tumor, cholangiocarcinoma and biliary obstruction induced by secondary lesions of the liver or lymph nodes. Patients usually present with weight loss, abdominal pain, jaundice and progressive increase of direct bilirubin, being essential the evaluation by imaging methods for the proper diagnosis, staging and therapeutic planning. This essay illustrates the imaging aspects of ultrasound and computed tomography – and in specific situations magnetic resonance cholangiography – of the major malignancies that lead to cholestatic jaundice.

Padrão citológico de punção aspirativa do tecido tireoidiano morfologicamente normal / Cytologic pattern for fine-needle aspiration among morphologically normal thyroids

Nódulos tireoidianos pequenos com diagnóstico citológico de padrão folicular causam muita inquietação porque, se por um lado podem representar uma lesão que exige muito rigor no acompanhamento, por outro poderão representar material aspirado do tecido tireoidiano normal. OBJETIVO: Verificar o padrão citológico do tecido tireoidiano normal obtido através de punções aspirativa e não-aspirativa em cadáveres. MÉTODOS: Estudo observacional em que se procedeu a dissecção anatômica da tireóide normal e se efetuou a citoaspiração da glândula, em 38 casos. Dois patologistas cegos para a metodologia do estudo, sem conhecer a correspondência entre citologia e histologia, analisaram os esfregaços e os cortes histológicos. RESULTADOS: As tireóides normais forneceram diagnóstico citológico de bócio adenomatoso em 70,4 por cento das vezes para um observador e 92,6 por cento para o outro. Houve uma concordância regular entre os observadores, com kappa de 0,51 (p < 0,0001). Contrariamente ao que se esperava, nenhum caso exibiu padrão folicular nos preparados citológicos. CONCLUSAO: O aspecto citológico da tireóide normal em cadáveres foi semelhante ao do bócio adenomatoso.

Prevalence and classification of headache in patients with systemic lupus erythematosus.

Studies on the prevalence of headache in systemic lupus erythematosus (SLE) have shown that it varies from 32 to 78%. The purpose of our study was to determine the prevalence and characteristics of headache in SLE compared with patients with different types of diffuse connective tissue diseases (DCTD) and its relationship with clinical and laboratory manifestations of SLE. We studied patients with SLE (SLE group) and patients with DCTD (control group). All patients were made to answer questionnaire to assess the presence of headache, characterized by at least five episodes of headache during the last year, which was classified according to the International Headache Society criteria. A total of 207 patients were studied, 115 in SLE group and 92 in the control group. The 1-year prevalence of headache was 75.7% in SLE group and 66% in the control group. When the groups were analyzed, 66.1% met the diagnostic criteria for migraine in the SLE group compared with 52.2% in the control group (p=0.04) and 13.9% for tension-type headache in SLE group compared with 16.3% in the control group. The former was the only variable that reached statistical significance comparing the two groups. Both headache and migraine were associated with Raynaud's phenomenon in SLE patients (odds ratio of 2.80, 95% confidence interval: 1.11-7.05, p=0.02 and odds ratio of 2.34, 95% confidence interval: 1.04-5.23, p=0.03, respectively). These results suggest that headache is a common manifestation in SLE and in other DCTD and we cannot exclude the possibility that it may be related to the emotional stress induced by such clinical situations.

Hipertensão pulmonar no lúpus eritematoso sistêmico / Pulmonary hypertension in systemic lupus erythematosus

Introdução: Hipertensão pulmonar (HP) ocorre em cerca de 10% dos pacientes com lúpus eritematoso sistêmico (LES) e pode estar associada a um pior prognóstico. O objetivo do presente estudo é descrever uma série de casos de LES com HP acompanhados em um ambulatório de referência na Bahia.Métodos: Foram estudados pacientes com diagnóstico de LES segundo os critérios do American College of Rheumatology em seguimento no Hospital Santa Izabel, que apresentavam manifestações clínicas e alterações ecocardiográficas compatíveis com HP. O diagnóstico de HP foi definido como uma pressão sistólica em artéria pulmonar (PSAP) maior que 40 mmHg obtida por ecocardiograma trans-torácico.Resultados: Foram identificados 16 casos de HP na nossa população de pacientes com LES, correspondendo a uma prevalência de 2,5%. A PSAP aferida pelo ecocardiograma variou de 41 a 130 mmHg, com uma média de 70 mais ou menos 23 mmHg. Todos os pacientes fizeram uso em algum momento de corticosteróides e 13 utilizaram ciclosfosfamida para o tratamento das diversas manifestações do LES. Sete pacientes estão em acompanhamento, ainda com HP, seis evoluíram para óbito e em três a PSAP voltou ao normal.Conclusão: HP é uma complicação clínica não rara em LES e, devido a isso, deve ser estimulada a realização de exame ecocardiográfico periódico de rotina, mesmo em pacientes assintomáticos, com o objetivo de se detectar precocemente essa complicação

Kikuchi-Fujimoto's disease associated with systemic lupus erythematosus: case report and review of the literature.

Kikuchi-Fujimoto's disease (KFD) or histiocytic necrotising lymphadenitis is a benign and self-limited disease, of unknown aetiology, which affects mainly young women. It presents with localised lymphadenopathy, predominantly in the cervical region, accompanied by fever and leukopenia in up to 50% of the cases. KFD has been rarely described in association with systemic lupus erythematosus (SLE), and its diagnosis can precede, postdate or coincide with the diagnosis of SLE. We present a patient with the diagnosis of SLE characterised by arthritis, leukopenia, malar rash, photosensitivity and positive ANA, besides cervical lymphadenopathy whose biopsy was compatible with KFD, which improved after using prednisone. Although the presence of lymphadenopathy is not uncommon in SLE patients, particularly in the phases of disease activity, the concomitance with KFD has rarely been reported in the literature. Its recognition is necessary because one can avoid laborious investigation for infectious and lymphoproliferative diseases.