Diagnostic Reliability of Plain Radiography in Osteonecrosis of the Femoral Head: General Radiological Features Revised.

BACKGROUND AND OBJECTIVES: Osteonecrosis of the femoral head (ONFH) is an incapacitating disease that frequently results in the collapse of the femoral head and secondary osteoarthritis. The diagnosis and staging of this pathology, which usually rely on imaging studies, are challenging. Currently, conventional radiography is the basis of the initial diagnostic assessment. In recent decades, however, radiographs have been considered insensitive to early changes in ONFH and thus, a suboptimal diagnostic tool. Paradoxically, the imaging features of radiographs are often profuse, substantial, and characteristic. This study aimed to elucidate the real limitations of this radiologic tool by assessing the diagnostic reliability of the key radiologic features and staging. METHODS: This was a retrospective study in which radiographs from 28 idiopathic ONFH confirmed cases who underwent hip arthroplasty were analyzed by eight observers who were asked to identify the presence or absence of ONFH universally reported imaging features in AP hip radiographs. RESULTS: Concordance analysis revealed a poor agreement between observers for most of the assessed imaging features. Only the identification of femoral head flattening and osteoarthritis signs exhibited moderate agreement with statistical significance. In contrast, the detection of radiological osteoporosis and the loss of trabeculation showed the lowest reliability, with negative kappa coefficients. CONCLUSION: There is a lack of agreement between qualified observers, even for the identification of the most characteristic ONFH radiographic feature. The reliability of plain radiography for the detection of basic radiological elements is even weaker in the early stages of the disease.

Primary intraarterial occlusive lipoma.

Lipomas are the most frequent soft tissue tumors. Intravenous lipomas are very uncommon, but even more unusual are intraarterial lipomas. A 68-year-old heavy smoker man, with chronic alcoholism, retinopathy, dyslipidemia, and a history of type 2 diabetes mellitus of more than 10 years of evolution was hospitalized in a state of dependency. He presented ulcers on both heels and right foot sole extending to the fifth metatarsal base and bedsores in the iliac and sacral regions. Ulcer cultures showed growth of Klebsiella pneumoniae OXA34. A computed tomography angiography scan revealed that the right posterior tibial artery showed several segments with signs of obstruction or sub-occlusive stenosis along its entire length, but especially in the distal two-thirds. The patient underwent supracondylar amputation of the right lower limb. Histopathological sections of the amputated leg showed calcific atherosclerosis obliterans of the posterior tibial artery and complete occlusion in the middle portion of this artery. The occlusion was due to a well-differentiated, white adipose tissue with lipid vacuoles of uniform size. To our knowledge, this case is the first known report of a primary intraarterial lipoma in a peripheral artery. The proliferating adipose tissue within the arterial lumen contributed to distal limb ischemic necrosis. Although an intraarterial lipoma is rare, it should be considered in the differential diagnosis of the causes of peripheral arterial occlusion.

A deep learning model for prognosis prediction after intracranial hemorrhage.

BACKGROUND AND PURPOSE: Intracranial hemorrhage (ICH) is a common life-threatening condition that must be rapidly diagnosed and treated. However, there is still a lack of consensus regarding treatment, driven to some extent by prognostic uncertainty. While several prediction models for ICH detection have already been published, here we present a deep learning predictive model for ICH prognosis. METHODS: We included patients with ICH (n = 262), and we trained a custom model for the classification of patients into poor prognosis and good prognosis, using a hybrid input consisting of brain CT images and other clinical variables. We compared it with two other models, one trained with images only (I-model) and the other with tabular data only (D-model). RESULTS: Our hybrid model achieved an area under the receiver operating characteristic curve (AUC) of .924 (95% confidence interval [CI]: .831-.986), and an accuracy of .861 (95% CI: .760-.960). The I- and D-models achieved an AUC of .763 (95% CI: .622-.902) and .746 (95% CI: .598-.876), respectively. CONCLUSIONS: The proposed hybrid model was able to accurately classify patients into good and poor prognosis. To the best of our knowledge, this is the first ICH prognosis prediction deep learning model. We concluded that deep learning can be applied for prognosis prediction in ICH that could have a great impact on clinical decision-making. Further, hybrid inputs could be a promising technique for deep learning in medical imaging.

Tracheostomy Decannulation and Disorders of Consciousness Evolution.

BACKGROUND: Tracheostomy is a frequent surgical procedure in subjects with chronic disorders of consciousness (DOC). There is no consensus about safety of tracheostomy decannulation in this population.The aim of our study was to estimate if DOC improvement is a predictor for tracheostomy decannulation. Secondary outcomes include mortality rate and discharge destination. METHODS: We conducted an observational, retrospective, case-control study at a weaning and rehabilitation center (WRC). We included tracheostomized subjects with DOC admitted between August 2015 and December 2017. We matched groups based on the consciousness level at admission assessed withthe coma recovery scale revised (CRS-R). Subjects who were later decannulated formed the cases, while those that remained tracheostomized at the end of follow-up formed the controls. Improvement of DOC was defined as a progress in the categories of the CRS-R. RESULTS: 22 subjects were included in each group. No significant differences were found in clinical and demographic variables, except that controls had longer neurologic injury evolution (65.5 vs 51 days, P = .047), more tracheostomy days at admission to ourinstitution (53 vs 33.5, P = .02), and higher prevalence of neurological comorbidities (12 vs 4, P = .03). Subjects who improved their DOC had more chances of being decannulated (OR 11.28, 95% CI 1.96-123.08). Tracheostomy decannulation could not be achieved in most subjects who did not improve from vegetative state (VS) (OR 0.13, 95% CI 0.02-0.60). 8 subjects, however, could be decannulated in VS, with only one decannulation failure and no deaths. Mortality was higher in controls (0 vs 6, P = .02), especially among VS (0 vs 5, P = .049). No significant differences were found in discharge destination between groups. CONCLUSIONS: Subjects who improve their DOC are more likely to achieve tracheostomy decannulation. Some subjects in VS were decannulated, with lower mortality than those who remained tracheostomized.

A primer on deep learning and convolutional neural networks for clinicians.

Deep learning is nowadays at the forefront of artificial intelligence. More precisely, the use of convolutional neural networks has drastically improved the learning capabilities of computer vision applications, being able to directly consider raw data without any prior feature extraction. Advanced methods in the machine learning field, such as adaptive momentum algorithms or dropout regularization, have dramatically improved the convolutional neural networks predicting ability, outperforming that of conventional fully connected neural networks. This work summarizes, in an intended didactic way, the main aspects of these cutting-edge techniques from a medical imaging perspective.

Impacto del SARS-CoV2 en un Centro de desvinculación de la ventilación mecánica y rehabilitación / Impact of SARS-CoV2 on a Center for Mechanical Ventilation Weaning and Rehabilitation

Introducción: Desde diciembre de 2019, el virus SARS-CoV2 se ha propagado por todo el mundo a gran velocidad. Múltiples estudios describen su comportamiento en unidades de terapia intensiva, pero hay poca información sobre su impacto en centro de rehabilitación y cuidados críticos crónicos (CRCCC). Objetivo: Demostrar si la implementación de un protocolo de acción de contingencia podría disminuir la diseminación del virus entre los pacientes internados en un CRCCC. Materiales y Métodos: Estudio observacional, retrospectivo, transversal. Se incluyeron pacientes mayores de 18 años bajo aislamiento respiratorio, ya sea por caso sospechoso de SARS-CoV2, contacto estrecho con caso confirmado o ingreso a la institución, durante mayo de 2020. Los valores se expresaron como mediana y rango intercuantilo o frecuencia y porcentaje, según la variable. Las diferencias entre SARS-CoV2 positivos y negativos se evaluaron con test de la mediana y test exacto de Fisher. Resultados: Durante el periodo de estudio, se colocaron en aislamiento respiratorio 30 pacientes (53% por caso sospechoso, 13% por contacto estrecho y 34% por ingreso). De ellos, 5 fueron positivos para SARS-CoV2, con una mediana de 61 años (18-71), mayoría de sexo masculino (4/5), 80% traqueostomizados y 33% con asistencia ventilatoria mecánica invasiva. Un paciente murió por complicaciones relacionadas al SARS-CoV2. No se hallaron diferencias significativas en cantidad de casos positivos según la causa de aislamiento (p = 0.37) ni en las características clínico-demográficas entre positivos y negativos. Conclusión: La implementación de un protocolo de contingencia para pacientes potencialmente infectados con SARS-CoV2 en una CRCCC podría disminuir su diseminación dentro de la institución.

Impact of SARS-CoV2 on a Center for Mechanical Ventilation Weaning and Rehabilitation / Impacto del SARS-CoV2 en un Centro de desvinculación de la ventilación mecánica y rehabilitación

Introduction: Since December 2019, the SARS-CoV2 virus has propagated throughout the world at great speed. Multiple studies describe its behavior in Intensive Care Units, but there is little information about its impact on a Critical Care Recovery Center (CCRC). Objective: To show if the use of a contingency protocol could reduce virus dissemination among patients hospitalized in a CCRC. Materials and Methods: Observational, retrospective, cross-sectional study. The study included patients older than 18 years on respiratory isolation for being a suspected case of SARS-CoV2, or close contact of a confirmed case or for their admission to theinstitution, during May 2020.The values were expressed as median and interquartile range or frequency and percentage, according to the variable. The differences between positive and negative SARS-CoV2 cases were evaluated with the median test and the Fisher' s Exact Test. Results: During the study period, 30 patients were placed in respiratory isolation (53% suspected cases, 13% close contact and 34% admission to the institution). 5 of them tested positive for SARS-CoV2, with a median of 61 years (18-71), mostly males (4/5), 80% tracheostomized and 33% with invasive mechanical ventilatory assistance. One patient died from complications associated withSARS-CoV2. No significant differences were found in the number of positive cases according to the isolation cause (p = 0.37) or the clinicaldemographic characteristics between positive and negative cases. Conclusion: The use of a contingency protocol for patients potentially infected with SARS-CoV2 in a CCRC could reduce the virus dissemination inside the institution.

Análisis de una cohorte de pacientes decanulados en un centro de cuidados críticos crónicos de Argentina / Analysis of a Cohort of Decannulated Patients in a Critical Care Center for Chronically Ill Patients in Argentina

Objetivos: Describir las características de una cohorte de pacientes decanulados que ingresan a un Centro de Neurorehabilitación y Cuidados Critico Crónicos y su condición al egreso. Como objetivo secundario analizar la existencia de posibles factores de riesgo asociados con su derivación a un centro de mayor complejidad. Materiales y Métodos: Estudio descriptivo, transversal, retrospectivo, en la Clínica de Neurorehabilitación Santa Catalina, Ciudad Autónoma de Buenos Aires, Argentina. Resultados: Se decanularon 87 pacientes. 29 ingresaron con AVMi y pudieron ser desvinculados en su totalidad. La mediana de días de TQT fue de 35 días (RIQ 22-68). De los pacientes decanulados, el 21% continuaba internado en la institución al cierre del estudio. El 53% egresó vivo a su domicilio, mientras que el 23% debió ser derivado a un centro de mayor complejidad. Dos pacientes decanulados fallecieron durante su internación. Se hallaron como variables independientemente asociadas a egresar hacia un centro de mayor complejidad la presencia de antecedentes neurológicos previos a la internación en UTI (OR = 4.22, IC 95% (1.03-10.5), p=0.02) y la internación en UTI por causa respiratoria (OR = 4.44, IC 95% (1.22-16.1), p = 0.02). Conclusión: La mayoría de los pacientes decanulados lograron egresar vivos a su domicilio. Presentar antecedentes neurológicos y patología respiratoria como motivo de ingreso a UTI podrían ser factores de riesgo para ser derivados a un centro de mayor complejidad.

Analysis of a Cohort of Decannulated Patients in a Critical Care Center for Chronically Ill Patients in Argentina

Objectives: To describe the characteristics of a cohort of decannulated patients admitted to a Neuro-rehabilitation and Critical Care Center and their condition upon discharge. The secondary objective was to analyze the existence of possible risk factors associated with referral of patients to a high complexity center. Materials and Method: Descriptive, cross-sectional, retrospective study in the Clínica de Neurorehabilitación Santa Catalina, Autonomous City of Buenos Aires, Argentina. Results: 87 patients were decannulated. 29 patients were admitted with IMVA and could be completely weaned. The median of TQT days was 35 days (IQR 22-68). 21% of decannulated patients were still hospitalized at the institution upon the end of the study. 53% were discharged home alive, whereas 23% had to be referred to a high complexity center. Two decannulated patients died while they were hospitalized. Some variables independently associated with referral to a high complexity center were found, the presence of a neurological history before ICU admission (OR [odds ratio] = 4.22, 95% CI [confidence interval] (1.03-10.5), p = 0.02) and ICU admission for respiratory causes (OR = 4.44, 95% CI (1.22-16.1), p = 0.02). Conclusion: Most decannulated patients were discharged home alive. Neurological history and respiratory disease as reasons for ICU admission could be risk factors to be referred to a high complexity center.