ABSTRACT
Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods can effectively eliminate similar problems. However, the complex network structure and redundant parameters of deep neural networks and the limited storage and computing resources of clinical medical hardware devices make it difficult for this method to use widely in clinical practice. Therefore, this paper studies a lightweight pneumonia classification network, CPGResNet50 (ResNet50 with custom channel pruning and ghost methods), based on ResNet50 pruning and compression to better meet the application requirements of clinical pneumonia auxiliary diagnosis with high precision and low memory. First, based on the hierarchical channel pruning method, the channel after the convolutional layer in the bottleneck part of the backbone network layer is used as the pruning object, and the pruning operation is performed after its normalization to obtain a network model with a high compression ratio. Second, the pruned convolutional layers are decomposed into original convolutions and cheap convolutions using the optimized convolution method. The feature maps generated by the two convolution parts are combined as the input to the next convolutional layer. Further, we conducted many experiments using pneumonia X-ray medical image data. The results show that the proposed method reduces the number of parameters of the ResNet50 network model from 23.7 M to 3.455 M when the pruning rate is 90%, a reduction is more than 85%, FIOPs dropped from 4.12G to 523.09 M, and the speed increased by more than 85%. The model training accuracy error remained within 1%. Therefore, the proposed method has a good performance in the auxiliary diagnosis of pneumonia and obtained good experimental results.
Subject(s)
Data Compression , Deep Learning , Pneumonia , Algorithms , Child , Child, Preschool , Humans , Neural Networks, Computer , Pneumonia/classification , Pneumonia/diagnostic imagingABSTRACT
Ceftobiprole medocaril is a broad-spectrum 5th-generation cephalosporin with activity against Gram-positives such asmethicillin-resistant Staphylococcus aureus and penicillin-resistant Streptococcus pneumoniae, and against Gram-negatives such as Pseudomonas aeruginosa. The recommended doseis 500 mg every 8 h in 2-hour infusions. Various clinical trialshave demonstrated its usefulness in the treatment of community-acquired pneumonia and nosocomial pneumonia, with theexception of ventilator-associated pneumonia. In summary, itis a very useful antibiotic for the treatment of pneumonia. (AU)
Subject(s)
Humans , Drug Resistance, Multiple , Pneumonia/classification , Pneumonia/diagnosis , Anti-Bacterial Agents , Healthcare-Associated Pneumonia , Cephalosporins , Cephalosporin ResistanceABSTRACT
Despite the fact that the last year has been marked by theSARS-CoV-2 pandemic, there have been many articles published on non-COVID pneumonia. Making the selection has notbeen easy, having based on those articles that we think canbring us some novelty and help in clinical practice. We have divided the selection into seven sections: patient severity, diagnosis, treatment, ventilation, novelties in the guidelines, fungalinfection and organ donation. (AU)
Subject(s)
Humans , Pneumonia/classification , Pneumonia/diagnosis , Pneumonia/drug therapy , Pneumonia, Aspiration , Tissue and Organ Procurement , Patient AcuityABSTRACT
BACKGROUND: The diagnosis of pneumonia in children is challenging, given the wide overlap of many of the symptoms and physical examination findings with other common respiratory illnesses. We sought to derive and validate the novel Pneumonia Risk Score (PRS), a clinical tool utilizing signs and symptoms available to clinicians to determine a child's risk of radiographic pneumonia. METHODS: We prospectively enrolled children 3 months to 18 years in whom a chest radiograph (CXR) was obtained in the emergency department to evaluate for pneumonia. Before CXR, we collected information regarding symptoms, physical examination findings, and the physician-estimated probability of radiographic pneumonia. Logistic regression was used to predict the presence of radiographic pneumonia, and the PRS was validated in a distinct cohort of children with suspected pneumonia. RESULTS: Among 1181 children included in the study, 206 (17%) had radiographic pneumonia. The PRS included age in years, triage oxygen saturation, presence of fever, presence of rales, and presence of wheeze. The area under the curve (AUC) of the PRS was 0.71 (95% confidence interval [CI]: 0.68-0.75), while the AUC of clinician judgment was 0.61 (95% CI: 0.56-0.66) (P < 0.001). Among 2132 children included in the validation cohort, the PRS demonstrated an AUC of 0.69 (95% CI: 0.65-0.73). CONCLUSIONS: In children with suspected pneumonia, the PRS is superior to clinician judgment in predicting the presence of radiographic pneumonia. Use of the PRS may help efforts to support the judicious use of antibiotics and chest radiography among children with suspected pneumonia.
Subject(s)
Pneumonia/diagnostic imaging , Pneumonia/diagnosis , Radiography/methods , Thorax/diagnostic imaging , Adolescent , Child , Child, Preschool , Female , Fever/etiology , Humans , Infant , Logistic Models , Male , Oxygen Saturation , Pneumonia/classification , Prospective Studies , Respiratory Sounds/etiology , Risk FactorsABSTRACT
Pneumonitis is an infectious disease that causes the inflammation of the air sac. It can be life-threatening to the very young and elderly. Detection of pneumonitis from X-ray images is a significant challenge. Early detection and assistance with diagnosis can be crucial. Recent developments in the field of deep learning have significantly improved their performance in medical image analysis. The superior predictive performance of the deep learning methods makes them ideal for pneumonitis classification from chest X-ray images. However, training deep learning models can be cumbersome and resource-intensive. Reusing knowledge representations of public models trained on large-scale datasets through transfer learning can help alleviate these challenges. In this paper, we compare various image classification models based on transfer learning with well-known deep learning architectures. The Kaggle chest X-ray dataset was used to evaluate and compare our models. We apply basic data augmentation and fine-tune our feed-forward classification head on the models pretrained on the ImageNet dataset. We observed that the DenseNet201 model outperforms other models with an AUROC score of 0.966 and a recall score of 0.99. We also visualize the class activation maps from the DenseNet201 model to interpret the patterns recognized by the model for prediction.
Subject(s)
Deep Learning , Neural Networks, Computer , Pneumonia/diagnostic imaging , Pneumonia/diagnosis , Radiographic Image Interpretation, Computer-Assisted/methods , Algorithms , COVID-19/diagnosis , COVID-19/diagnostic imaging , Computational Biology , Databases, Factual , Humans , Pneumonia/classification , Radiographic Image Interpretation, Computer-Assisted/statistics & numerical data , SARS-CoV-2ABSTRACT
BACKGROUND: The World Health Organization (WHO)-defined radiological pneumonia is a preferred endpoint in pneumococcal vaccine efficacy and effectiveness studies in children. Automating the WHO methodology may support more widespread application of this endpoint. METHODS: We trained a deep learning model to classify pneumonia CXRs in children using the World Health Organization (WHO)'s standardized methodology. The model was pretrained on CheXpert, a dataset containing 224,316 adult CXRs, and fine-tuned on PERCH, a pediatric dataset containing 4,172 CXRs. The model was then tested on two pediatric CXR datasets released by WHO. We also compared the model's performance to that of radiologists and pediatricians. RESULTS: The average area under the receiver operating characteristic curve (AUC) for primary endpoint pneumonia (PEP) across 10-fold validation of PERCH images was 0.928; average AUC after testing on WHO images was 0.977. The model's classification performance was better on test images with high inter-observer agreement; however, the model still outperformed human assessments in AUC and precision-recall spaces on low agreement images. CONCLUSION: A deep learning model can classify pneumonia CXR images in children at a performance comparable to human readers. Our method lays a strong foundation for the potential inclusion of computer-aided readings of pediatric CXRs in vaccine trials and epidemiology studies.
Subject(s)
Deep Learning , Image Interpretation, Computer-Assisted/methods , Radiography, Thoracic/classification , Datasets as Topic , Female , Humans , Infant , Male , Models, Statistical , Observer Variation , Pneumonia/classification , Pneumonia/diagnostic imaging , ROC Curve , Reproducibility of Results , World Health OrganizationABSTRACT
OBJECTIVE: Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. METHODS: Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1-5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. RESULTS: All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. CONCLUSION: Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. ADVANCES IN KNOWLEDGE: Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.
Subject(s)
Deep Learning , Lung/diagnostic imaging , Pneumonia/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Child, Preschool , Early Diagnosis , Humans , Infant , Pneumonia/classification , ROC Curve , Reproducibility of ResultsABSTRACT
BACKGROUND: Deep neural networks (DNNs) are widely investigated in medical image classification to achieve automated support for clinical diagnosis. It is necessary to evaluate the robustness of medical DNN tasks against adversarial attacks, as high-stake decision-making will be made based on the diagnosis. Several previous studies have considered simple adversarial attacks. However, the vulnerability of DNNs to more realistic and higher risk attacks, such as universal adversarial perturbation (UAP), which is a single perturbation that can induce DNN failure in most classification tasks has not been evaluated yet. METHODS: We focus on three representative DNN-based medical image classification tasks (i.e., skin cancer, referable diabetic retinopathy, and pneumonia classifications) and investigate their vulnerability to the seven model architectures of UAPs. RESULTS: We demonstrate that DNNs are vulnerable to both nontargeted UAPs, which cause a task failure resulting in an input being assigned an incorrect class, and to targeted UAPs, which cause the DNN to classify an input into a specific class. The almost imperceptible UAPs achieved > 80% success rates for nontargeted and targeted attacks. The vulnerability to UAPs depended very little on the model architecture. Moreover, we discovered that adversarial retraining, which is known to be an effective method for adversarial defenses, increased DNNs' robustness against UAPs in only very few cases. CONCLUSION: Unlike previous assumptions, the results indicate that DNN-based clinical diagnosis is easier to deceive because of adversarial attacks. Adversaries can cause failed diagnoses at lower costs (e.g., without consideration of data distribution); moreover, they can affect the diagnosis. The effects of adversarial defenses may not be limited. Our findings emphasize that more careful consideration is required in developing DNNs for medical imaging and their practical applications.
Subject(s)
Diagnostic Imaging/classification , Image Interpretation, Computer-Assisted/methods , Image Interpretation, Computer-Assisted/standards , Neural Networks, Computer , Diabetic Retinopathy/classification , Diabetic Retinopathy/diagnostic imaging , Diagnostic Imaging/standards , Humans , Photography/classification , Pneumonia/classification , Pneumonia/diagnostic imaging , Radiography, Thoracic/classification , Skin Neoplasms/classification , Skin Neoplasms/diagnostic imaging , Tomography, Optical Coherence/classificationABSTRACT
We investigated the effect of Punica granatum peel aqueous extract (PGE), on pulmonary inflammation and alveolar degradation induced by intratracheal administration of Elastase in Sprague Dawley rats. Lung inflammation was induced in rats by intratracheal instillation of Elastase. On day 1 and 2, animals received an intraperitoneal injection of PGE (200 mg/mL), three hours later, they were intratracheally instilled with 25U/kg pancreatic porcine Elastase. Animals were sacrificed 7 days later. Bronchoalveolar lavage (BAL) were collected and cellularity, histology and mRNA expression of Monocyte chemotactic protein 1(MCP-1), Tumor Necrosis Factor-Alpha (TNF-α), Interleukin 6 (IL-6), and Matrix Metalloproteinase-2 (MMP-2) were studied. In addition, activity of TNF- α, IL-6 and MCP-1 on BAL were also analyzed by ELISA Kit. Elastase administration increased: BAL cellularity, neutrophils recruitment and BAL MCP1, IL-6 expressions. It also increased lung TNF-α, MCP-1, MMP-2 expressions, platelets recruitment, histological parameters at 7th day of elastase treatment. Intraperitoneal injection of 200 mg/kg of PGE reduced, significantly, BAL cellularity, and neutrophils recruitment. However, in animal treated with PGE, MCP-1, MMP-2 and IL-6 on day 7, were similar to the Sham group. Treatment with PGE (200 mg/ kg) also significantly reduced lung TNF-α, and MCP-1 expression. This study reveals that PGE Punica granatum protects against elastase lung inflammation and alveolar degradation induced in rats
Subject(s)
Animals , Male , Rats , Plant Extracts/analysis , Pancreatic Elastase/classification , Plant Bark , Pomegranate/adverse effects , Pneumonia/classification , Pulmonary Edema/classification , Emphysema/classificationABSTRACT
This study aimed to develop and validate computer-aided diagnosis (CXDx) system for classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray (CXR) images. From two public datasets, 1248 CXR images were obtained, which included 215, 533, and 500 CXR images of COVID-19 pneumonia patients, non-COVID-19 pneumonia patients, and the healthy samples, respectively. The proposed CADx system utilized VGG16 as a pre-trained model and combination of conventional method and mixup as data augmentation methods. Other types of pre-trained models were compared with the VGG16-based model. Single type or no data augmentation methods were also evaluated. Splitting of training/validation/test sets was used when building and evaluating the CADx system. Three-category accuracy was evaluated for test set with 125 CXR images. The three-category accuracy of the CAD system was 83.6% between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy. Sensitivity for COVID-19 pneumonia was more than 90%. The combination of conventional method and mixup was more useful than single type or no data augmentation method. In conclusion, this study was able to create an accurate CADx system for the 3-category classification. Source code of our CADx system is available as open source for COVID-19 research.
Subject(s)
Coronavirus Infections/diagnosis , Pneumonia, Viral/diagnosis , Pneumonia/diagnosis , Thorax/diagnostic imaging , Adult , Aged , Automation , Betacoronavirus/isolation & purification , COVID-19 , Coronavirus Infections/virology , Databases, Factual , Deep Learning , Diagnosis, Computer-Assisted , Female , Humans , Male , Middle Aged , Pandemics , Pneumonia/classification , Pneumonia, Viral/virology , SARS-CoV-2ABSTRACT
The COVID-19 diagnostic approach is mainly divided into two broad categories, a laboratory-based and chest radiography approach. The last few months have witnessed a rapid increase in the number of studies use artificial intelligence (AI) techniques to diagnose COVID-19 with chest computed tomography (CT). In this study, we review the diagnosis of COVID-19 by using chest CT toward AI. We searched ArXiv, MedRxiv, and Google Scholar using the terms "deep learning", "neural networks", "COVID-19", and "chest CT". At the time of writing (August 24, 2020), there have been nearly 100 studies and 30 studies among them were selected for this review. We categorized the studies based on the classification tasks: COVID-19/normal, COVID-19/non-COVID-19, COVID-19/non-COVID-19 pneumonia, and severity. The sensitivity, specificity, precision, accuracy, area under the curve, and F1 score results were reported as high as 100%, 100%, 99.62, 99.87%, 100%, and 99.5%, respectively. However, the presented results should be carefully compared due to the different degrees of difficulty of different classification tasks.
Subject(s)
Betacoronavirus , Clinical Laboratory Techniques , Coronavirus Infections/diagnostic imaging , Pandemics , Pneumonia, Viral/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Tomography, X-Ray Computed/statistics & numerical data , Artificial Intelligence , COVID-19 , COVID-19 Testing , Coronavirus Infections/diagnosis , Coronavirus Infections/epidemiology , Deep Learning , Humans , Neural Networks, Computer , Pneumonia/classification , Pneumonia/diagnostic imaging , Pneumonia, Viral/epidemiology , Radiographic Image Interpretation, Computer-Assisted/statistics & numerical data , Radiography, Thoracic/statistics & numerical data , SARS-CoV-2 , Sensitivity and SpecificityABSTRACT
BACKGROUND: Cervical arthroplasty has established itself as a safe and efficacious alternative to fusion in management of symptomatic cervical degenerative disease. Recent literature has indicated a trend toward decreased risk of reoperation with cervical arthroplasty, and reoperation in this subset commonly occurs secondary to recurrent pain and device-related complications. The instance of cervical arthroplasty migration, particularly in the setting of trauma, is particularly rare. Here, we report the first case of implant migration secondary to iatrogenic trauma following neck manipulation during direct laryngoscopy for mechanical intubation. CASE DESCRIPTION: A 53-year-old smoker with cervical spondylosis underwent a cervical 3/4 arthroplasty with a ProDisc-C implant. About a month postoperatively, he was intubated via direct laryngoscopy for community acquired pneumonia and began experiencing new dysphonia and dysphagia after extubation. Delayed imaging revealed anterior migration of the implant. The patient immediately underwent removal of the implant and conversion to anterior cervical discectomy and fusion. CONCLUSIONS: Supraphysiologic forces exerted through neck manipulation in mechanical intubation mimicked low-energy trauma, and in the setting of ligamentous resection necessary for cervical arthroplasty and inadequate osseous integration, led to migration of the implant. We recommend the integration of fiberoptic technique or video laryngoscopy with manual in line stabilization for intubation of post cervical arthroplasty patients when airway management is necessary within 10 months after cervical arthroplasty. Clinicians and anesthesiologists should have a high clinical suspicion for prompt and early workup with spine imaging in the setting of persistent postintubation symptoms such as dysphonia and/or dysphagia.
Subject(s)
Arthroplasty/methods , Intervertebral Disc Degeneration/surgery , Intubation, Intratracheal/adverse effects , Neurosurgical Procedures/methods , Device Removal , Diskectomy/methods , Foreign-Body Migration , Humans , Laryngoscopy/adverse effects , Male , Middle Aged , Pneumonia/classification , Pneumonia/therapy , Prostheses and Implants , Spinal Fusion , Spondylosis/surgeryABSTRACT
OBJECTIVE: This study aimed to investigate the clinical characteristics and risk factors associated with severe pneumonia in systemic lupus erythematosus (SLE) patients from China. METHOD: We performed a retrospective study in 112 hospitalized SLE patients who had had pneumonia for 8 years. The primary outcome was severe pneumonia, followed by descriptive analysis, group comparison and bivariate analysis. RESULTS: A total of 28 SLE patients were diagnosed with severe pneumonia, with a ratio of 5:23 between men and women. The mean age at diagnosis was 44.36 ± 12.389 years. The median disease duration was 72 months, and the median SLE Disease Activity Index 2000 (SLEDAI 2K) score was 8. The haematological system was the most affected, with an incidence of anaemia in 85.7% of cases and thrombocytopenia in 75% of cases, followed by lupus nephritis in 50% of cases and central nervous system involvement in 10.71% of cases. Cultured sputum specimens were positive in 17 (68%) SLE patients with severe pneumonia, of whom nine (36%) were cases of fungal infection, five (20%) were cases of bacterial infection and three (12%) were cases of mixed infection. Using multivariate logistic regression analysis, we concluded that a daily dosage of prednisone (>10 mg; odds ratio (OR) = 3.193, p = 0.005), a low percentage of CD4+ T lymphocytes (OR = 0.909, p = 0.000), a high SLEDAI 2K score (OR = 1.182, p = 0.001) and anaemia (OR = 1.182, p = 0.001) were all independent risk factors for pneumonia in SLE patients, while a low percentage of CD4+ T lymphocytes (OR = 0.908, p = 0.033), a daily dose of prednisone of >10 mg (OR = 35.67, p = 0.001) were independent risk factors for severe pneumonia in SLE patients. CONCLUSION: Severe pneumonia is not rare in lupus, and is associated with high mortality and poor prognosis. Monitoring CD4+ T-cell counts and giving a small dose of glucocorticoids can reduce the occurrence of severe pneumonia and improve the prognosis of patients with lupus.
Subject(s)
Lupus Erythematosus, Systemic/complications , Pneumonia/diagnosis , Pneumonia/epidemiology , Sputum/microbiology , Adult , China/epidemiology , Female , Glucocorticoids/adverse effects , Glucocorticoids/therapeutic use , Humans , Immunosuppressive Agents/adverse effects , Immunosuppressive Agents/therapeutic use , Logistic Models , Lupus Erythematosus, Systemic/drug therapy , Lupus Nephritis/epidemiology , Male , Middle Aged , Multivariate Analysis , Pneumonia/classification , Prognosis , Retrospective Studies , Risk Factors , Severity of Illness Index , Thrombocytopenia/epidemiologyABSTRACT
Antimicrobial resistance is a global crisis. Prescribing antibacterial combinations may be one way of reducing the development of resistance in target pathogens, as in the treatment of tuberculosis. Combinations may be useful for ascertaining synergy, broadening antimicrobial cover to reduce the risk of non-susceptibility, antimicrobial stewardship reasons, and immune modulation. The current research literature and/or prevailing global standards of clinical care suggest that combination therapy may be advantageous in: severe community-acquired pneumonia; severe hospital-acquired or ventilator-associated pneumonia or when there is a high risk of resistance in hospital-acquired or ventilator-associated pneumonia; multi-drug or extensively drug-resistant Gram-negative infections; and severe group A streptococcal infections. In other situations, combinations may be harmful. Overall, outside of tuberculosis, combination antibacterial therapy is likely to improve outcomes only in specific circumstances and there is little evidence to suggest that this prevents the development of bacterial resistance. Further high-quality research is essential.
Subject(s)
Anti-Bacterial Agents/therapeutic use , Pneumonia/drug therapy , Acute Disease , Anti-Bacterial Agents/administration & dosage , Antimicrobial Stewardship , Bacteriological Techniques , Community-Acquired Infections , Cross Infection , Drug Resistance, Bacterial , Drug Synergism , Drug Therapy, Combination , Humans , Immunomodulation/drug effects , Pneumonia/classification , Severity of Illness IndexABSTRACT
Resumen La neumonía es una infección a nivel del parénquima pulmonar, que puede categorizarse según el lugar de contagio como adquirida en la comunidad (NAC) o nosocomial, lo cual resulta muy importante tener presente al momento de definir el manejo. Para fines del presente artículo, se hace énfasis en la NAC de etiología bacteriana, enfatizando aquellas infecciones producidas por microorganismos como: Sreptococcus pneumoniae, Haemophilus influenzae, Mycoplasma pneumoniae y Legionella sp También se hace referencia a la presentación clínica y pruebas de gabinete existentes para facilitar el diagnóstico y valorar de forma objetiva la evolución del cuadro. Se menciona la utilidad de escalas como la PSI, CURB65, SMART-COP, SCAP, entre otras, para determinar si el manejo más oportuno de la NAC es a nivel ambulatorio o intrahospitalario y, en caso de ser este último, identificar si lo más recomendado es el seguimiento en la Unidad de Cuidados Intensivos (UCI) o en salones de medicina interna. Con respecto al tratamiento, se exponen diversos esquemas de antibioticoterapia recomendados para el manejo de NAC a nivel ambulatorio, intrahospitalario y en unidad de cuidados intensivos (UCI), tales como el uso de penicilinas, inhibidores de betalactamasas, quinolonas, cefalosporinas, macrólidos, entre otros. A su vez, se mencionan los criterios que definen los tiempos de duración de los esquemas antibióticos y las recomendaciones del National Institute for Health and Care Excellence (NICE) para la educación del paciente con NAC por parte del médico tratante.
Abstract: Pneumonia is an infection located in lung parenchyma that can be classified according to the place of acquisition into Community-Acquired Pneumonia (CAP) or Hospital and Healthcare-Acquired Pneumonia, which is of major importance to define the physician management. In this article the main idea to present the bacterial CAP giving special importance to those caused by Sreptococcus pneumoniae, Haemophilus influenzae, Mycoplasma pneumoniae y Legionella sp. In addition, the following article approaches the clinical presentation and diverse laboratory tests to complement an accurate diagnosis and the evolution of the disease. The scores PSI, CURB65, SMART-COP and SCAP can be a very useful tool to help the physician determine if the patient needs to be hospitalized in an internal medicine service, intensive care unit or if the case can be handled as an outpatient. The antibiotics are keystone to treat the pneumonia, and different therapies designed to manage CAP in outpatients and inpatients are explained, such as amoxicillin, amoxixillin/clavulanate, azithromycin, cefdinir, moxifloxacin among others; as well as the criteria to determine the optimal duration of the treatment. As an addition the recommendations given by the National Institute for Health and Care Excellence (NICE) are provided to the physicians as a tool to improve patient's education and optimize the initial approach and management.
Subject(s)
Humans , Pneumococcal Infections/drug therapy , Pneumonia/classification , Anti-Bacterial Agents/therapeutic use , Respiratory Therapy/trends , Costa RicaABSTRACT
BACKGROUND: Pneumonia is the leading cause of sepsis. In 2016, the 3rd International Consensus Conference for Sepsis released the Quick Sepsis-Related Organ Failure Assessment (qSOFA) to identify risk for poor outcomes in sepsis. OBJECTIVE: We sought to externally validate qSOFA in emergency department (ED) patients with pneumonia and compare the accuracy of qSOFA to systemic inflammatory response syndrome score (SIRS), Confusion, Respiratory Rate and Blood Pressure (CRB), Confusion, Respiratory Rate, Blood Pressure and Age (CRB-65), and DS CRB-65, which is based on the CRB-65 score and includes two additional items-presence of underlying comorbid disease and blood oxygen saturation. METHODS: A subgroup analysis of U.S. Critical Illness and Injury Trials Group (USCIITG-Lung Injury Prevention Study [LIPS]; ClinicalTrials.gov ID: NCT00889772) prospective cohort. The primary outcome was in-hospital mortality. Secondary outcomes were measures of intensive care unit (ICU) utilization. Sensitivity, specificity, and area under the curve (AUC) were reported. RESULTS: From March to August 2009, 5584 patients were enrolled; 713 met inclusion criteria. Median age was 61 years (interquartile range 49-75 years). SIRS criteria had the highest sensitivity for death (89%) and lowest specificity (25%), while CRB had the highest specificity (88%) and lowest sensitivity (31%), followed by qSOFA (80% and 53%, respectively). This trend was maintained for the secondary outcomes. There was no significant difference in the AUC for death using qSOFA (AUC 0.75; 95% confidence interval [CI] 0.66-0.84), SIRS (AUC 0.70; 95% CI 0.61-0.78), CRB (AUC 0.71; 95% CI 0.62-0.80), CRB-65 (AUC 0.71; 95% CI 0.63-0.80), and DS CRB-65 (AUC 0.73; 95% CI 0.64-0.82). CONCLUSIONS: In this multicenter observational study of ED patients hospitalized with pneumonia, we found no significant differences between qSOFA and SIRS for predicting in-hospital death. In addition, several popular pneumonia-specific severity scores performed nearly identically to qSOFA score in predicting death and ICU utilization. Validation is needed in a larger sample.
Subject(s)
Emergency Service, Hospital/standards , Organ Dysfunction Scores , Pneumonia/classification , Adult , Aged , Area Under Curve , Cohort Studies , Emergency Service, Hospital/organization & administration , Emergency Service, Hospital/statistics & numerical data , Female , Humans , Male , Middle Aged , Pneumonia/physiopathology , Prospective Studies , ROC Curve , Retrospective Studies , Severity of Illness IndexABSTRACT
In recent years, the use of immune checkpoint inhibitor (ICI) therapy has rapidly grown, with increasing U.S. Food and Drug Administration approvals of a variety of agents used as first- and second-line treatments of various malignancies. ICIs act through a unique mechanism of action when compared with those of conventional chemotherapeutic agents. ICIs target the cell surface receptors cytotoxic T-lymphocyte antigen-4, programmed cell death protein 1, or programmed cell death ligand 1, which result in immune system-mediated destruction of tumor cells. Immune-related adverse events are an increasingly recognized set of complications of ICI therapy that may affect any organ system. ICI therapy-related pneumonitis is an uncommon but important complication of ICI therapy, with potential for significant morbidity and mortality. As the clinical manifestation is often nonspecific, CT plays an important role in diagnosis and triage. Several distinct radiographic patterns of pneumonitis have been observed: (a) organizing pneumonia, (b) nonspecific interstitial pneumonia, (c) hypersensitivity pneumonitis, (d) acute interstitial pneumonia-acute respiratory distress syndrome, (e) bronchiolitis, and (f) radiation recall pneumonitis. Published guidelines outline the treatment of ICI therapy-related pneumonitis based on the severity of symptoms. Treatment is often effective, although recurrence is possible. This article reviews the mechanism of ICIs and ICI therapy complications, with subsequent management techniques and illustrations of the various radiologic patterns of ICI-therapy related pneumonitis.©RSNA, 2019.
Subject(s)
Antineoplastic Agents, Immunological/adverse effects , B7-H1 Antigen/antagonists & inhibitors , CTLA-4 Antigen/antagonists & inhibitors , Pneumonia/chemically induced , Programmed Cell Death 1 Receptor/antagonists & inhibitors , Alveolitis, Extrinsic Allergic/chemically induced , Alveolitis, Extrinsic Allergic/diagnostic imaging , Bronchiolitis/chemically induced , Bronchiolitis/diagnostic imaging , Cryptogenic Organizing Pneumonia/chemically induced , Cryptogenic Organizing Pneumonia/diagnostic imaging , Diagnosis, Differential , Hamman-Rich Syndrome/chemically induced , Hamman-Rich Syndrome/diagnostic imaging , Humans , Neoplasms/complications , Neoplasms/drug therapy , Pneumonia/classification , Pneumonia/diagnosis , Pneumonia/drug therapy , Prognosis , Radiodermatitis/chemically induced , Radiodermatitis/diagnostic imaging , Recurrence , Respiratory Distress Syndrome/chemically induced , Respiratory Distress Syndrome/diagnostic imaging , Sarcoidosis/diagnostic imaging , Severity of Illness Index , Symptom Assessment , Tomography, X-Ray ComputedABSTRACT
OBJECTIVE: To evaluate whether changes in diagnosis assignment explain reductions in 30-day readmission for patients with pneumonia following the Hospital Readmission Reduction Program (HRRP). DATA SOURCES: 100 percent MedPAR, 2008-2015. STUDY DESIGN: Retrospective cohort study of Medicare discharges in HRRP-eligible hospitals. Outcomes were 30-day readmission rates for pneumonia under a "narrow" definition (used for the HRRP until October 2015; n = 2 288 644) and a "broad" definition that included certain diagnoses of sepsis and aspiration pneumonia (used since October 2015; n = 3 618 215). We estimated changes in 30-day readmissions in the pre-HRRP period (January 2008-March 2010), the HRRP implementation period (April 2010-September 2012), and the HRRP penalty period (October 2012-June 2015). PRINCIPAL FINDINGS: Under the narrow definition, adjusted annual readmission rates changed by +0.07 percentage points (pp) during the pre-HRRP period (95% CI: -0.03 pp, +0.18 pp), -1.07 pp during HRRP implementation (95% CI: -1.15 pp, -0.99 pp), and -0.09 pp during the penalty period (95% CI: -0.18 pp, -0.00 pp). Under the broad definition, 30-day readmissions changed by +0.21 pp during the pre-HRRP period (95% CI: +0.12 pp, +0.30 pp), -1.28 pp during HRRP implementation (95% CI: -1.35 pp, -1.21 pp), and -0.09 pp during the penalty period (95% CI: -0.16 pp, -0.02 pp). CONCLUSIONS: Changes in the coding of inpatient pneumonia admissions do not explain readmission reduction following the HRRP.
Subject(s)
Clinical Coding/standards , Hospitalization/statistics & numerical data , Medicare/statistics & numerical data , Patient Readmission/statistics & numerical data , Pneumonia/classification , Cohort Studies , Humans , Retrospective Studies , United StatesABSTRACT
No disponible
Subject(s)
Humans , Community-Acquired Infections/epidemiology , Age Distribution , Social Determinants of Health , Pneumonia/epidemiology , Risk Factors , Odds Ratio , Pneumonia/classification , Pneumonia/pathologyABSTRACT
This study proposes a convolutional neural network model trained from scratch to classify and detect the presence of pneumonia from a collection of chest X-ray image samples. Unlike other methods that rely solely on transfer learning approaches or traditional handcrafted techniques to achieve a remarkable classification performance, we constructed a convolutional neural network model from scratch to extract features from a given chest X-ray image and classify it to determine if a person is infected with pneumonia. This model could help mitigate the reliability and interpretability challenges often faced when dealing with medical imagery. Unlike other deep learning classification tasks with sufficient image repository, it is difficult to obtain a large amount of pneumonia dataset for this classification task; therefore, we deployed several data augmentation algorithms to improve the validation and classification accuracy of the CNN model and achieved remarkable validation accuracy.