Feature Selection, Ranking of Each Feature and Classification for the Diagnosis of Community Acquired Legionella Pneumonia

Diagnosis of community acquired legionella pneumonia (CALP) is currently performed by means of laboratory techniques which may delay diagnosis several hours. To determine whether ANN can categorize CALP and non-legionella community-acquired pneumonia (NLCAP) and be standard for use by clinicians, we prospectively studied 203 patients with community-acquired pneumonia (CAP) diagnosed by laboratory tests. Twenty one clinical and analytical variables were recorded to train a neural net with two classes (LCAP or NLCAP class). In this paper we deal with the problem of diagnosis, feature selection, and ranking of the features as a function of their classification importance, and the design of a classifier the criteria of maximizing the ROC (Receiving operating characteristics) area, which gives a good trade-off between true positives and false negatives. In order to guarantee the validity of the statistics; the train-validation-test databases were rotated by the jackknife technique, and a multistarting procedure was done in order to make the system insensitive to local maxima.

Diagnostic microbiologique de la pneumonie [Microbiological diagnosis of pneumonia].

Les pneumonies causent une mortalité et une morbidité significatives. De manière simplifiée, deux types de pneumonie sont décrits : la pneumonie communautaire et la pneumonie nosocomiale avec le pneumocoque et l'Haemophilus influenzae comme causes principales pour la première, le Pseudomonas et diverses entérobactéries pour la deuxième. La réalité est cependant plus complexe puisque l'on distingue aussi la pneumonie d'aspiration par exemple. La culture est très importante dans le cas des pneumonies nosocomiales car elle permet de déterminer la sensibilité aux antibiotiques de l'agent infectieux et d'adapter le traitement. Pour les patients immunosupprimés, le diagnostic différentiel est plus large et la recherche par tests moléculaires de certains virus, de champignons filamenteux et du Pneumocystis peut se révéler informative. Pneumonia is an importance cause of mortality and morbidity in adults. Two types of pneumonia are defined: community-acquired and nosocomial pneumonia with their corresponding etiology such as pneumococci or Haemophilus influenzae and Pseudomonas or enterobacteriaceae, respectively. However, the reality is more complex with aspiration pneumonia, pneumonia in immunocompromised patient, and pneumonia in ventilated patients. Culture in the case of nosocomial pneumonia is especially important to obtain the antibiotic susceptibility of the infectious agent and to adjust therapy. Moreover for immunocompromised patients, the differential diagnosis is much wider looking for viruses, filamentous fungi and Pneumocystis can be very informative, using new molecular assays.

Pneumonia intersticial linfocítica: correlação da tomografia computadorizada de alta resolução com a anatomopatologia

A proposta do trabalho é apresentar os achados radiológicos observados na tomografia computadorizada de alta resolução do tórax de dois pacientes com pneumonia intersticial linfocítica e correlacioná-los com os aspectos anatomopatológicos, obtidos a partir de biópsias a céu aberto. Um dos pacientes mostrou, na tomografia, basicamente opacidades em vidro fosco difusas, e o outro tinha infiltração ao longo das bainhas conjuntivas peribroncovasculares. Na anatomopatologia o padrão predominante foi o de infiltração intersticial, especialmente ao longo dos septos alveolares, por linfócitos policlonais. O estudo mostrou estreita correlação entre os achados anatomopatológicos e aqueles observados na tomografia computadorizada de alta resolução do tórax.

Cell wall precursors are required to organize the chlamydial division septum.

Members of the Chlamydiales order are major bacterial pathogens that divide at mid-cell, without a sequence homologue of the FtsZ cytokinetic tubulin and without a classical peptidoglycan cell wall. Moreover, the spatiotemporal mechanisms directing constriction in Chlamydia are not known. Here we show that the MreB actin homologue and its conserved regulator RodZ localize to the division furrow in Waddlia chondrophila, a member of the Chlamydiales order implicated in human miscarriage. RodZ is recruited to the septal site earlier than MreB and in a manner that depends on biosynthesis of the peptidoglycan precursor lipid II by the MurA enzyme. By contrast, crosslinking of lipid II peptides by the Pbp3 transpeptidase disperses RodZ from the septum. Altogether, these findings provide a cytological framework for understanding chlamydial cytokinesis driven by septal cell wall synthesis.

Biomarkers of Host Response Predict Primary End-Point Radiological Pneumonia in Tanzanian Children with Clinical Pneumonia: A Prospective Cohort Study.

BACKGROUND: Diagnosing pediatric pneumonia is challenging in low-resource settings. The World Health Organization (WHO) has defined primary end-point radiological pneumonia for use in epidemiological and vaccine studies. However, radiography requires expertise and is often inaccessible. We hypothesized that plasma biomarkers of inflammation and endothelial activation may be useful surrogates for end-point pneumonia, and may provide insight into its biological significance. METHODS: We studied children with WHO-defined clinical pneumonia (n = 155) within a prospective cohort of 1,005 consecutive febrile children presenting to Tanzanian outpatient clinics. Based on x-ray findings, participants were categorized as primary end-point pneumonia (n = 30), other infiltrates (n = 31), or normal chest x-ray (n = 94). Plasma levels of 7 host response biomarkers at presentation were measured by ELISA. Associations between biomarker levels and radiological findings were assessed by Kruskal-Wallis test and multivariable logistic regression. Biomarker ability to predict radiological findings was evaluated using receiver operating characteristic curve analysis and Classification and Regression Tree analysis. RESULTS: Compared to children with normal x-ray, children with end-point pneumonia had significantly higher C-reactive protein, procalcitonin and Chitinase 3-like-1, while those with other infiltrates had elevated procalcitonin and von Willebrand Factor and decreased soluble Tie-2 and endoglin. Clinical variables were not predictive of radiological findings. Classification and Regression Tree analysis generated multi-marker models with improved performance over single markers for discriminating between groups. A model based on C-reactive protein and Chitinase 3-like-1 discriminated between end-point pneumonia and non-end-point pneumonia with 93.3% sensitivity (95% confidence interval 76.5-98.8), 80.8% specificity (72.6-87.1), positive likelihood ratio 4.9 (3.4-7.1), negative likelihood ratio 0.083 (0.022-0.32), and misclassification rate 0.20 (standard error 0.038). CONCLUSIONS: In Tanzanian children with WHO-defined clinical pneumonia, combinations of host biomarkers distinguished between end-point pneumonia, other infiltrates, and normal chest x-ray, whereas clinical variables did not. These findings generate pathophysiological hypotheses and may have potential research and clinical utility.

Pneumonia lipídica - aspectos na tomografia computadorizada: relato de caso

Os autores relatam um caso de pneumonia lipídica em um paciente de 80 anos de idade, que iniciou o quadro com dispnéia em repouso. Havia história de constipação crônica, com uso freqüente de laxativos oleosos. O paciente apresentava diminuição do nível de consciência e os familiares relatavam tosse e engasgos freqüentes, durante o uso do medicamento. As radiografias de tórax demonstravam consolidação localizada no segmento posterior do lobo superior do pulmão direito, além de opacidades mal definidas nos lobos inferiores e que não se modificavam em exames sucessivos. A tomografia computadorizada de alta resolução mostrou consolidações com medidas de densidade negativas em seu interior, variando de -29 a -83 UH, e opacidades em vidro fosco localizadas no lobo superior do pulmão direito e nos lobos inferiores, com predomínio nos segmentos posteriores. O diagnóstico foi feito através do lavado bronco-alveolar, que evidenciou a presença do material oleoso. O paciente foi orientado a interromper o uso de laxativos oleosos e não retornou para o controle ambulatorial.

Severe pneumonia due to Parachlamydia acanthamoebae following intranasal inoculation: a mice model.

Parachlamydia acanthamoebae is an obligate intracellular bacterium naturally infecting free-living amoebae. The role of this bacterium as an agent of pneumonia is suggested by sero-epidemiological studies and molecular surveys. Furthermore, P. acanthamoebae may escape macrophages microbicidal effectors. Recently, we demonstrated that intratracheal inoculation of P. acanthamoebae induced pneumonia in 100% of infected mice. However, the intratracheal route of infection is not the natural way of infection and we therefore developed an intranasal murine model. Mice inoculated with P. acanthamoebae by intranasal inoculation lost 18% of their weight up to 8 days post-inoculation. All mice presented histological signs of pneumonia at day 2, 4, 7, and 10 post-inoculation, whereas no control mice harboured signs of pneumonia. A 5-fold increase in bacterial load was observed from day 0 to day 4 post-inoculation. Lungs of inoculated mice were positive by Parachlamydia-specific immunohistochemistry 4 days post-inoculation, and P. acanthamoebae were localized within macrophages. Thus, we demonstrated that P. acanthamoebae induce a severe pneumonia in mice. This animal model (i) further supports the role of P. acanthamoebae as an agent of pneumonia, confirming the third Koch postulate, and (ii) identified alveolar macrophages as one of the initial cells where P. acanthamoebae is localized following infection.

Pneumonia lipoídica em adultos: aspectos na tomografia computadorizada de alta resolução

OBJETIVO: Apresentar os aspectos na tomografia computadorizada de alta resolução do tórax da pneumonia lipoídica exógena por aspiração de óleo mineral, em pacientes adultos MATERIAIS E MÉTODOS: Foram estudados oito pacientes adultos - quatro mulheres e quatro homens - com média de idade de 69,4 anos, todos usuários de óleo mineral para tratamento de constipação intestinal. Os exames foram avaliados por dois radiologistas, de forma independente RESULTADOS: Os achados tomográficos mais comuns foram as consolidações com áreas de densidade de gordura de permeio, e o padrão de pavimentação em mosaico. As lesões foram bilaterais em seis pacientes, e unilaterais em dois CONCLUSÃO: O encontro de consolidações pulmonares com áreas de densidade de gordura de permeio, associado à história clínica do uso de óleo mineral, é diagnóstico de pneumonia lipoídica exógena.

A prospective cohort study of healthcare visits and rehospitalizations after hospital discharge in community-acquired pneumonia

Background and objective: We aimed to identify the frequency of, reasons for and risk factors associated with additional healthcare visits and rehospitalizations (healthcare interactions) by patients with community-acquired pneumonia (CAP) within 30 days of hospital discharge. Methods: Observational analysis of a prospective cohort of adults hospitalized with CAP at a tertiary hospital (2007-2009). Additional healthcare interactions were defined as the visits to a primary care centre or emergency department and hospital readmissions within 30 days of discharge. Results: Of the 934 hospitalized patients with CAP, 282 (34.1%) had additional healthcare interactions within 30 days of hospital discharge: 149 (52.8%) needed an additional visit to their primary care centre and 177 (62.8%) attended the emergency department. Seventy-two (25.5%) patients were readmitted to hospital. The main reasons for additional healthcare interactions were worsening of signs or symptoms of CAP and new or worsening comorbid conditions independent of pneumonia, mainly cardiovascular and pulmonary diseases. The only independent factor associated with visits to primary care centre or emergency department was alcohol abuse (odds ratio [OR] = 1.65; 95% confidence interval [CI]: 1.03-2.64). Prior hospitalization (≤ 90 days) (OR = 2.47; 95% CI: 1.11-5.52) and comorbidities (OR = 3.99; 95% CI: 1.12-14.23) were independently associated with rehospitalization. Conclusions: Additional healthcare visits and rehospitalizations within 30 days of hospital discharge are common in patients with CAP. This is mainly due to a worsening of signs or symptoms of CAP and/or comorbid conditions. These findings may have implications for discharge planning and follow-up of patients with CAP.

External Validation of the Prestroke Independence, Sex, Age, National Institutes of Health Stroke Scale (ISAN) Score for Predicting Stroke-Associated Pneumonia in the Athens Stroke Registry.

BACKGROUND AND PURPOSE: The Prestroke Independence, Sex, Age, National Institutes of Health Stroke Scale (ISAN) score was developed recently for predicting stroke-associated pneumonia (SAP), one of the most common complications after stroke. The aim of the present study was to externally validate the ISAN score. METHODS: Data included in the Athens Stroke Registry between June 1992 and December 2011 were used for this analysis. Inclusion criteria were the availability of all ISAN score variables (prestroke independence, sex, age, National Institutes of Health Stroke Scale score). Receiver operating characteristic curves and linear regression analyses were used to determine the discriminatory power of the score and to assess the correlation between actual and predicted pneumonia in the study population. Separate analyses were performed for patients with acute ischemic stroke (AIS) and intracerebral hemorrhage (ICH). RESULTS: The analysis included 3204 patients (AIS: 2732, ICH: 472). The ISAN score demonstrated excellent discrimination in patients with AIS (area under the curve [AUC]: .83 [95% confidence interval {CI}: .81-.85]). In the ICH group, the score was less effective (AUC: .69 [95% CI: .63-.74]). Higher-risk groups of ISAN score were associated with an increased relative risk of SAP; risk increase was more prominent in the AIS population. Predicted pneumonia correlated very well with actual pneumonia (AIS group: R(2) = .885; β-coefficient = .941, P < .001; ICH group: R(2) = .880, β-coefficient = .938, P < .001). CONCLUSIONS: In our external validation in the Athens Stroke Registry cohort, the ISAN score predicted SAP very accurately in AIS patients and demonstrated good discriminatory power in the ICH group. Further validation and assessment of clinical usefulness would strengthen the score's utility further.

A prospective cohort study of healthcare visits and rehospitalizations after hospital discharge in community-acquired pneumonia

Background and objective: We aimed to identify the frequency of, reasons for and risk factors associated with additional healthcare visits and rehospitalizations (healthcare interactions) by patients with community-acquired pneumonia (CAP) within 30 days of hospital discharge. Methods: Observational analysis of a prospective cohort of adults hospitalized with CAP at a tertiary hospital (2007-2009). Additional healthcare interactions were defined as the visits to a primary care centre or emergency department and hospital readmissions within 30 days of discharge. Results: Of the 934 hospitalized patients with CAP, 282 (34.1%) had additional healthcare interactions within 30 days of hospital discharge: 149 (52.8%) needed an additional visit to their primary care centre and 177 (62.8%) attended the emergency department. Seventy-two (25.5%) patients were readmitted to hospital. The main reasons for additional healthcare interactions were worsening of signs or symptoms of CAP and new or worsening comorbid conditions independent of pneumonia, mainly cardiovascular and pulmonary diseases. The only independent factor associated with visits to primary care centre or emergency department was alcohol abuse (odds ratio [OR] = 1.65; 95% confidence interval [CI]: 1.03-2.64). Prior hospitalization (≤ 90 days) (OR = 2.47; 95% CI: 1.11-5.52) and comorbidities (OR = 3.99; 95% CI: 1.12-14.23) were independently associated with rehospitalization. Conclusions: Additional healthcare visits and rehospitalizations within 30 days of hospital discharge are common in patients with CAP. This is mainly due to a worsening of signs or symptoms of CAP and/or comorbid conditions. These findings may have implications for discharge planning and follow-up of patients with CAP.

A prospective cohort study of healthcare visits and rehospitalizations after hospital discharge in community-acquired pneumonia

Background and objective: We aimed to identify the frequency of, reasons for and risk factors associated with additional healthcare visits and rehospitalizations (healthcare interactions) by patients with community-acquired pneumonia (CAP) within 30 days of hospital discharge. Methods: Observational analysis of a prospective cohort of adults hospitalized with CAP at a tertiary hospital (2007-2009). Additional healthcare interactions were defined as the visits to a primary care centre or emergency department and hospital readmissions within 30 days of discharge. Results: Of the 934 hospitalized patients with CAP, 282 (34.1%) had additional healthcare interactions within 30 days of hospital discharge: 149 (52.8%) needed an additional visit to their primary care centre and 177 (62.8%) attended the emergency department. Seventy-two (25.5%) patients were readmitted to hospital. The main reasons for additional healthcare interactions were worsening of signs or symptoms of CAP and new or worsening comorbid conditions independent of pneumonia, mainly cardiovascular and pulmonary diseases. The only independent factor associated with visits to primary care centre or emergency department was alcohol abuse (odds ratio [OR] = 1.65; 95% confidence interval [CI]: 1.03-2.64). Prior hospitalization (≤ 90 days) (OR = 2.47; 95% CI: 1.11-5.52) and comorbidities (OR = 3.99; 95% CI: 1.12-14.23) were independently associated with rehospitalization. Conclusions: Additional healthcare visits and rehospitalizations within 30 days of hospital discharge are common in patients with CAP. This is mainly due to a worsening of signs or symptoms of CAP and/or comorbid conditions. These findings may have implications for discharge planning and follow-up of patients with CAP.