Made by DATEXIS (Data Science and Text-based Information Systems) at Beuth University of Applied Sciences Berlin
Deep Learning Technology: Sebastian Arnold, Betty van Aken, Paul Grundmann, Felix A. Gers and Alexander Löser. Learning Contextualized Document Representations for Healthcare Answer Retrieval. The Web Conference 2020 (WWW'20)
Funded by The Federal Ministry for Economic Affairs and Energy; Grant: 01MD19013D, Smart-MD Project, Digital Technologies
The chest x-ray is distinctive with features that appear similar to an extensive pneumonia, with both lungs showing widespread white patches. The white patches may seem to migrate from one area of the lung to another as the disease persists or progresses. Computed tomography (CT) may be used to confirm the diagnosis. Often the findings are typical enough to allow the doctor to make a diagnosis without ordering additional tests. To confirm the diagnosis, a doctor may perform a lung biopsy using a bronchoscope. Many times, a larger specimen is needed and must be removed surgically.
Plain chest radiography shows normal lung volumes, with characteristic patchy unilateral or bilateral consolidation. Small nodular opacities occur in up to 50% of patients and large nodules in 15%. On high resolution computed tomography, airspace consolidation with air bronchograms is present in more than 90% of patients, often with a lower zone predominance A subpleural or peribronchiolar distribution is noted in up to 50% of patients. Ground glass appearance or hazy opacities associated with the consolidation are detected in most patients.
Pulmonary physiology is restrictive with a reduced diffusion capacity of the lung for carbon monoxide (DCO). Airflow limitation is uncommon; gas exchange is usually abnormal and mild hypoxemia is common. Bronchoscopy with bronchoalveolar lavage reveals up to 40% lymphocytes, along with more subtle increases in neutrophils and eosinophils. In patients with typical clinical and radiographic features, a transbronchial biopsy that shows the pathologic pattern of organizing pneumonia and lacks features of an alternative diagnosis is adequate to make a tentative diagnosis and start therapy. On surgical lung biopsy, the histopathologic pattern is organizing pneumonia with preserved lung architecture; this pattern is not exclusive to BOOP and must be interpreted in the clinical context.
Histologically, cryptogenic organizing pneumonia is characterized by the presence of polypoid plugs of loose organizing connective tissue (Masson bodies) within alveolar ducts, alveoli, and bronchioles.
Respiratory diseases may be investigated by performing one or more of the following tests
- Biopsy of the lung or pleura
- Blood test
- Bronchoscopy
- Chest x-ray
- Computed tomography scan, including high-resolution computed tomography
- Culture of microorganisms from secretions such as sputum
- Ultrasound scanning can be useful to detect fluid such as pleural effusion
- Pulmonary function test
- Ventilation—perfusion scan
Respiratory disease is a common and significant cause of illness and death around the world. In the US, approximately 1 billion "common colds" occur each year. A study found that in 2010, there were approximately 6.8 million emergency department visits for respiratory disorders in the U.S. for patients under the age of 18. In 2012, respiratory conditions were the most frequent reasons for hospital stays among children.
In the UK, approximately 1 in 7 individuals are affected by some form of chronic lung disease, most commonly chronic obstructive pulmonary disease, which includes asthma, chronic bronchitis and emphysema.
Respiratory diseases (including lung cancer) are responsible for over 10% of hospitalizations and over 16% of deaths in Canada.
In 2011, respiratory disease with ventilator support accounted for 93.3% of ICU utilization in the United States.
Rare cases of BOOP have induced with lobar cicatricial atelectasis.
For some types of chILD and few forms adult ILD genetic causes have been identified. These may be identified by blood tests. For a limited number of cases this is a definite advantage, as a precise molecular diagnosis can be done; frequently then there is no need for a lung biopsy. Testing is available for
Chest radiography is usually the first test to detect interstitial lung diseases, but the chest radiograph can be normal in up to 10% of patients, especially early on the disease process.
High resolution CT of the chest is the preferred modality, and differs from routine CT of the chest. Conventional (regular) CT chest examines 7–10 mm slices obtained
at 10 mm intervals; high resolution CT examines 1-1.5 mm slices at 10 mm
intervals using a high spatial frequency reconstruction algorithm. The HRCT therefore provides approximately 10 times more resolution than the conventional CT chest, allowing the HRCT to elicit details that cannot otherwise be visualized.
Radiologic appearance alone however is not adequate and should be interpreted in the clinical context, keeping in mind the temporal profile of the disease process.
Interstitial lung diseases can be classified according to radiologic patterns.
The diagnosis can be confirmed by the characteristic appearance of the chest x-ray, which shows widespread pulmonary infiltrates, and an arterial oxygen level (PaO) that is strikingly lower than would be expected from symptoms. Gallium 67 scans are also useful in the diagnosis. They are abnormal in approximately 90% of cases and are often positive before the chest x-ray becomes abnormal. The diagnosis can be definitively confirmed by histological identification of the causative organism in sputum or bronchio-alveolar lavage (lung rinse). Staining with toluidine blue, silver stain, periodic-acid schiff stain, or an immunofluorescence assay will show the characteristic cysts. The cysts resemble crushed ping-pong balls and are present in aggregates of 2 to 8 (and not to be confused with "Histoplasma" or "Cryptococcus", which typically do not form aggregates of spores or cells). A lung biopsy would show thickened alveolar septa with fluffy eosinophilic exudate in the alveoli. Both the thickened septa and the fluffy exudate contribute to dysfunctional diffusion capacity which is characteristic of this pneumonia.
"Pneumocystis" infection can also be diagnosed by immunofluorescent or histochemical staining of the specimen, and more recently by molecular analysis of polymerase chain reaction products comparing DNA samples. Notably, simple molecular detection of "Pneumocystis jirovecii" in lung fluids does not mean that a person has "Pneumocystis" pneumonia or infection by HIV. The fungus appears to be present in healthy individuals in the general population.
Several diseases can present with similar signs and symptoms to pneumonia, such as: chronic obstructive pulmonary disease (COPD), asthma, pulmonary edema, bronchiectasis, lung cancer, and pulmonary emboli. Unlike pneumonia, asthma and COPD typically present with wheezing, pulmonary edema presents with an abnormal electrocardiogram, cancer and bronchiectasis present with a cough of longer duration, and pulmonary emboli presents with acute onset sharp chest pain and shortness of breath.
The most common organisms which cause lobar pneumonia are "Streptococcus pneumoniae", also called pneumococcus, "Haemophilus influenzae" and "Moraxella catarrhalis". "Mycobacterium tuberculosis", the tubercle bacillus, may also cause lobar pneumonia if pulmonary tuberculosis is not treated promptly.
Like other types of pneumonia, lobar pneumonia can present as community acquired, in immune suppressed patients or as nosocomial infection. However, most causative organisms are of the community acquired type.
Pathological specimens to be obtained for investigations include:
1. Sputum for culture, AAFBS and gram stain
2. Blood for full hemogram/complete blood count, ESR and other acute phase reactants
3. Procalcitonin test, more specific
The identification of the infectious organism (or other cause) is an important part of modern treatment of pneumonia. The anatomical patterns of distribution can be associated with certain organisms, and can help in selection of an antibiotic while waiting for the pathogen to be cultured.
A chest radiograph is frequently used in diagnosis. In people with mild disease, imaging is needed only in those with potential complications, those not having improved with treatment, or those in which the cause is uncertain. If a person is sufficiently sick to require hospitalization, a chest radiograph is recommended. Findings do not always match the severity of disease and do not reliably separate between bacterial infection and viral infection.
X-ray presentations of pneumonia may be classified as lobar pneumonia, bronchopneumonia (also known as lobular pneumonia), and interstitial pneumonia. Bacterial, community-acquired pneumonia classically show lung consolidation of one lung segmental lobe, which is known as lobar pneumonia. However, findings may vary, and other patterns are common in other types of pneumonia. Aspiration pneumonia may present with bilateral opacities primarily in the bases of the lungs and on the right side. Radiographs of viral pneumonia may appear normal, appear hyper-inflated, have bilateral patchy areas, or present similar to bacterial pneumonia with lobar consolidation. Radiologic findings may not be present in the early stages of the disease, especially in the presence of dehydration, or may be difficult to be interpreted in the obese or those with a history of lung disease. A CT scan can give additional information in indeterminate cases. Lung ultrasound may also be useful in helping to make the diagnosis.
The specific criteria for diagnosis of CPA are:
Chest X-rays showing one or more lung cavities. There may be a fungal ball present or not.
Symptoms lasting more than 3 months, usually including weight loss, fatigue, cough, coughing blood (haemoptysis) and breathlessness
A blood test or tissue fluid test positive for Aspergillus species
Aspergilloma
An aspergilloma is a fungal mass caused by a fungal infection with Aspergillus species that grows in either scarred lungs or in a pre-existing lung cavity, which may have been caused by a previous infection. Patients with a previous history of tuberculosis, sarcoidosis, cystic fibrosis or other lung disease are most susceptible to an aspergilloma. Aspergillomas may have no specific symptoms but in many patients there is some coughing up of blood called haemoptysis - this may be infrequent and in small quantity, but can be severe and then it requires urgent medical help.
Tests used to diagnose an aspergilloma may include:
- Chest X-ray
- Chest CT
- Sputum culture
- Bronchoscopy or bronchoscopy with lavage (BAL)
- Serum precipitins for aspergillus (blood test to detect antibodies to aspergillus)
Almost all aspergillomas are caused by "Aspergillus fumigatus". In diabetic patients it may be caused by "Aspergillus niger". It is very rarely caused by "Aspergillus flavus", "Aspergillus oryzae", "Aspergillus terreus" or "Aspergillus nidulans".
UIP may be diagnosed by a radiologist using computed tomography (CT) scan of the chest, or by a pathologist using tissue obtained by a lung biopsy. Radiologically, the main feature required for a confident diagnosis of UIP is honeycomb change in the periphery and the lower portions (bases) of the lungs. The histologic hallmarks of UIP, as seen in lung tissue under a microscope by a pathologist, are interstitial fibrosis in a "patchwork pattern", honeycomb change and fibroblast foci (see images below).
Endogenous lipoid pneumonia and non-specific interstitial pneumonitis has been seen prior to the development of pulmonary alveolar proteinosis in a child.
Aspiration pneumonia is typically diagnosed by a combination of clinical circumstances (a debilitated or neurologically impaired person), radiologic findings (an infiltrate in the proper location), and sometimes with the help of microbiologic cultures. Some cases of aspiration pneumonia are caused by aspiration of food particles or other particulate substances like pill fragments; these can be diagnosed by pathologists on lung biopsy specimens.
Eosinophilic pneumonia is diagnosed in one of three circumstances: when a complete blood count reveals increased eosinophils and a chest x-ray or computed tomography (CT) identifies abnormalities in the lung, when a biopsy identifies increased eosinophils in lung tissue, or when increased eosinophils are found in fluid obtained by a bronchoscopy (bronchoalveolar lavage [BAL] fluid). Association with medication or cancer is usually apparent after review of a person's medical history. Specific parasitic infections are diagnosed after examining a person's exposure to common parasites and performing laboratory tests to look for likely causes. If no underlying cause is found, a diagnosis of AEP or CEP is made based upon the following criteria. AEP is most likely with respiratory failure after an acute febrile illness of usually less than one week, changes in multiple areas and fluid in the area surrounding the lungs on a chest x-ray, and greater than 25% eosinophils on a BAL. Other typical laboratory abnormalities include an elevated white blood cell count, erythrocyte sedimentation rate, and immunoglobulin G level. Pulmonary function testing usually reveals a restrictive process with reduced diffusion capacity for carbon monoxide. CEP is most likely when the symptoms have been present for more than a month. Laboratory tests typical of CEP include increased blood eosinophils, a high erythrocyte sedimentation rate, iron deficiency anemia, and increased platelets. A chest x-ray can show abnormalities anywhere, but the most specific finding is increased shadow in the periphery of the lung, away from the heart.
A CT scan of the lungs and histopathology along with a history of working in the flocking industry can diagnose flock worker's lung. A differential diagnosis may also include Sjögren's syndrome and lymphoid interstitial pneumonia. Flock worker's lung may be misdiagnosed as asthma or recurrent pneumonia. Though X-rays may be abnormal, CT scans are more useful as a diagnostic tool in flock worker's lung. Other diagnostic methods may include a transbronchial biopsy or wedge biopsy.
The differential diagnosis includes other types of lung disease that cause similar symptoms and show similar abnormalities on chest radiographs. Some of these diseases cause fibrosis, scarring or honeycomb change. The most common considerations include:
- chronic hypersensitivity pneumonitis
- non-specific interstitial pneumonia
- sarcoidosis
- pulmonary Langerhans cell histiocytosis
- asbestosis
The initial investigations for suspected empyema remains chest X-ray, although it cannot differentiate an empyema from uninfected parapneumonic effusion. Ultrasound must be used to confirm the presence of a pleural fluid collection and can be used to estimate the size of the effusion, differentiate between free and loculated pleural fluid and guide thoracocentesis if necessary. Chest CT and MRI do not provide additional information in most cases and should therefore not be performed routinely. On a CT scan, empyema fluid most often has a radiodensity of about 0-20 Hounsfield units (HU), but gets over 30 HU when becoming more thickened with time.
The most often used "golden" criteria for empyema are pleural effusion with macroscopic presence of pus, a positive Gram stain or culture of pleural fluid, or a pleural fluid pH under 7.2 with normal peripheral blood pH. Clinical guidelines for adult patients therefore advocate diagnostic pleural fluid aspiration in patients with pleural effusion in association with sepsis or pneumonic illness. Because pleural effusion in the pediatric population is almost always parapneumonic and the need for chest tube drainage can be made on clinical grounds, British guidelines for the management of pleural infection in children do not recommend diagnostic pleural fluid sampling.
Blood and sputum culture has often already been performed in the setting of community acquired pneumonia needing hospitalization. It should however be noted that the micro-organism responsible for development of empyema is not necessarily the same as the organism causing the pneumonia, especially in adults. As already mentioned before, sensitivity of pleural fluid culture is generally low, often partly due to prior administration of antibiotics. It has been shown that culture yield can be increased from 44% to 69% if pleural fluid is injected into blood culture bottles (aerobic and anaerobic) immediately after aspiration. Furthermore, diagnostic rates can be improved for specific pathogens using polymerase chain reaction or antigen detection, especially for Streptococcus pneumoniae, Streptococcus pyogenes and Staphylococcus aureus. In a study including 78 children with pleural empyema, the causative micro-organism could be identified using direct culture of fresh pleural fluid in 45% of patients, with an additional 28% using PCR on pleural fluid of negative cultures. Pneumococcal antigen detection in pleural fluid samples by latex agglutination can also be useful for rapid diagnosis of pneumococcal empyema. In the previously noted study, positive and negative predictive value of pneumococcal antigen detection was 95% and 90%, respectively. However, despite the additional diagnostic value of these tests, PCR and antigen detection have limited value in determining treatment choice because of the lack of information on antibiotic resistance.
Exogenous lipid pneumonia is rare in the general population, but occupational accidents may not be uncommon in fire performers. Diagnosis is usually made on the basis of history of exposure to hydrocarbon fuels, symptoms, and radiological findings. The radiological findings are nonspecific, and the disease presents with variable patterns and distribution. For this reason, lipoid pneumonia may mimic many other diseases, and the diagnosis is often delayed.
Chest X-rays taken shortly after the accident may or may not be abnormal, but typically over time show infiltrates in the lower lobes of the lungs. High-resolution CT will frequently demonstrate abnormalities, including opacities, pleural effusion, consolidation, or pulmonary nodules. Histopathology of lung biopsy or bronchoalveolar lavage may indicate lipid-laden macrophages. Laboratory results may show highly elevated inflammatory markers.
The fibrosing pattern of NSIP has a five year survival rate of 86% to 92%, while the cellular pattern of NSIP has a 100% five year survival rate. Patients with NSIP(whether cellular or fibrosing), have a better prognosis than those with usual interstitial pneumonia (UIP).
Treatment is with corticosteroids and possibly intravenous immunoglobulins.
Chest radiographs (X-ray photographs) often show a pulmonary infection before physical signs of atypical pneumonia are observable at all.
This is occult pneumonia. In general, occult pneumonia is rather often present in patients with pneumonia and can also be caused by "Streptococcus pneumoniae", as the decrease of occult pneumonia after vaccination of children with a pneumococcal vaccine suggests.
Infiltration commonly begins in the perihilar region (where the bronchus begins) and spreads in a wedge- or fan-shaped fashion toward the periphery of the lung field. The process most often involves the lower lobe, but may affect any lobe or combination of lobes.
Fungal pneumonia can be diagnosed in a number of ways. The simplest and cheapest method is to culture the fungus from a patient's respiratory fluids. However, such tests are not only insensitive but take time to develop which is a major drawback because studies have shown that slow diagnosis of fungal pneumonia is linked to high mortality. Microscopy is another method but is also slow and imprecise. Supplementing these classical methods is the detection of antigens. This technique is significantly faster but can be less sensitive and specific than the classical methods.
A molecular test based on quantitative PCR is also available from Myconostica. Relying on DNA detection, this is the most sensitive and specific test available for fungi but it is limited to detecting only pneumocystis jirovecii and aspergillus.
Flock worker's lung can be prevented with engineering controls that protect workers from inhaling flock. Engineering controls to prevent inhalation of flock can include using guillotine cutters rather than rotary cutters, and ensuring that blades are sharp, since dull blades shear off more respirable particles. Flocking plants have also implemented medical surveillance programs for workers to diagnose cases at an earlier stage. Another technique for preventing flock worker's lung is cleaning the workplace with alternatives to compressed air in order to avoid resuspending particulates in the air.
Some CAP patients require intensive care, with clinical prediction rules such as the pneumonia severity index and CURB-65 guiding the decision to hospitalize. Factors increasing the need for hospitalization include:
- Age greater than 65
- Underlying chronic illnesses
- Respiratory rate greater than 30 per minute
- Systolic blood pressure less than 90 mmHg
- Heart rate greater than 125 per minute
- Temperature below 35 or over 40 °C
- Confusion
- Evidence of infection outside the lung
Laboratory results indicating hospitalization include:
- Arterial oxygen tension less than 60 mm Hg
- Carbon dioxide over 50 mmHg or pH under 7.35 while breathing room air
- Hematocrit under 30 percent
- Creatinine over 1.2 mg/dl or blood urea nitrogen over 20 mg/dl
- White-blood-cell count under 4 × 10^9/L or over 30 × 10^9/L
- Neutrophil count under 1 x 10^9/L
X-ray findings indicating hospitalization include:
- Involvement of more than one lobe of the lung
- Presence of a cavity
- Pleural effusion