Search

Hyperhydration is characterized by increased quantity and altered distribution of body fluids. Fluid overload is frequently found in critically ill patients with acute kidney injury (AKI) and in heart failure patients and is associated with adverse outcomes. Although physical examination is still the first choice for the assessment of the hydration state, it is imprecise and often unreliable. Nowadays novel techniques are employed, sometimes together, in a comprehensive assessment strategy previously proposed as the “5B” approach: body weight changes, blood volume online monitoring, bioimpedance spectroscopy (BIS), B-natriuretic peptide, and body ultrasound (US), which includes inferior vena cava (IVC) diameter measure and lung US (LUS). The modern LUS has extended its field of clinical application from cardiology and intensive care setting to hemodialysis patients since the clinical evaluation alone has proven to be rather imprecise in estimating the correct “dry weight.” B-line detection by LUS has recently been confirmed to be superior in sensitivity to clinical signs of fluid overload such as lung crackles and peripheral edema. Furthermore, LUS has shown a greater predictive power for hydration-related cardiovascular morbidity and mortality than NYHA score or echocardiography. Based on evidence, LUS can be considered a valid diagnostic and prognostic tool for pulmonary congestion measurement in both extracorporeal and peritoneal dialysis patients.

A 9-year-old previously healthy, fully immunized female is seen in the pediatrician’s office for a 3 day history of fevers to 102 °F, cough, and right-sided abdominal pain. On examination, she has a temperature of 38.6 °C, heart rate of 120 beats per minute, respiratory rate of 20 breaths per minute, and oxygen saturations of 94% on room air. She is mildly ill-appearing, with crackles over the right lung base noted on auscultation. The remainder of her exam is benign. She is clinically diagnosed with right lower lobe community-acquired pneumonia (CAP). A 10-day course of oral amoxicillin is prescribed. Two days later, she is seen in the emergency department for persistent fevers, now up to 104 °F, worsening dyspnea, chest pain, abdominal pain, and vomiting. A chest x-ray at this time reveals a right lower lobe pneumonia with a large pleural effusion. She is admitted to the hospital for management of complicated CAP and treated with intravenous ampicillin. The pleural fluid is drained and sent to the microbiology lab for diagnostic evaluation. PCR of the pleural fluid is positive for Streptococcus pneumoniae, the most common cause of bacterial CAP. She continues receiving intravenous ampicillin during her hospital stay. By day 5, she has been afebrile for over 24 hours, tolerating oral intake, and has no supplemental oxygen requirement. She is discharged home to complete a course of oral amoxicillin for treatment of complicated CAP.

Community-acquired pneumonia is an infection of the small airways and pulmonary parenchyma that develops in the outpatient setting. Despite the development of new antibiotics and vaccines, pneumonia is still a disease that occurs frequently in children under 5 years of age and is one of the main causes of mortality, especially in developing countries. The biggest challenge in treating pneumonia is to determine the agent, which depends on age, disease severity, immunological condition, geographic location, epidemiological situation, and immunizations. The classic clinical picture presents with fever, coughing, and difficulty in breathing. The physical examination shows tachypnea, reduced breath sounds, and fine crackles. Wheezing may be present in infants with viral pneumonia. The chest X-ray is considered an important tool to confirm the disease diagnosis and may guide specific treatment. Acute-phase reactants have a low sensitivity and specificity to distinguish between virus and bacteria. Microbiological identification does not have a clinical impact for most children with community-acquired pneumonia. Bronchoalveolar lavage may be considered for immunocompromised patients. Antibiotic treatment is empirical based on the best possible etiology, depending on the patient’s age and epidemiological timing. Amoxicillin is the treatment of choice for Streptococcus pneumoniae, and azithromycin is preferred for Mycoplasma pneumoniae.

This study presents a pilot investigation for lung sounds with 3 data collected from a published library recorded by electronic stethoscope. By using the tool of spectrogram with the Gaussian window which the variance number is tuned, the sound data were analyzed. The feature of the lung sound which the frequencies ranged from 0 to 800 Hz, contain 2 part, the high frequencies and low frequencies. In normal breath, the high and low frequencies are alternated and differed 300 Hz. In the disease related to bronchi, crackles or some high frequency bulbs will be occurred. The sound pattern can be analyzed easier with the 3D surface presentation rather than the 2D cross-sectional image.

A 71-year-old male presents to his primary care physician with an 8-week history of cough with intermittent blood-tinged sputum. He denies fevers or sick contacts. However, he notes a 20-pound weight loss in the last 3 months and feeling more fatigued. He has a 40-pack-year smoking history. He previously worked as a welder in a shipyard for 30 years before retiring 5 years ago. His past medical history only includes hypertension. Breath sounds are equal without crackles. Cardiac exam also reveals a regular rate and rhythm. His blood pressure is 120/80 mmHg, and heart rate is 88/min. An initial chest x-ray reveals a mass in the right hilar region measuring 3.1 cm × 3.5 cm.

Interstitial (diffuse) lung diseases in infants and children comprise a rare heterogeneous group of parenchymal lung disorders, with clinical syndromes characterized by dyspnea, tachypnea, crackles, and hypoxemia. They arise from a wide spectrum of developmental, genetic, inflammatory, infectious, and reactive disorders. In the past, there has been a paucity of information and limited understanding regarding their pathogenesis, natural history, imaging findings, and histopathologic features, which often resulted in enormous diagnostic challenges and confusion. In recent years, there has been a substantial improvement in the understanding of interstitial lung disease in pediatric patients due to the development of a structured classification system based on the etiology of the lung disease, established pathologic criteria for consistent diagnosis, and the improvement of thoracoscopic techniques for lung biopsy. Imaging plays an important role in evaluating interstitial lung diseases in infants and children by confirming and characterizing the disorder, generating differential diagnoses, and providing localization for lung biopsy for pathological diagnosis. In this chapter, the authors present the epidemiology, challenges, and uncertainties of diagnosis and amplify a recently developed classification system for interstitial lung disease in infants and children with clinical, imaging, and pathological correlation.

The present study reports a case of a young male patient, 22 years old, with a previous diagnosis of Hodgkin’s lymphoma who presented for two weeks with dyspnea complaints with minimum efforts, a continuous chest pain on pressure, dysphagia, sporadic palpitations, and dry cough with fever episodes not measured. Physical exam revealed presence of fever, bibasal pulmonary crackles in respiratory auscultation, increased jugular venous pulse, and hypotension associated with paradoxical pulse, and hypotension associated with paradoxical pulse were found. No more pathological finding was noticed.

Crackles are intermittent, nonmusical, and brief adventitious lung sounds that can be heard on inspiration and sometimes during expiration. They are classified as fine or coarse depending on their frequency and duration; fine crackles have high frequency and short duration, whereas coarse crackles have lower frequency and longer duration. They are generated when air is forced through abnormally narrowed respiratory passages. The study of lung sounds, in general, and crackles, in particular, has advanced rapidly in the last two decades, thanks to the contribution of evolving technology. Based on various methods of artificial intelligence, researchers have managed to effectively detect and analyze lung sound signals and characterize them objectively. Unfortunately, the diagnostic utility of these high-end methods in clinical settings is still limited. In this review we attempt to summarize what is known about crackles and, in addition, discuss in less detail some of the other less common adventitious lung sounds.

In this paper, we propose a novel architecture called noise masking recurrent neural network (NMRNN) for lung sound classification. The model jointly learns to extract only important respiratory-like frames without redundant noise and then by exploiting this information is trained to classify lung sounds into four categories: normal, containing wheezes, crackles and both wheezes and crackles. We compare the performance of our model with machine learning based models. As a result, the NMRNN model reaches state-of-the-art performance on recently introduced publicly available respiratory sound database.

Respiratory sounds are composed by normal and adventitious respiratory sounds which comprise the sounds heard over the trachea/mouth and chest wall. All sounds can be described using frequency, intensity, and timbre. Frequency and intensity are perceived by human beings as pitch and loudness, respectively. Timbre allows the differentiation between two sounds with the same frequency and intensity. For respiratory sounds, some additional information is often informative, such as the timing within the respiratory cycle in which the sound occurs, the sound duration, and the influence of gravity/forced expiratory maneuvers on the sound. It is also important to know the origin and mechanisms of the respiratory sound. Normal and adventitious respiratory sounds can be highly informative about a person’s respiratory health as it is known that their characteristics change with gender, location where it is heard, body size, body position, and airflow, being particularly different between children and adults and in the presence of a respiratory condition. This chapter provides a comprehensive understanding of the use of normal and adventitious respiratory sounds for identifying respiratory conditions and their severity and monitoring respiratory interventions.

Respiratory medicine relies both on clinical information and on complementary, laboratory tests results. However, despite today’s technological wonders, a proper history and a sound physical examination have no substitute as the initial step in making a correct diagnosis and, by consequence, providing the appropriate treatment. Respiratory complaints are frequently the cause that brings a patient to the doctor, and the respiratory system is the most commonly affected organ system in clinical practice. Consequently, respiratory sounds, either heard at a distance or auscultated over the chest, are integral to the evaluation of patients and may provide valuable clues. This chapter focuses on lung sounds as they are reported by patients (or by their guardians in the case of young children) and as a sign noted on chest auscultation performed with the stethoscope. The characteristics and the pathogenesis of adventitious breath sounds (stridor, wheeze, crackles, squawk) are briefly addressed and their clinical usefulness is discussed; voice-transmitted sounds and noisy breathing (grunt, snuffle, rattle, snore) are also presented. The four clinical cases included at the end of this chapter highlight the value of the proper understanding of breath sounds.

Three days after arriving for a ski vacation in Vail, Colorado, 15-year-old Bodie’s headache had become so severe that he had to go to the ER. Bodie had come from Long Island hoping to enjoy a week of skiing with his family during his school break. He had been having a mild cough several weeks prior, but it had not been severe enough to address. His headache started a day after arriving in Vail that steadily worsened, accompanied by nausea and a decreased appetite. Bodie tried taking both acetaminophen and ibuprofen without any effect on his headache. Bodie presented to the ER with a normal heart rate, breathing rate, and blood pressure. However, his blood-oxygen saturation level was only 82%—far below normal. When listening to his lungs, crackles could be heard on the lower right side. While the crackles could suggest pneumonia or pulmonary edema from heart failure, both were unlikely in a generally healthy 15-year-old. The key to understanding Bodie’s strange symptoms is to appreciate one particular detail of his trip—Bodie lives essentially at sea level on Long Island but traveled without time for acclimation to the high altitude in the Colorado Rockies. Ideally, the duration of spring break would allow several days at a medium elevation prior to transitioning to the highest elevation. Vail’s base elevation is 8120 ft above sea level, and the summit is at 11,570 ft. Bodie was diagnosed with Acute Mountain Sickness (AMS) and High-Altitude Pulmonary Edema (HAPE). As a result of not being accustomed to the thinner air in Colorado, Bodie’s lungs were filling with fluid .

A 67-year-old woman with mild Alzheimer’s disease who has a 2-day history of productive cough, fever, and increased confusion is transferred from a nursing home to the emergency department. According to the transfer records, she has had no recent hospitalizations or recent use of antibiotic agents. Her temperature is 38.4°C (101°F), the blood pressure is 145/85 mm Hg, the respiratory rate is 30 breaths per minute, the heart rate is 120 beats per minute, and the oxygen saturation is 91% while she is breathing ambient air. Crackles are heard in both lower lung fields. She is oriented to person only. The white-cell count is 4000 per cubic millimeter, the serum sodium level is 130 mmol per liter, and the blood urea nitrogen is 25 mg per deciliter (9.0 mmol per liter). A radiograph of the chest shows infiltrates in both lower lobes. How and where should this patient be treated?

Heart failure (HF) can be defined as an abnormality of cardiac structure or function leading to failure of the heart to deliver oxygen at a rate commensurate with the requirements of the metabolizing tissues, despite normal filling pressures (or only at the expense of increased filling pressures) [1]. HF can be also defined, clinically, as a syndrome in which patients have typical symptoms (e.g. breathlessness, ankle swelling, and fatigue) and signs (e.g. elevated jugular venous pressure, pulmonary crackles, and displaced apex beat) resulting from an abnormality of cardiac structure or function. The diagnosis of HF, according to the guidelines of the European Society of Cardiology, can be difficult and is based on a criterion of clinical evaluation, which relies on the clinical history, physical examination and appropriate investigations [2]. For this reason is more important the need to obtain objective evidence of a structural or functional cardiac abnormality that is thought to account for the patient’s symptoms and signs, to secure the diagnosis of HF.

Recently, imaging of discontinuous adventitious sounds (DAS) has been proposed to help diagnose of pulmonary diseases where automated recognition of DAS becomes relevant. To form a DAS image (DAS-I), previous efforts have combined the independent component analysis (ICA) with time variant autoregressive modeling (TVAR) to isolate and count crackles from multichannel lung sound recordings. The present study focuses on the semiautomatic selection of independent components (ICs) associated with DAS in contrast with the manual selection which was previously reported. Mutual information between the extracted ICs is calculated to form ICs clusters; afterwards, to select ICs containing mainly DAS the average kurtosis values of each cluster were used. The proposed methodology was applied to simulated lung sound and real cases. The results showed that the ICA-TVAR method combined with the semiautomatic selection via mutual information and kurtosis is promising to imaging DAS. These images could complement the classical pulmonary auscultation provided by a pneumologist making available the location and number of DAS fundamental to diagnose pulmonary diseases.

A computer aided diagnostic system capable of analyzing respiratory sounds can be very helpful in detection of pneumonia, asthma and tuberculosis as the Respiratory sound signal carries information about the underlying physiology of the lungs and is used to detect presence of adventitious lung sounds which are an indication of disease. Respiratory sound analysis helps in distinguishing normal respiratory sounds from abnormal respiratory sounds and this can be used to accurately diagnose respiratory diseases as is done by a medical specialist via auscultation. This process has subjective nature and that is why simple auscultation cannot be relied upon.In this paper we present a novel method for automated detection of crackles and bronchial breath sounds which when coupled together indicate presence and severity of Pneumonia. The proposed system consists of four modules i.e., pre-processing in which noise is filtered out, followed by feature extraction. The proposed system then performs classification to separate crackles and bronchial breath sounds from normal breath sounds.