Current Diagnostic Techniques for Pneumonia: A Scoping Review

Abstract

Community-acquired pneumonia is one of the most lethal infectious diseases, especially for infants and the elderly. Given the variety of causative agents, the accurate early detection of pneumonia is an active research area. To the best of our knowledge, scoping reviews on diagnostic techniques for pneumonia are lacking. In this scoping review, three major electronic databases were searched and the resulting research was screened. We categorized these diagnostic techniques into four classes (i.e., lab-based methods, imaging-based techniques, acoustic-based techniques, and physiological-measurement-based techniques) and summarized their recent applications. Major research has been skewed towards imaging-based techniques, especially after COVID-19. Currently, chest X-rays and blood tests are the most common tools in the clinical setting to establish a diagnosis; however, there is a need to look for safe, non-invasive, and more rapid techniques for diagnosis. Recently, some non-invasive techniques based on wearable sensors achieved reasonable diagnostic accuracy that could open a new chapter for future applications. Consequently, further research and technology development are still needed for pneumonia diagnosis using non-invasive physiological parameters to attain a better point of care for pneumonia patients.

Keywords: COVID-19; community-acquired pneumonia; diagnostic radiography; medical diagnosis; non-invasive measurements.

Figure 1

Classification of pneumonia according to the site of infection contraction.

Figure 2

Number of journal publications in the major databases for the selected keywords for the defined time range.

Figure 3

Number of papers for each technique included in the study.

Figure 4

PRISMA 2020 flow diagram for selection of articles for the proposed scoping review. * IEEE Xplore, PubMed, and Science Direct, respectively. ** Duplicate records removed using EndNote Web 20.

Figure 5

Pneumonia diagnostic methods.

Figure 6

Possible lab-based tests for different causative agents, adapted from A. Torres et al. [18].

Figure 7

(a) Normal lung CXR images. (b) Pneumonia-infected lung CXR images taken from RSNA dataset. Bottom: CXR images of normal lungs, bacterial pneumonia, and viral pneumonia from left to right (c–e), taken from Kaggle, the open-access dataset [30,31].

Figure 8

Reprinted: This shows the four types of lines found in LUS images. A lines are shown in blue; B lines are yellow; C line is shown in red; and the pleural line is green [33].

Figure 9

Number of selected studies in the given period. There was a surge in research containing the keyword pneumonia in 2020, and the trend continued after this point. This could be explained as being related to the COVID-19 pandemic.

Figure 10

Technique-wise distribution of the number of selected papers for the time when research related to pneumonia had a surge. Radiology-based techniques were the most researched.

Figure 11

Categorical distribution of selected papers on radiology for the three years after the outbreak of COVID-19.

Figure 12

The methodologies employed for diagnosing pneumonia using radiographic images. Advancements in deep learning and machine learning have been a fundamental reason for targeting images.