Introduction: Chest X-rays (CXR) are routinely used to diagnose lung and heart conditions. AI based Bone suppression imaging (BSI) aims to enhance accuracy in identifying chest anomalies by eliminating bony structures such as the ribs, clavicles, and scapula from CXRs. The aim of this retrospective study was to assess the clinical value of BSI in detecting pneumonia.
Methods: Ninety-nine emergency patients with suspected pneumonia underwent erect postero-anterior CXRs. The BSI processing system was used to generate corresponding bone-suppressed images for the 99 radiographs. Each patient had undergone a computed tomography (CT) examination within 48 h, considered the standard of reference. Two blinded readers separately analyzed images, indicating confidence levels regarding signs of pneumonia for each lung separated in three fields, first with standard images, then with BSI. Sensitivity, specificity, predictive values, and readers' certitude were calculated, and inter-reader agreement was evaluated with the kappa statistic.
Results: Out of the 99 included cases, 39 cases of pneumonia were diagnosed (39.4%). Of the remaining 60 patients, 14 presented only pleural effusions (14.1%). BSI images led to a significant increase in false positives (+251%) and significantly affected one reader's diagnosis and certitude, decreasing accuracy (up to 17%) and specificity (up to 14%). Sensitivity increased by 66% with BSI. Inter-reader agreement ranged from weak to moderate (0.113-0.53) and did not improve with BSI. For both readers, BSI images were read with significantly lesser certitude than standard images.
Conclusion: BSI did not add clinical value in pneumonia detection on CXR due to a significant increase in false positive results and a decrease one readers' certitude.
Implication For Practice: The study emphasizes the importance of proper clinical training before implementing new post-processing and artificial intelligence (AI) tools in clinical practice.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.radi.2024.09.050 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Technical advances in laboratory diagnosis of bloodstream infections.
Expert Rev Mol Diagn
January 2025
Hebei Provincial Center for Clinical Laboratories, Shijiazhuang, China, the Second Hospital of Hebei Medical University, Shijiazhuang, Hebei Province, People's Republic of China.
Introduction: Rapid and accurate laboratory diagnosis is essential for the effective treatment of bloodstream infection (BSI).
Areas Covered: This review aims to address novel and traditional approaches that exhibit different performance characteristics in the diagnosis of BSI. In particular, the authors will discuss the pros and cons of the blood culture-based phenotypic methods, nucleic acid-targeted molecular methods, and host response-targeted biomarker detection in the diagnosis of BSI.
Clinical and imaging characteristics of 135 cases of infectious sacroiliitis: a retrospective cohort study in China.
Clin Rheumatol
January 2025
Department of Rheumatology and Immunology, The First Medical Center, People Liberation Army General Hospital, Beijing, 100853, China.
To study the clinical, imaging, and computed tomography (CT)-guided biopsy pathology of patients with infectious sacroiliitis (ISI). We retrospectively analysed 135 patients diagnosed with ISI between 2008 and 2020, comprehensively evaluating clinical characteristics, laboratory test outcomes, pathological examination results, and magnetic resonance images (MRI). Among the 135 patients with ISI, 90 (66.
View Article and Find Full Text PDFImpact of reporting rapid susceptibility results in Gram negative bloodstream infections: a real world prospective study.
Eur J Clin Microbiol Infect Dis
January 2025
Laboratory of Medical Microbiology, Ghent University Hospital, Ghent, Belgium.
Purpose: Mortality and morbidity of patients with bloodstream infection (BSI) remain high despite advances in diagnostic methods and efforts to speed up reporting. This study investigated the impact of reporting rapid Minimum Inhibitory Concentration (MIC)-results in Gram negative BSIs with the ASTar system (Q-linea, Uppsala, Sweden) on the adaptation of empirically started antimicrobial therapy. We performed a real-world study during which antimicrobial susceptibility testing (AST) results were instantly reported to the treating physician in an established multidisciplinary antimicrobial stewardship setting.
View Article and Find Full Text PDFImpact of Multidrug-Resistant Bacteria in a Cohort of COVID-19 Critically Ill Patients: Data from a Prospective Observational Study Conducted in a High-Antimicrobial-Resistance-Prevalence Center.
J Clin Med
January 2025
Department of Surgical Sciences, University of Turin, 10126 Turin, Italy.
: Bacterial superinfections are common complications during viral infections, but the impact of multidrug-resistant (MDR) pathogens in critically ill patients affected by coronavirus disease 2019 (COVID-19) is still debated. : This is an observational, monocentric, and prospective study designed to investigate the incidence, risk factors, and outcomes of MDR bacterial superinfections in COVID-19 patients admitted to the intensive care unit (ICU). : A high incidence of superinfections (66%, 159/241) was observed: ventilator-associated pneumonia (VAP) (65%, 104/159) and bloodstream infection (BSI, 32%, 51/159) were the most common.
View Article and Find Full Text PDFBloodstream Infections in Critical Care Units in England, April 2017 to March 2023: Results from the First Six Years of a National Surveillance Programme.
Microorganisms
January 2025
UK Health Security Agency, London E14 4PU, UK.
Background: Patients in critical care units (CCUs) are at an increased risk of bloodstream infections (BSIs), which can be associated with central vascular catheters (CVCs). This study describes BSIs, CVC-BSIs, organism distribution, percentage of antimicrobial resistant (AMR) organisms, and case fatality rates (CFRs) over the first six years of a voluntary national CCU surveillance programme in England.
Methods: Surveillance data on BSIs, CVCs, and bed-days between 04/2017 and 03/2023 for adult CCUs were linked to mortality and AMR data, and crude rates were calculated.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!