Pectoralis Muscle Area as a Predictor of Mortality in Patients Hospitalized with Bronchiectasis Exacerbation.

INTRODUCTION: Data on factors related to mortality in patients with bronchiectasis exacerbation are insufficient. Computed tomography (CT) can measure the pectoralis muscle area (PMA) and is a useful tool to diagnose sarcopenia. This study aimed to evaluate whether PMA can predict mortality in patients with bronchiectasis exacerbation. METHODS: Patients hospitalized due to bronchiectasis exacerbation at a single center were retrospectively divided into survivors and non-survivors based on 1-year mortality. Thereafter, a comparison of the clinical and radiologic characteristics was conducted between the two groups. RESULTS: A total of 66 (14%) patients died at 1 year. In the multivariate analysis, age, BMI <18.4 kg/m2, sex-specific PMA quartile, ≥3 exacerbations in the previous year, serum albumin <3.5 g/dL, cystic bronchiectasis, tuberculosis-destroyed lung, and diabetes mellitus were independent predictors for the 1-year mortality in patients hospitalized with bronchiectasis exacerbation. A lower PMA was associated with a lower overall survival rate in the survival analysis according to sex-specific quartiles of PMA. PMA had the highest area under the curve during assessment of prognostic performance in predicting the 1-year mortality. The lowest sex-specific PMA quartile group exhibited higher disease severity than the highest quartile group. CONCLUSIONS: CT-derived PMA was an independent predictor of 1-year mortality in patients hospitalized with bronchiectasis exacerbation. Patients with lower PMA exhibited higher disease severity. These findings suggest that PMA might be a useful marker for providing additional information regarding prognosis of patients with bronchiectasis exacerbation.

Development and Validation of a Robust and Interpretable Early Triaging Support System for Patients Hospitalized With COVID-19: Predictive Algorithm Modeling and Interpretation Study.

BACKGROUND: Robust and accurate prediction of severity for patients with COVID-19 is crucial for patient triaging decisions. Many proposed models were prone to either high bias risk or low-to-moderate discrimination. Some also suffered from a lack of clinical interpretability and were developed based on early pandemic period data. Hence, there has been a compelling need for advancements in prediction models for better clinical applicability. OBJECTIVE: The primary objective of this study was to develop and validate a machine learning-based Robust and Interpretable Early Triaging Support (RIETS) system that predicts severity progression (involving any of the following events: intensive care unit admission, in-hospital death, mechanical ventilation required, or extracorporeal membrane oxygenation required) within 15 days upon hospitalization based on routinely available clinical and laboratory biomarkers. METHODS: We included data from 5945 hospitalized patients with COVID-19 from 19 hospitals in South Korea collected between January 2020 and August 2022. For model development and external validation, the whole data set was partitioned into 2 independent cohorts by stratified random cluster sampling according to hospital type (general and tertiary care) and geographical location (metropolitan and nonmetropolitan). Machine learning models were trained and internally validated through a cross-validation technique on the development cohort. They were externally validated using a bootstrapped sampling technique on the external validation cohort. The best-performing model was selected primarily based on the area under the receiver operating characteristic curve (AUROC), and its robustness was evaluated using bias risk assessment. For model interpretability, we used Shapley and patient clustering methods. RESULTS: Our final model, RIETS, was developed based on a deep neural network of 11 clinical and laboratory biomarkers that are readily available within the first day of hospitalization. The features predictive of severity included lactate dehydrogenase, age, absolute lymphocyte count, dyspnea, respiratory rate, diabetes mellitus, c-reactive protein, absolute neutrophil count, platelet count, white blood cell count, and saturation of peripheral oxygen. RIETS demonstrated excellent discrimination (AUROC=0.937; 95% CI 0.935-0.938) with high calibration (integrated calibration index=0.041), satisfied all the criteria of low bias risk in a risk assessment tool, and provided detailed interpretations of model parameters and patient clusters. In addition, RIETS showed potential for transportability across variant periods with its sustainable prediction on Omicron cases (AUROC=0.903, 95% CI 0.897-0.910). CONCLUSIONS: RIETS was developed and validated to assist early triaging by promptly predicting the severity of hospitalized patients with COVID-19. Its high performance with low bias risk ensures considerably reliable prediction. The use of a nationwide multicenter cohort in the model development and validation implicates generalizability. The use of routinely collected features may enable wide adaptability. Interpretations of model parameters and patients can promote clinical applicability. Together, we anticipate that RIETS will facilitate the patient triaging workflow and efficient resource allocation when incorporated into a routine clinical practice.

Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

BACKGROUND: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. OBJECTIVE: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. METHODS: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. RESULTS: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). CONCLUSIONS: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Correction: Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

[This corrects the article DOI: 10.2196/42717.].

Erratum: Correction of Affiliations in the Article "Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019".

This corrects the article on p. e413 in vol. 35, PMID: 33258333.

Feasibility of Deep Learning-Based Noise and Artifact Reduction in Coronal Reformation of Contrast-Enhanced Chest Computed Tomography.

PURPOSE: This study aimed to evaluate the feasibility of a deep learning method for imaging artifact and noise reduction in coronal reformation of contrast-enhanced chest computed tomography (CT). METHODS: A total of 19,052 coronal reformatted chest CT images of 110 CT image sets (55 pairs of concordant 16- and 320-row CT image sets) were included and used to train a deep learning algorithm for artifact and noise correction. For internal validation, 4093 coronal reformatted CT images of 25 patients from 16-row CT images underwent correction processing. For external validation, chest CT images of 30 patients (1028 coronal reformatted CT images), acquired in other institutions using different scanners, were subjected to correction processing. For both validations, image quality was compared between original ("CT origin ") and deep learning-based corrected ("CT correct ") CT images. Quantitative analysis for stair-step artifact (coefficient of variance of CT density on coronal reformation), image noise, signal-to-noise ratio, and contrast-to-noise ratio were evaluated. Subjective image quality scores were assigned for image contrast, artifact, and conspicuity of major structures. RESULTS: CT correct showed significantly reduced stair-step artifact (mean coefficient of variance: CT origin 7.35 ± 2.0 vs CT correct 5.17 ± 2.4, P < 0.001) and image noise and improved signal-to-noise ratio and contrast-to-noise ratio in the aorta, pulmonary artery, and liver, compared with those of CT origin ( P < 0.01). On subjective analysis, CT correct had higher image contrast, lower artifact, and better conspicuity than CT origin . Most results of the external validation were consistent with those obtained from the internal validation, except for those concerning the pulmonary artery. CONCLUSIONS: Deep learning-based artifact correction significantly improved the image quality of coronal reformation chest CT by reducing image noise and artifacts.

Deep Learning-Based Automatic CT Quantification of Coronavirus Disease 2019 Pneumonia: An International Collaborative Study.

OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.

Development and Validation of a Multimodal-Based Prognosis and Intervention Prediction Model for COVID-19 Patients in a Multicenter Cohort.

The ability to accurately predict the prognosis and intervention requirements for treating highly infectious diseases, such as COVID-19, can greatly support the effective management of patients, especially in resource-limited settings. The aim of the study is to develop and validate a multimodal artificial intelligence (AI) system using clinical findings, laboratory data and AI-interpreted features of chest X-rays (CXRs), and to predict the prognosis and the required interventions for patients diagnosed with COVID-19, using multi-center data. In total, 2282 real-time reverse transcriptase polymerase chain reaction-confirmed COVID-19 patients' initial clinical findings, laboratory data and CXRs were retrospectively collected from 13 medical centers in South Korea, between January 2020 and June 2021. The prognostic outcomes collected included intensive care unit (ICU) admission and in-hospital mortality. Intervention outcomes included the use of oxygen (O2) supplementation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO). A deep learning algorithm detecting 10 common CXR abnormalities (DLAD-10) was used to infer the initial CXR taken. A random forest model with a quantile classifier was used to predict the prognostic and intervention outcomes, using multimodal data. The area under the receiver operating curve (AUROC) values for the single-modal model, using clinical findings, laboratory data and the outputs from DLAD-10, were 0.742 (95% confidence interval [CI], 0.696−0.788), 0.794 (0.745−0.843) and 0.770 (0.724−0.815), respectively. The AUROC of the combined model, using clinical findings, laboratory data and DLAD-10 outputs, was significantly higher at 0.854 (0.820−0.889) than that of all other models (p < 0.001, using DeLong's test). In the order of importance, age, dyspnea, consolidation and fever were significant clinical variables for prediction. The most predictive DLAD-10 output was consolidation. We have shown that a multimodal AI model can improve the performance of predicting both the prognosis and intervention in COVID-19 patients, and this could assist in effective treatment and subsequent resource management. Further, image feature extraction using an established AI engine with well-defined clinical outputs, and combining them with different modes of clinical data, could be a useful way of creating an understandable multimodal prediction model.

Ultrasound-Guided Percutaneous Needle Biopsy for Small Pleural Lesions: Diagnostic Yield and Impact of CT and Ultrasound Characteristics.

BACKGROUND. Ultrasound (US)-guided percutaneous pleural needle biopsy (PCPNB) is widely used to evaluate pleural lesions, although its diagnostic accuracy is variable. OBJECTIVE. The purpose of this study is to assess the diagnostic yield of US-guided PCPNB for small (≤ 2 cm) pleural lesions and the impact of CT and US morphologic and technical factors. METHODS. A total of 103 patients (73 men and 30 women; mean [± SD] age, 68.0 ± 13.3 years) who underwent US-guided PCPNB of a small pleural lesion performed by a single experienced operator from July 2013 to December 2019 were retrospectively analyzed. Final diagnosis was established via histopathologic results, including findings from repeat US-guided and CT-guided biopsies as well as imaging and clinical follow-up. Pleural morphology and thickness were assessed on CT and US, and needle pathway length throughout the pleura was measured on US. Accuracy, sensitivity, specificity, PPV, and NPV were calculated. The association of diagnostic yield with imaging and technical factors was evaluated. ROC curve analysis was used to determine the optimal CT pleural thickness cutoff value. Multivariable logistic regression was performed to identify independent predictors of diagnostic yield. RESULTS. The diagnostic accuracy, sensitivity, specificity, PPV, and NPV of US-guided PCPNB were 85.4%, 84.8%, 100.0%, 100.0%, and 21.1%, respectively. Diagnostic, compared with nondiagnostic, procedures more commonly (p ≤ .002) revealed nodular morphology on CT (96.4% vs 3.6%) and US (97.3% vs 2.7%,), greater pleural thickness on CT (7.5 vs 3.2 mm) and US (7.4 vs 3.0 mm), and a greater needle pathway length (11.0 vs 6.1 mm). The optimal cutoff value for pleural thickness on CT was 4.5 mm. Diagnostic yield was 96.4% for nodular lesions, 95.0% for diffuse lesions that had a thickness of 4.5 mm or greater on CT, 55.6% for diffuse lesions that had a thickness less than 4.5 mm on CT, and 100% for diffuse lesions on CT that had nodular morphology on US. Nodular morphology on US (p = .002) and needle pathway length (p = .04) were independent predictors of diagnostic yield. CONCLUSION. US-guided PCPNB has excellent diagnostic accuracy for small pleural lesions; imaging characteristics influence this accuracy. CLINICAL IMPACT. US-guided PCPNB is highly likely diagnostic for small pleural lesions with nodular morphology on either CT or US or with a pleural thickness of 4.5 mm or greater.

Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019.

BACKGROUND: The Korean Society of Thoracic Radiology (KSTR) recently constructed a nation-wide coronavirus disease 2019 (COVID-19) database and imaging repository, referred to the Korean imaging cohort of COVID-19 (KICC-19) based on the collaborative efforts of its members. The purpose of this study was to provide a summary of the clinico-epidemiological data and imaging data of the KICC-19. METHODS: The KSTR members at 17 COVID-19 referral centers retrospectively collected imaging data and clinical information of consecutive patients with reverse transcription polymerase chain reaction-proven COVID-19 in respiratory specimens from February 2020 through May 2020 who underwent diagnostic chest computed tomography (CT) or radiograph in each participating hospital. RESULTS: The cohort consisted of 239 men and 283 women (mean age, 52.3 years; age range, 11-97 years). Of the 522 subjects, 201 (38.5%) had an underlying disease. The most common symptoms were fever (n = 292) and cough (n = 245). The 151 patients (28.9%) had lymphocytopenia, 86 had (16.5%) thrombocytopenia, and 227 patients (43.5%) had an elevated CRP at admission. The 121 (23.4%) needed nasal oxygen therapy or mechanical ventilation (n = 38; 7.3%), and 49 patients (9.4%) were admitted to an intensive care unit. Although most patients had cured, 21 patients (4.0%) died. The 465 (89.1%) subjects underwent a low to standard-dose chest CT scan at least once during hospitalization, resulting in a total of 658 CT scans. The 497 subjects (95.2%) underwent chest radiography at least once during hospitalization, which resulted in a total of 1,475 chest radiographs. CONCLUSION: The KICC-19 was successfully established and comprised of 658 CT scans and 1,475 chest radiographs of 522 hospitalized Korean COVID-19 patients. The KICC-19 will provide a more comprehensive understanding of the clinical, epidemiological, and radiologic characteristics of patients with COVID-19.

Community-Acquired Pneumonia with Negative Chest Radiography Findings: Clinical and Radiological Features.

BACKGROUND: Data regarding community-acquired pneumonia (CAP) identified on chest computed tomography (CT) but not on chest radiography (CR) are limited. OBJECTIVES: The present study aimed to investigate the clinical and radiological features of these patients. METHODS: We retrospectively compared the clinical characteristics, etiological agents, treatment outcomes, and CT findings between CAP patients with negative CR and positive CT findings (negative CR group) and those with positive CR as well as CT findings (control group). RESULTS: Of 1,925 patients, 94 patients (4.9%) were included in the negative CR group. Negative CR findings could be attributed to the location of the lesions (e.g., those located in the dependent lung) and CT pattern with a low attenuation, such as ground-glass opacity (GGO). The negative CR group was characterized by a higher frequency of aspiration pneumonia, lower incidences of complicated parapneumonic effusion or empyema and pleural drainage, and lower blood levels of inflammatory markers than the control group. On CT, the negative CR group exhibited higher rates of GGO- and bronchiolitis-predominant patterns and a lower rate of consolidation pattern. Despite shorter length of hospital stay in the negative CR group, 30-day and in-hospital mortalities were similar between the two groups. CONCLUSIONS: CAP patients with negative CR findings are characterized by lower blood levels of inflammatory markers, a higher incidence of aspiration pneumonia, and a lower incidence of complicated para-pneumonic effusion or empyema than those with positive CR findings. Chest CT scan should be considered in suspected CAP patients with a negative CR, especially in bedridden patients.

Clinical relevance of necrotizing change in patients with community-acquired pneumonia.

BACKGROUND AND OBJECTIVE: Few studies have analysed a large number of patients with necrotizing pneumonia (NP) diagnosed based on computed tomography (CT) scans. The aim of the present study was to document the incidence and clinical features of NP in patients with community-acquired pneumonia (CAP). METHODS: This retrospective study was conducted on CAP patients who had been admitted to a tertiary referral centre and who had available enhanced CT scan images. Patients were allocated into NP and non-NP groups, and they were compared with respect to various clinical variables. RESULTS: Of the 830 patients included in the present study, necrotizing change was observed in 103 patients (12%). Patients with NP experienced more symptoms of pneumonia, had higher blood levels of inflammatory markers and more often required pleural drainage compared to patients with non-NP. Although the use of mechanical ventilation, vasopressor infusion, 30-day mortality, in-hospital mortality and clinical deterioration did not differ between the NP and non-NP groups, the median length of hospital stay (LOS) was significantly longer in the NP group. Multivariate analysis using Cox proportional hazards model showed that necrotizing change independently predicted LOS in patients with CAP. CONCLUSION: NP affects approximately one-tenth of hospitalized CAP patients. It may be associated with more severe clinical manifestations and may increase the need for pleural drainage. NP was found to be an independent predictor of LOS, but not of mortality in CAP patients.

Clinical Relevance of Pleural Effusion in Patients with Pulmonary Embolism.

BACKGROUND: Data regarding pleural effusion due to pulmonary embolism (PE) are limited. OBJECTIVES: The aim of this study was to investigate the clinical characteristics of PE patients with pleural effusion caused by PE. METHODS: Patients with PE were retrospectively analyzed and divided into 2 groups based on computed tomography: a group with pleural effusion due to PE (effusion group) and a group without pleural effusion (control group). Clinical characteristics were compared between the 2 groups. RESULTS: The study population consisted of the effusion group (n = 127) and the control group (n = 651). Serum C-reactive protein (CRP) level was significantly higher in the effusion group than in the control group. The percentages of high-risk Simplified PE Severity Index (57 vs. 47%, p = 0.008), central PE (84 vs. 73%, p = 0.013), right ventricular dilation (45 vs. 36%, p = 0.053), and pulmonary infarction (40 vs. 8%, p < 0.001) were higher in the effusion group than in the control group. Multivariate analysis demonstrated that pulmonary infarction (odds ratio [OR] 6.20, 95% confidence interval [CI] 3.49-10.91, p < 0.001) and CRP level (OR 1.05, 95% CI 1.101-1.09, p = 0.023) were independent predictors of pleural effusion due to PE. The presence of pleural effusion was not a predictor of short-term outcomes or length of hospital stay. CONCLUSIONS: Patients with more severe PE are likely to have pleural effusion caused by PE. However, pleural effusion was not a proven predictor of short-term outcome or length of hospital stay. Pulmonary infarction and CRP levels were independent risk factors for the development of pleural effusion.

Risk factors for mortality in patients with septic pulmonary embolism.

Data regarding prognostic factors for patients with septic pulmonary embolism (SPE) are lacking. The purpose of the present study was to investigate the clinical features of SPE and to ascertain the risk factors for mortality in patients with this condition. Patients with SPE, whose data were retrospectively collected from a tertiary referral center in Korea, were categorized by the presence or absence of in-hospital death into two groups: death and survival groups. The two groups were compared for clinical and radiologic parameters. SPE was community-acquired in most patients (78%). The most common focus of primary infection was that of bone, joint, or soft tissue (33%), followed by liver abscess (17%). The in-hospital mortality was 12%. Multivariate analysis showed that tachypnea (odds ratio [OR] 4.73, 95% confidence interval [CI] 1.09-20.53, p = 0.038) and segmental or lobar consolidation on computed tomography (CT) scan (OR 10.79, 95% CI 2.51-46.43, p = 0.001) were independent predictors of in-hospital death in SPE patients. Taken together, the primary infectious foci of SPE in Korea are different from those reported in Western countries. Tachypnea and segmental or lobar consolidation on CT scan may be independent risk factors for in-hospital death in these patients.

Relationship Between Emphysema Severity and the Location of Lung Cancer in Patients With Chronic Obstructive Lung Disease.

OBJECTIVE: New phenotypes of chronic obstructive pulmonary disease (COPD) based on emphysema severity have been recognized recently. The purpose of this study was to determine the relationship between emphysema severity (phenotype) and lung cancer location in patients with COPD. MATERIALS AND METHODS: Four hundred patients with 405 primary lung cancers confirmed pathologically between January 2010 and March 2014 were included in the study. Of these, 193 patients received a diagnosis of COPD according to the Global Initiative for Chronic Obstructive Lung Disease guidelines. We scored emphysema severity (0-4) on thin-section CT and assigned the anatomic tumor location of lung cancer as peripheral or central. RESULTS: Patients with COPD had a higher proportion of centrally located lung cancer compared with those without COPD (36.4% vs 17.4%; p < 0.001). In patients with COPD, lower emphysema grades (odds ratio [OR], 0.69; 95% CI, 0.51-0.93; p = 0.016) and reduced ratio of forced expiratory volume in 1 second (FEV1) to forced vital capacity (FVC) (OR, 0.94; 95% CI, 0.89-0.99; p = 0.024) were associated with central location. After adjusting for age, smoking, and spirometry results, the proportion of central location was approximately four times higher in patients with lower emphysema grades (0-2, < 25%) than in those with severe grades (grade 4, > 51%). CONCLUSION: Lower emphysema grades and reduced FEV1/FVC seemed to be independent predictors of central location of lung cancer in COPD. Therefore, in patients with COPD with lower grade emphysema and airway-predominant disease, additional screening tools may have to be considered for central lung cancer detection along with thin-section CT.

Diagnostic performance of the QuantiFERON-TB Gold In-Tube assay and factors associated with nonpositive results in patients with miliary tuberculosis.

The QuantiFERON-TB Gold In-Tube (QFT-GIT) assay provides suboptimal diagnostic performance in patients with miliary tuberculosis. QFT-GIT results should be carefully interpreted, particularly in patients suspected of having miliary tuberculosis with severe lymphocytopenia or an extent of ground glass opacity (GGO) >50% on chest computed tomography (CT). Diagnostic performance of the QFT-GIT assay was evaluated in 44 patients with miliary tuberculosis. Among these individuals, 30 (68%) had true-positive QFT-GIT results. Severe lymphocytopenia and an extent of GGO >50% on chest CT were independent risk factors for nonpositive QFT-GIT results.

Diagnostic and prognostic implications of bacteremia in patients with complicated pleural infection.

Objectives: The clinical significance of bacteremia in patients with complicated pleural infection is still uncertain. We aimed to examine the incidence and clinical significance of bacteremia in patients with complicated pleural infection. Methods: This retrospective study comprised of consecutive patients who received pleural drainage due to complicated parapneumonic effusion or empyema. The clinical, laboratory, and radiologic data and clinical outcome were compared between patients with and without bacteremia. Additionally, the factors associated with overall mortality were evaluated in these patients. Results: Of 341 patients included in the analysis, 25 (7 %) had a positive blood culture. Blood culture testing added 2 % identification of causative pathogen compared to pleural fluid culture alone. By multivariable analysis, radiologic features of cavitary lesion, a RAPID score≥5, and a positive microbial culture in pleural fluid were independently associated with bacteremia. Despite these clinical distinctions, there was ultimately no significant difference in in-hospital mortality between patients with and without bacteremia (3 vs. 4 %, p=1.0). The only factor significantly associated with overall mortality among patients with complicated pleural infections was a higher RAPID score [HR=1.96 (95 % CI=1.35-2.84)]. Conclusions: The rate of bacteremia in patients with complicated pleural infection was 7 %. Blood culture testing demonstrated limited diagnostic yield and had minimal impact on clinical outcomes compared to pleural fluid culture. Therefore, it seems that blood culture testing is more advantageous for specific patients with suspected pleural infection who have cavitary lesions or a RAPID score≥5.