Effectiveness of COVID-19 Vaccines Over Time Against Clinical and Radiologic Outcomes Related to Severe SARS-CoV-2 Infection.

Background The impact of waning vaccine effectiveness on the severity of COVID-19-related findings discovered with radiologic examinations remains underexplored. Purpose To evaluate the effectiveness of vaccines over time against severe clinical and radiologic outcomes related to SARS-CoV-2 infections. Materials and Methods This multicenter retrospective study included patients in the Korean Imaging Cohort of COVID-19 database who were hospitalized for COVID-19 between June 2021 and December 2022. Patients who had received at least one dose of a SARS-CoV-2 vaccine were categorized based on the time elapsed between diagnosis and their last vaccination. Adjusted multivariable logistic regression analysis was used to estimate vaccine effectiveness against a composite of severe clinical outcomes (invasive ventilation, extracorporeal membrane oxygenation, or in-hospital death) and severe radiologic pneumonia (≥25% of lung involvement), and odds ratios (ORs) were compared between patients vaccinated within 90 days of diagnosis and those vaccinated more than 90 days before diagnosis. Results Of 4196 patients with COVID-19 (mean age, 66 years ± 17 [SD]; 2132 [51%] women, 2064 [49%] men), the ratio of severe pneumonia since their most recent vaccination was as follows: 90 days or less, 18% (277 of 1527); between 91 and 120 days, 22% (172 of 783); between 121 and 180 days, 27% (274 of 1032); between 181 and 240 days, 32% (159 of 496); and more than 240 days, 31% (110 of 358). Patients vaccinated more than 240 days before diagnosis showed increased odds of severe clinical outcomes compared with patients vaccinated within 90 days (OR = 1.94 [95% CI: 1.16, 3.24]; P = .01). Similarly, patients vaccinated more than 240 days before diagnosis showed increased odds of severe pneumonia on chest radiographs compared with patients vaccinated within 90 days (OR = 1.65 [95% CI: 1.13, 2.40]; P = .009). No difference in odds of severe clinical outcomes (P = .13 to P = .68) or severe pneumonia (P = .15 to P = .86) were observed between patients vaccinated 91-240 days before diagnosis and those vaccinated within 90 days of diagnosis. Conclusion Vaccine effectiveness against severe clinical outcomes and severe pneumonia related to SARS-CoV-2 infection gradually declined, with increased odds of both observed in patients vaccinated more than 240 days before diagnosis. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Wells in this issue.

Deep Learning for Estimating Lung Capacity on Chest Radiographs Predicts Survival in Idiopathic Pulmonary Fibrosis.

Background Total lung capacity (TLC) has been estimated with use of chest radiographs based on time-consuming methods, such as planimetric techniques and manual measurements. Purpose To develop a deep learning-based, multidimensional model capable of estimating TLC from chest radiographs and demographic variables and validate its technical performance and clinical utility with use of multicenter retrospective data sets. Materials and Methods A deep learning model was pretrained with use of 50 000 consecutive chest CT scans performed between January 2015 and June 2017. The model was fine-tuned on 3523 pairs of posteroanterior chest radiographs and plethysmographic TLC measurements from consecutive patients who underwent pulmonary function testing on the same day. The model was tested with multicenter retrospective data sets from two tertiary care centers and one community hospital, including (a) an external test set 1 (n = 207) and external test set 2 (n = 216) for technical performance and (b) patients with idiopathic pulmonary fibrosis (n = 217) for clinical utility. Technical performance was evaluated with use of various agreement measures, and clinical utility was assessed in terms of the prognostic value for overall survival with use of multivariable Cox regression. Results The mean absolute difference and within-subject SD between observed and estimated TLC were 0.69 L and 0.73 L, respectively, in the external test set 1 (161 men; median age, 70 years [IQR: 61-76 years]) and 0.52 L and 0.53 L in the external test set 2 (113 men; median age, 63 years [IQR: 51-70 years]). In patients with idiopathic pulmonary fibrosis (145 men; median age, 67 years [IQR: 61-73 years]), greater estimated TLC percentage was associated with lower mortality risk (adjusted hazard ratio, 0.97 per percent; 95% CI: 0.95, 0.98; P < .001). Conclusion A fully automatic, deep learning-based model estimated total lung capacity from chest radiographs, and the model predicted survival in idiopathic pulmonary fibrosis. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Sorkness in this issue.

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.].

Diagnostic effect of artificial intelligence solution for referable thoracic abnormalities on chest radiography: a multicenter respiratory outpatient diagnostic cohort study.

OBJECTIVES: We aim ed to evaluate a commercial artificial intelligence (AI) solution on a multicenter cohort of chest radiographs and to compare physicians' ability to detect and localize referable thoracic abnormalities with and without AI assistance. METHODS: In this retrospective diagnostic cohort study, we investigated 6,006 consecutive patients who underwent both chest radiography and CT. We evaluated a commercially available AI solution intended to facilitate the detection of three chest abnormalities (nodule/masses, consolidation, and pneumothorax) against a reference standard to measure its diagnostic performance. Moreover, twelve physicians, including thoracic radiologists, board-certified radiologists, radiology residents, and pulmonologists, assessed a dataset of 230 randomly sampled chest radiographic images. The images were reviewed twice per physician, with and without AI, with a 4-week washout period. We measured the impact of AI assistance on observer's AUC, sensitivity, specificity, and the area under the alternative free-response ROC (AUAFROC). RESULTS: In the entire set (n = 6,006), the AI solution showed average sensitivity, specificity, and AUC of 0.885, 0.723, and 0.867, respectively. In the test dataset (n = 230), the average AUC and AUAFROC across observers significantly increased with AI assistance (from 0.861 to 0.886; p = 0.003 and from 0.797 to 0.822; p = 0.003, respectively). CONCLUSIONS: The diagnostic performance of the AI solution was found to be acceptable for the images from respiratory outpatient clinics. The diagnostic performance of physicians marginally improved with the use of AI solutions. Further evaluation of AI assistance for chest radiographs using a prospective design is required to prove the efficacy of AI assistance. KEY POINTS: • AI assistance for chest radiographs marginally improved physicians' performance in detecting and localizing referable thoracic abnormalities on chest radiographs. • The detection or localization of referable thoracic abnormalities by pulmonologists and radiology residents improved with the use of AI assistance.

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 Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs.

BACKGROUND: Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. METHODS: We developed a deep learning-based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. RESULTS: DLAD demonstrated classification performance of 0.977-1.000 and localization performance of 0.973-1.000. Sensitivities and specificities for classification were 94.3%-100% and 91.1%-100% using the high-sensitivity cutoff and 84.1%-99.0% and 99.1%-100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746-0.971) and localization (0.993 vs 0.664-0.925) compared to all groups of physicians. CONCLUSIONS: Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.

Development and Validation of Deep Learning-based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs.

Purpose To develop and validate a deep learning-based automatic detection algorithm (DLAD) for malignant pulmonary nodules on chest radiographs and to compare its performance with physicians including thoracic radiologists. Materials and Methods For this retrospective study, DLAD was developed by using 43 292 chest radiographs (normal radiograph-to-nodule radiograph ratio, 34 067:9225) in 34 676 patients (healthy-to-nodule ratio, 30 784:3892; 19 230 men [mean age, 52.8 years; age range, 18-99 years]; 15 446 women [mean age, 52.3 years; age range, 18-98 years]) obtained between 2010 and 2015, which were labeled and partially annotated by 13 board-certified radiologists, in a convolutional neural network. Radiograph classification and nodule detection performances of DLAD were validated by using one internal and four external data sets from three South Korean hospitals and one U.S. hospital. For internal and external validation, radiograph classification and nodule detection performances of DLAD were evaluated by using the area under the receiver operating characteristic curve (AUROC) and jackknife alternative free-response receiver-operating characteristic (JAFROC) figure of merit (FOM), respectively. An observer performance test involving 18 physicians, including nine board-certified radiologists, was conducted by using one of the four external validation data sets. Performances of DLAD, physicians, and physicians assisted with DLAD were evaluated and compared. Results According to one internal and four external validation data sets, radiograph classification and nodule detection performances of DLAD were a range of 0.92-0.99 (AUROC) and 0.831-0.924 (JAFROC FOM), respectively. DLAD showed a higher AUROC and JAFROC FOM at the observer performance test than 17 of 18 and 15 of 18 physicians, respectively (P < .05), and all physicians showed improved nodule detection performances with DLAD (mean JAFROC FOM improvement, 0.043; range, 0.006-0.190; P < .05). Conclusion This deep learning-based automatic detection algorithm outperformed physicians in radiograph classification and nodule detection performance for malignant pulmonary nodules on chest radiographs, and it enhanced physicians' performances when used as a second reader. © RSNA, 2018 Online supplemental material is available for this article.

Association between dental health and obstructive coronary artery disease: an observational study.

BACKGROUND: The association between dental health and coronary artery disease (CAD) remains a topic of debate. This study aimed to investigate the association between dental health and obstructive CAD using multiple dental indices. METHODS: Eighty-eight patients (mean age: 65 years, 86% male) were prospectively enrolled before undergoing coronary CT angiography (n = 52) or invasive coronary angiography (n = 36). Obstructive CAD was defined as luminal stenosis of ≥50% for the left main coronary artery or ≥ 70% for the other epicardial coronary arteries. All patients underwent thorough dental examinations to evaluate 7 dental health indices, including the sum of decayed and filled teeth, the ratio of no restoration, the community periodontal index of treatment needs, clinical attachment loss, the total dental index, the panoramic topography index, and number of lost teeth. RESULTS: Forty patients (45.4%) had obstructive CAD. Among the 7 dental health indices, only the number of lost teeth was significantly associated with obstructive CAD, with patients who had obstructive CAD having significantly more lost teeth than patients without obstructive CAD (13.08 ± 10.4 vs. 5.44 ± 5.74, p < 0.001). The number of lost teeth was correlated with the number of obstructed coronary arteries (p < 0.001). Multiple binary logistic regression analysis revealed that having ≥10 lost teeth was independently associated with the presence of obstructive CAD (odds ratio: 8.02, 95% confidence interval: 1.80-35.64; p = 0.006). CONCLUSIONS: Tooth loss was associated with the presence of obstructive CAD in patients undergoing coronary evaluation. Larger longitudinal studies are needed to determine whether there is a causal relationship between tooth loss and CAD.

Coronary artery assessment using self-navigated free-breathing radial whole-heart magnetic resonance angiography in patients with congenital heart disease.

OBJECTIVES: To evaluate a self-navigated free-breathing three-dimensional (SNFB3D) radial whole-heart MRA technique for assessment of main coronary arteries (CAs) and side branches in patients with congenital heart disease (CHD). METHODS: SNFB3D-MRA datasets of 109 patients (20.1±11.8 years) were included. Three readers assessed the depiction of CA segments, diagnostic confidence in determining CA dominance, overall image quality and the ability to freeze cardiac and respiratory motion. Vessel sharpness was quantitatively measured. RESULTS: The percentages of cases with excellent CA depiction were as follows (mean score): left main, 92.6 % (1.92); left anterior descending (LAD), 88.3 % (1.88); right (RCA), 87.8 % (1.85); left circumflex, 82.8 % (1.82); posterior descending, 50.2 % (1.50) and first diagonal, 39.8 % (1.39). High diagnostic confidence for the assessment of CA dominance was achieved in 56.2 % of MRA examinations (mean score, 1.56). Cardiac motion freezing (mean score, 2.18; Pearson's r=0.73, P<0.029) affected image quality more than respiratory motion freezing (mean score, 2.20; r=0.58, P<0.029). Mean quantitative vessel sharpness of the internal thoracic artery, RCA and LAD were 53.1, 52.5 and 48.7 %, respectively. CONCLUSIONS: Most SNFB3D-MRA examinations allow for excellent depiction of the main CAs in young CHD patients; visualisation of side branches remains limited. KEY POINTS: • Self-navigated free-breathing three-dimensional magnetic resonance angiography (SNFB3D-MRA) sufficiently visualises coronary arteries (CAs). • Depiction of main CAs in patients with congenital heart disease is excellent. • Visualisation of CA side branches using SNFB3D-MRA is limited. • SNFB3D-MRA image quality is especially correlated to cardiac motion freezing ability.

The regional association between bronchiectasis and lung cancer in chest CT.

BACKGROUND: Limited studies have examined the association between lung cancer and bronchiectasis (BE). This study evaluated the regional association between BE and lung cancer by analyzing the lobar location of lung cancer in patients with underlying BE. METHODS: This clustered multi-level study enrolled patients who had underlying BE and were newly diagnosed with lung cancer between January 1, 2010 and May 30, 2013 in two referral hospitals in South Korea. By analyzing the presence of lung cancer and underlying BE as event variables at the level of lung lobes on chest computed tomography (CT), we evaluated the association of BE and lung cancer by the locations of the diseases. RESULTS: Eighty-one patients with BE and combined lung cancer were enrolled. Within 486 lung lobes of the patients, combined BE and lung cancer in the same lobe was found in 11 lobes (2.3 %). Using the general estimating equation assuming BE as a risk factor of lung cancer, the results indicated that the prevalence of lung cancer was significantly lower in the lobes with pre-existing BE (ß = -1.09, p-value = 0.001). CONCLUSIONS: Regionally, pre-existing BE was associated with a lower risk of the occurrence of lung cancer in the same lobe.

Computed tomography guided percutaneous injection of a mixture of lipiodol and methylene blue in rabbit lungs: evaluation of localization ability for video-assisted thoracoscopic surgery.

Preoperative localization is necessary prior to video assisted thoracoscopic surgery for the detection of small or deeply located lung nodules. We compared the localization ability of a mixture of lipiodol and methylene blue (MLM) (0.6 mL, 1:5) to methylene blue (0.5 mL) in rabbit lungs. CT-guided percutaneous injections were performed in 21 subjects with MLM and methylene blue. We measured the extent of staining on freshly excised lung and evaluated the subjective localization ability with 4 point scales at 6 and 24 hr after injections. For MLM, radio-opacity was evaluated on the fluoroscopy. We considered score 2 (acceptable) or 3 (excellent) as appropriate for localization. The staining extent of MLM was significantly smaller than methylene blue (0.6 vs 1.0 cm, P<0.001). MLM showed superior staining ability over methylene blue (2.8 vs 2.2, P=0.010). Excellent staining was achieved in 17 subjects (81%) with MLM and 8 (38%) with methylene blue (P=0.011). An acceptable or excellent radio-opacity of MLM was found in 13 subjects (62%). An appropriate localization rate of MLM was 100% with the use of the directly visible ability and radio-opacity of MLM. MLM provides a superior pulmonary localization ability over methylene blue.

Diffusing capacity as an independent predictor of acute exacerbations in chronic obstructive pulmonary disease.

A weak correlation between diffusing capacity of the lung for carbon monoxide (DLCO) and emphysema has been reported. This study investigated whether impaired DLCO in chronic obstructive pulmonary disease (COPD) is associated with increased risk of acute exacerbation independent of the presence or extent of emphysema. This retrospective cohort study included patients with COPD between January 2004 and December 2019. The participants were divided into four groups based on visually detected emphysema and impaired DLCO. Among 597 patients with COPD, 8.5% had no emphysema and impaired DLCO whereas 36.3% had emphysema without impaired DLCO. Among the four groups, patients with impaired DLCO and emphysema showed a higher risk of moderate-to-severe or severe exacerbation than those with normal DLCO. Impaired DLCO was an independent risk factor for severe exacerbation (hazard ratio, 1.524 [95% confidence interval 1.121-2.072]), whereas the presence of emphysema was not. The risk of moderate-to-severe or severe exacerbation increases with the severity of impaired DLCO. After propensity-score matching for the extent of emphysema, impaired DLCO was significantly associated with a higher risk of moderate-to-severe (p = 0.041) or severe exacerbation (p = 0.020). In patients with COPD and heterogeneous parenchymal abnormalities, DLCO can be considered an independent biomarker of acute exacerbation.

Acute Exacerbation and Longitudinal Lung Function Change of Preserved Ratio Impaired Spirometry.

Background: Preserved ratio impaired spirometry (PRISm) is a heterogeneous disease entity. Limited data are available regarding its prevalence, clinical course, or prognosis. We aimed to evaluate the longitudinal clinical course of patients with PRISm compared with chronic obstructive pulmonary disease (COPD). Methods: A retrospective study enrolled PRISm and COPD patients who underwent chest computed tomography and longitudinal pulmonary function tests between January 2013 and December 2020. We compared the incidence of acute exacerbations and lung function changes between PRISm and COPD patients. Results: Of the 623 patients, 40 and 583 had PRISm and COPD, respectively. Compared to COPD patients, PRISm patients were younger, more likely to be female and have a history of tuberculosis, and less likely to be smokers. They also had less severe comorbidities, lower forced vital capacity (FVC) and diffusing capacity of the lungs for carbon monoxide (DLCO). The clinical course was not significantly different between the PRISm and COPD patients in terms of the risk of moderate-to-severe acute exacerbations or proportion of frequent exacerbators. During follow-up, PRISm patients had a significantly slower annual decline of forced expiratory volume in 1 second, FVC, and DLCO than COPD patients. Conclusion: PRISm patients had no significant difference in the risk of acute exacerbations, but a significantly slower decline of lung function during longitudinal follow-up, compared with COPD patients.

Automatic Mechanical Ventilation vs Manual Bag Ventilation During CPR: A Pilot Randomized Controlled Trial.

BACKGROUND: There is insufficient evidence supporting the theory that mechanical ventilation can replace the manual ventilation method during CPR. RESEARCH QUESTION: Is using automatic mechanical ventilation (MV) feasible and comparable to the manual ventilation method during CPR? STUDY DESIGN AND METHODS: This pilot randomized controlled trial compared MV and manual bag ventilation (BV) during CPR after out-of-hospital cardiac arrest (OHCA). Patients with medical OHCA arriving at the ED were randomly assigned to two groups: an MV group using a mechanical ventilator and a BV group using a bag valve mask. Primary outcome was any return of spontaneous circulation (ROSC). Secondary outcomes were changes of arterial blood gas analysis results during CPR. Tidal volume, minute volume, and peak airway pressure were also analyzed. RESULTS: A total of 60 patients were enrolled, and 30 patients were randomly assigned to each group. There were no statistically significant differences in basic characteristics of OHCA patients between the two groups. The rate of any return of spontaneous circulation was 56.7% in the MV group and 43.3% in the BV group, indicating no significant (P = .439) difference between the two groups. There were also no statistically significant differences in changes of PH, Pco2, Po2, bicarbonate, or lactate levels during CPR between the two groups (P values = .798, 0.249, .515, .876, and .878, respectively). Significantly lower tidal volume (P < .001) and minute volume (P = .009) were observed in the MV group. INTERPRETATION: In this pilot trial, the use of MV instead of BV during CPR was feasible and could serve as a viable alternative. A multicenter randomized controlled trial is needed to create sufficient evidence for ventilation guidelines during CPR. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov; No.: NCT05550454; URL: www. CLINICALTRIALS: gov.

Preoperative computed tomography of the chest in lung cancer patients: the predictive value of calcified lymph nodes for the perioperative outcomes of video-assisted thoracoscopic surgery lobectomy.

OBJECTIVES: To determine the predictive value of identifying calcified lymph nodes (LNs) for the perioperative outcomes of video-assisted thoracoscopic surgery (VATS). METHODS: Fifty-six consecutive patients who underwent VATS lobectomy for lung cancer were included. We evaluated the number and location of calcified LNs on computed tomography (CT). We investigated clinical parameters, including percentage forced expiratory volume in 1 s (FEV1%), surgery duration, chest tube indwelling duration, and length of hospital stay. We performed linear regression analysis and multiple comparisons of perioperative outcomes. RESULTS: Mean number of calcified LNs per patient was 0.9 (range, 0-6), mostly located in the hilar-interlobar zone (43.8 %). For surgery duration (mean, 5.0 h), FEV1% and emphysema severity were independent predictors (P = 0.010 and 0.003, respectively). The number of calcified LNs was an independent predictor for chest tube indwelling duration (P = 0.030) and length of hospital stay (P = 0.046). Mean duration of chest tube indwelling and hospital stay was 8.8 days and 12.7 days in no calcified LN group; 9.2 and 13.2 in 1 calcified LN group; 12.8 and 19.7 in ≥2 calcified LNs group, respectively. CONCLUSIONS: The presence of calcified LNs on CT can help predict more complicated perioperative course following VATS lobectomy.

[Expert Opinion Questionnaire About Chest CT Scan Using A Negative Pressure Isolation Strecher in COVID-19 Patients: Image Quality and Infection Risk]. / COVID-19 환자에서 음압격리들것을 이용한 흉부 CT 검사에 대한 ì „ë¬¸ê°€ 의견 설문: 영상품질과 감염위험.

Purpose: To survey perceptions of certified physicians on the protocol of chest CT in patients with coronavirus (COVID-19) using a negative pressure isolation stretcher (NPIS). Materials and Methods: This study collected questionnaire responses from a total of 27 certified physicians who had previously performed chest CT with NPIS in COVID-19 isolation hospitals. Results: The nine surveyed hospitals performed an average of 116 chest CT examinations with NPIS each year. Of these, an average of 24 cases (21%) were contrast chest CT. Of the 9 pulmonologists we surveyed, 5 (56%) agreed that patients who showed abnormalities in serum D-dimer required contrast chest CT. All 9 surveyed radiologists agreed that the image quality of the chest CT with NPIS was sufficient for CT image interpretation regarding pneumonia or pulmonary embolism. Furthermore, in our 9 surveyed infectionologists, 5 (56%) agreed that a risk of secondary infection in the CT room after temporary opening of NPIS could be prevented through a process of disinfection. Conclusion: Experienced physicians considered that the effects of NIPS on chest CT image quality was minimal in patients with COVID-19, and the risk of CT room contamination was easily controlled.

Chest Radiography of Tuberculosis: Determination of Activity Using Deep Learning Algorithm.

BACKGROUND: Inactive or old, healed tuberculosis (TB) on chest radiograph (CR) is often found in high TB incidence countries, and to avoid unnecessary evaluation and medication, differentiation from active TB is important. This study develops a deep learning (DL) model to estimate activity in a single chest radiographic analysis. METHODS: A total of 3,824 active TB CRs from 511 individuals and 2,277 inactive TB CRs from 558 individuals were retrospectively collected. A pretrained convolutional neural network was fine-tuned to classify active and inactive TB. The model was pretrained with 8,964 pneumonia and 8,525 normal cases from the National Institute of Health (NIH) dataset. During the pretraining phase, the DL model learns the following tasks: pneumonia vs. normal, pneumonia vs. active TB, and active TB vs. normal. The performance of the DL model was validated using three external datasets. Receiver operating characteristic analyses were performed to evaluate the diagnostic performance to determine active TB by DL model and radiologists. Sensitivities and specificities for determining active TB were evaluated for both the DL model and radiologists. RESULTS: The performance of the DL model showed area under the curve (AUC) values of 0.980 in internal validation, and 0.815 and 0.887 in external validation. The AUC values for the DL model, thoracic radiologist, and general radiologist, evaluated using one of the external validation datasets, were 0.815, 0.871, and 0.811, respectively. CONCLUSION: This DL-based algorithm showed potential as an effective diagnostic tool to identify TB activity, and could be useful for the follow-up of patients with inactive TB in high TB burden countries.

Machine learning-based prediction of in-ICU mortality in pneumonia patients.

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO2/FiO2 ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Establishment and characterization of BMC-PDC-019: a novel patient-derived cell line of EGFR-mutant pulmonary adenocarcinoma transformed into small-cell lung cancer.

Transformed small-cell lung cancer (tSCLC) from EGFR-mutant adenocarcinoma is a rare and aggressive form of lung cancer that can occur when the tumor develops resistance to EGFR targeted therapy and the cancer cells acquire additional genomic alterations that cause them to transform into SCLC. Treatment for tSCLC has not been established yet, and chemotherapy regimens for de novo SCLC are mostly recommended. However, these treatments showed disappointing outcome, and novel anti-cancer agents and immunological approaches are currently being developed. The patient-derived cell line is a critical tool for pre-clinical and translational research, but cell line models for tSCLC are not publicly available from cell banks. The aim of this study was to establish and characterize a novel cell line for tSCLC. Using a lymph-node biopsy tissue from a 58-year-old female patient, whose tumor was EGFR-mutant lung adenocarcinoma progressed on afatinib, we successfully established a cell line, named BMC-PDC-019. The tumor sample and cell line showed a typical expression of SCLC markers, such as CD56 and synaptophysin. The population doubling-time of BMC-PDC-019 cells was 48 h. We examined a range of proliferation-inhibiting effects of anti-cancer drugs currently used for de novo SCLC, using BMC-PDC-019 cells. We concluded that BMC-PDC-019 would be a useful tool for pre-clinical and translational research.