Evaluating Efficiency and Adherence in Asian Lung Cancer Screening: Comparing Self-paid and Clinical Study Approaches in Taiwan.

RATIONALE AND OBJECTIVES: This study aimed to assess how different screening methods, specifically self-paid screening versus participation in clinical studies, affect screening efficiency and adherence in a real-world Asian lung cancer screening population. MATERIALS AND METHODS: This study collected 4166 participants from our hospital imaging database who underwent baseline low-dose computed tomography (LDCT) between January 2014 and August 2021. Adherence status was determined by counting CT scans, with one check indicating non-adherence and two or more checks indicating adherence. The primary objective was to investigate adherence to LDCT follow-up schedules among individuals with baseline pure ground-glass nodules (GGNs) based on different screening settings and to evaluate adherence status and CT follow-up clinical profiles. RESULTS: Of the 4166 participants in the study, 3619 in the self-paid group and 547 in the clinical study group were men, with an average follow-up period of 4.5 years. Significant differences were observed in the proportions of Lung-RADS 4 lesions, subsolid nodules, and pure GGN lesions between the self-paid and clinical trial groups. A significant difference was found in adherence rates between the self-paid screening group (60.5%) and the clinical study group (84.8%) (p < 0.001). Adherence status rates significantly increased with larger GGN sizes across categories (p < 0.001). Multivariate logistic regression revealed that age (odds ratio [OR], 1.025; p = 0.012), smoking habits (OR, 1.744; p = 0.036), and clinical study screening type (OR, 3.097; p < 0.001) significantly influenced the adherence status. CONCLUSION: The disparities in Asian lung cancer screening emphasize the need for increased efficacy, public awareness, and culturally sensitive approaches to mitigate overdiagnosis and enhance adherence among self-paying groups.

LASSO-derived model for the prediction of lean-non-alcoholic fatty liver disease in examinees attending a routine health check-up.

BACKGROUND: Lean individuals with non-alcohol fatty liver disease (NAFLD) often have normal body size but abnormal visceral fat. Therefore, an alternative to body mass index should be considered for prediction of lean-NAFLD. This study aimed to use representative visceral fat links with other laboratory parameters using the least absolute shrinkage and selection operator (LASSO) method to construct a predictive model for lean-NAFLD. METHODS: This retrospective cross-sectional analysis enrolled 2325 subjects with BMI < 24 kg/m2 from medical records of 51,271 examinees who underwent a routine health check-up. They were randomly divided into training and validation cohorts at a ratio of 1:1. The LASSO-derived prediction model used LASSO regression to select 23 clinical and laboratory factors. The discrimination and calibration abilities were evaluated using the Hosmer-Lemeshow test and calibration curves. The performance of the LASSO model was compared with the fatty liver index (FLI) model. RESULTS: The LASSO-derived model included four variables-visceral fat, triglyceride levels, HDL-C-C levels, and waist hip ratio-and demonstrated superior performance in predicting lean-NAFLD with high discriminatory ability (AUC, 0.8416; 95% CI: 0.811-0.872) that was comparable with the FLI model. Using a cut-off of 0.1484, moderate sensitivity (75.69%) and specificity (79.86%), as well as high negative predictive value (95.9%), were achieved in the LASSO model. In addition, with normal WC subgroup analysis, the LASSO model exhibits a trend of higher accuracy compared to FLI (cut-off 15.45). CONCLUSIONS: We developed a LASSO-derived predictive model with the potential for use as an alternative tool for predicting lean-NAFLD in clinical settings.

Researchers developed a model to predict a type of liver disease called non-alcoholic fatty liver disease (NAFLD) in lean individuals.The model accurately detects NAFLD in lean individuals using factors like visceral fat, triglyceride levels, and waist-to-hip ratio, aiding in identifying the disease in normal-weight people with abnormal fat distribution.

Eplerenone improves hyperglycemia and sympathetic excitation in chronic renocardiac syndrome in rats.

We aimed to assess the efficacy of eplerenone, a steroidal mineralocorticoid receptor antagonist known to reduce blood pressure and mitigate cardiovascular disease (CVD) progression, in retarding the progression of chronic kidney disease (CKD) and CVD in a rat model of type 4 cardiorenal syndrome (CRS). We grouped rats into four experimental categories: sham surgery, sham treatment with eplerenone, nephrectomy without eplerenone (Nx), and nephrectomy with eplerenone (Nx + EP). For the Nx + EP group, rats received five-sixths nephrectomy, inducing CKD and CVD conditions such as renal hypertension and hyperglycemia, and were then treated with eplerenone (100 mg/kg/day, orally) over 4 weeks after an initial 4-week observation period. Heart rate, blood pressure, blood sugar levels, and sympathetic nerve excitation were monitored biweekly. In addition, assessments of renal and cardiac tissues, including evaluation of renal tubulointerstitial injury, glomerular injury, and cardiomyocyte hypertrophy, were conducted at week 8. Eplerenone administration mitigated CKD and CVD progression in the Nx + EP group, evident by improved blood pressure (217.3 ± 5.4 versus 175.3 ± 5.6), blood sugar (121.8 ± 1.3 versus 145.6 ± 6.0) level, reduced sympathetic nerve excitation, and cardiomyocyte hypertrophy compared to the Nx group. However, renal tubulointerstitial injury, glomerular injury, and cardiovascular dysfunction, which were increased in rats with type 4 CRS, did not show significant changes with eplerenone treatment. Our study demonstrated that eplerenone treatment did not exacerbate type 4 CRS but improved blood pressure, blood sugar levels, sympathetic nerve excitation, and cardiomyocyte hypertrophy in this model.

Impact of Voxel Normalization on a Machine Learning-Based Method: A Study on Pulmonary Nodule Malignancy Diagnosis Using Low-Dose Computed Tomography (LDCT).

Lung cancer (LC) stands as the foremost cause of cancer-related fatality rates worldwide. Early diagnosis significantly enhances patient survival rate. Nowadays, low-dose computed tomography (LDCT) is widely employed on the chest as a tool for large-scale lung cancer screening. Nonetheless, a large amount of chest radiographs creates an onerous burden for radiologists. Some computer-aided diagnostic (CAD) tools can provide insight to the use of medical images for diagnosis and can augment diagnostic speed. However, due to the variation in the parameter settings across different patients, substantial discrepancies in image voxels persist. We found that different voxel sizes can create a compromise between model generalization and diagnostic efficacy. This study investigates the performance disparities of diagnostic models trained on original images and LDCT images reconstructed to different voxel sizes while making isotropic. We examined the ability of our method to differentiate between benign and malignant nodules. Using 11 features, a support vector machine (SVM) was trained on LDCT images using an isotropic voxel with a side length of 1.5 mm for 225 patients in-house. The result yields a favorable model performance with an accuracy of 0.9596 and an area under the receiver operating characteristic curve (ROC/AUC) of 0.9855. In addition, to furnish CAD tools for clinical application, future research including LDCT images from multi-centers is encouraged.

Managing Persistent Subsolid Nodules in Lung Cancer: Education, Decision Making, and Impact of Interval Growth Patterns.

With the popularization of lung cancer screening, many persistent subsolid nodules (SSNs) have been identified clinically, especially in Asian non-smokers. However, many studies have found that SSNs exhibit heterogeneous growth trends during long-term follow ups. This article adopted a narrative approach to extensively review the available literature on the topic to explore the definitions, rationale, and clinical application of different interval growths of subsolid pulmonary nodule management and follow-up strategies. The development of SSN growth thresholds with different growth patterns could support clinical decision making with follow-up guidelines to reduce over- and delayed diagnoses. In conclusion, using different SSN growth thresholds could optimize the follow-up management and clinical decision making of SSNs in lung cancer screening programs. This could further reduce the lung cancer mortality rate and potential harm from overdiagnosis and over management.

Gender Differences in Subclinical Coronary Atherosclerosis in the Asian Population With a Coronary Artery Calcium Score of Zero.

There is little evidence on whether gender difference influences the incidence of subclinical coronary atherosclerosis in Asian populations with a 0 score. In this study, we investigated the influence of age and gender on the extent of subclinical coronary atherosclerotic burden within a healthy Asian population with a 0 coronary artery calcium (CAC) score. A total of 934 participants (320 women and 614 men) from Taiwan's Han Chinese population with an initial CAC score of 0 were included in this study. They underwent 2 consecutive cardiac computed tomography scans over a clinical follow-up period of 4.35 ± 2.37 years. Clinical information and laboratory measurements were collected for analysis. Compared with the female group, the male group demonstrated significantly higher rates of subclinical CAC progression (27.4% vs 13.8%, p <0.001). Across the age group deciles (≤40, 41 to 50, 51 to 60, ≥61 years), the male group had a higher prevalence of subclinical CAC progression than the female group. For the subclinical CAC progression, the logistic regression model demonstrated that age, gender (male gender), cholesterol level, and follow-up period were statistically significant parameters. In conclusion, these findings support that a gender difference impacts the long-term natural course of subclinical coronary calcification conversion in women compared with men, suggesting that the gender-based effect on coronary CAC conversion plays an important role in subclinical coronary atherosclerosis risk stratification in personalized preventive medicine.

Corrigendum: Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan.

[This corrects the article DOI: 10.3389/fonc.2023.1105100.].

Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan.

Purpose: To compare the diagnostic performance of radiomic analysis with machine learning (ML) model with a convolutional neural network (CNN) in differentiating thymic epithelial tumors (TETs) from other prevascular mediastinal tumors (PMTs). Methods: A retrospective study was performed in patients with PMTs and undergoing surgical resection or biopsy in National Cheng Kung University Hospital, Tainan, Taiwan, E-Da Hospital, Kaohsiung, Taiwan, and Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan between January 2010 and December 2019. Clinical data including age, sex, myasthenia gravis (MG) symptoms and pathologic diagnosis were collected. The datasets were divided into UECT (unenhanced computed tomography) and CECT (enhanced computed tomography) for analysis and modelling. Radiomics model and 3D CNN model were used to differentiate TETs from non-TET PMTs (including cyst, malignant germ cell tumor, lymphoma and teratoma). The macro F1-score and receiver operating characteristic (ROC) analysis were performed to evaluate the prediction models. Result: In the UECT dataset, there were 297 patients with TETs and 79 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 83.95%, ROC-AUC = 0.9117) had better performance than the 3D CNN model (macro F1-score = 75.54%, ROC-AUC = 0.9015). In the CECT dataset, there were 296 patients with TETs and 77 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 85.65%, ROC-AUC = 0.9464) had better performance than the 3D CNN model (macro F1-score = 81.01%, ROC-AUC = 0.9275). Conclusion: Our study revealed that the individualized prediction model integrating clinical information and radiomic features using machine learning demonstrated better predictive performance in the differentiation of TETs from other PMTs at chest CT scan than 3D CNN model.

Prediction of Interval Growth of Lung Adenocarcinomas Manifesting as Persistent Subsolid Nodules ≤3 cm Based on Radiomic Features.

RATIONALES AND OBJECTIVES: To investigate the prognostic value of the radiomic-based prediction model in predicting the interval growth rate of persistent subsolid nodules (SSNs) with an initial size of ≤ 3 cm manifesting as lung adenocarcinomas. MATERIALS AND METHODS: A total of 133 patients (mean age, 59.02 years; male, 37.6%) with 133 SSNs who underwent a series of CT examinations at our hospital between 2012 and 2022 were included in this study. Forty-one radiomic features were extracted from each volumetric region of interest. Radiomic features combined with conventional clinical and semantic parameters were then selected for radiomic-based model building. To investigate the model performance in terms of substantial SSN growth and stage shift growth, the model performance was compared by the area under the curve (AUC) obtained by receiver operating characteristic analysis. RESULTS: The mean follow-up period was 3.62 years. For substantial SSN growth, a radiomic-based model (Model 2) based on clinical characteristics, CT semantic features, and radiomic features yielded an AUCs of 0.869 (95% CI: 0.799-0.922). In comparison with Model 1 (clinical characteristics and CT semantic features), Model 2 performed better than Model 1 for substantial SSN growth (AUC model 1:0.793 versus AUC model 2:0.869, p = 0.028). A radiomic-based nomogram combining sex, follow-up period, and three radiomic features was built for substantial SSN growth prediction. For the stage shift growth, a radiomic-based model (Model 4) based on clinical characteristics, CT semantic features, and radiomic features yielded an AUCs of 0.883 (95% CI: 0.815-0.933). Compared with Model 3 (clinical characteristics and CT semantic features), Model 4 performed better than the model 3 for stage shift growth (AUC model 1: 0.769 versus AUC model 2: 0.883, p = 0.006). A radiomic-based nomogram combining the initial nodule size, SSN classification, follow-up period, and three radiomic features was built to predict the stage shift growth. CONCLUSION: Radiomic-based models have superior utility in estimating the prognostic interval growth of patients with early lung adenocarcinomas (≤ 3 cm) than conventional clinical-semantic models in terms of substantial interval growth and stage shift growth, potentially guiding clinical decision-making with follow-up strategies of SSNs in personalized precision medicine.

An integrated nomogram combined semantic-radiomic features to predict invasive pulmonary adenocarcinomas in subjects with persistent subsolid nodules.

Background: Patients with persistent pulmonary subsolid nodules have a relatively high incidence of lung adenocarcinoma. Preoperative early diagnosis of invasive pulmonary adenocarcinoma spectrum lesions could help avoid extensive advanced cancer management and overdiagnosis in lung cancer screening programs. Methods: In total, 260 consecutive patients with persistent subsolid nodules ≤30 mm (n=260) confirmed by surgical pathology were retrospectively investigated from February 2016 to August 2020 at the Kaohsiung Veterans General Hospital. All patients underwent surgical resection within 3 months of the chest CT exam. The study subjects were divided into a training cohort (N=195) and a validation cohort (N=65) at a ratio of 3:1. The purpose of our study was to develop and validate a least absolute shrinkage and selection operator-derived nomogram integrating semantic-radiomic features in differentiating preinvasive and invasive pulmonary adenocarcinoma lesions, and compare its predictive value with clinical-semantic, semantic, and radiologist's performance. Results: In the training cohort of 195 subsolid nodules, 106 invasive lesions and 89 preinvasive lesions were identified. We developed a least absolute shrinkage and selection operator-derived combined nomogram prediction model based on six predictors (nodular size, CTR, roundness, GLCM_Entropy_log10, HISTO_Entropy_log10, and CONVENTIONAL_Humean) to predict the invasive pulmonary adenocarcinoma lesions. Compared with other predictive models, the least absolute shrinkage and selection operator-derived model showed better diagnostic performance with an area under the curve of 0.957 (95% CI: 0.918 to 0.981) for detecting invasive pulmonary adenocarcinoma lesions with balanced sensitivity (92.45%) and specificity (88.64%). The results of Hosmer-Lemeshow test showed P values of 0.394 and 0.787 in the training and validation cohorts, respectively, indicating good calibration power. Conclusions: We developed a least absolute shrinkage and selection operator-derived model integrating semantic-radiomic features with good calibration. This nomogram may help physicians to identify invasive pulmonary adenocarcinoma lesions for guidance in personalized medicine and make more informed decisions on managing subsolid nodules.

Psychometric properties and measurement invariance of Short-Form Life Attitude Inventory for hospital staff.

BACKGROUND: The life attitude of health care workers can deeply influence the quality of care. Examining the performance of the Short-Form Life Attitude Inventory (SF-LAI), this study analyzes the factorial structure, reliability, and invariance of the revised SF-LAI across genders and professions among the staff of a teaching medical center. METHODS: The SF-LAI was developed for university students in Taiwan. From January to February 2019, we administered a cross-sectional survey of life attitudes by distributing the SF-LAI to all staff members of a medical center in Taiwan. The construct validity was evaluated using a confirmatory factor analysis (CFA). Model fit was assessed in terms of the comparative fit index (CFI), Tucker-Lewis index (TFI), standardized root mean square residual (SRMR), and root mean square of error of approximation (RMSEA). Internal consistency was calculated using Cronbach's alpha and McDonald's omega. We also performed the CFA invariance analysis for the SF-LAI-R across genders and professions (physician, nurse and other hospital staff). RESULTS: Of 884 (24.62%) responses, 835 were valid. The participants had a mean age of 47.8 years, and 20.12% were male. In a comparison of multiple CFAs, a second-order model with six factors outperformed other models. The goodness of fit indices revealed the CFI was 0.955, TFI was 0.952, RMSEA was 0.071, and SRMR was 0.038. The Cronbach's alphas, McDonald's omega coefficients for internal consistency were all greater than 0.8. The first and second-order model had metric and scalar invariance across genders and professions. CONCLUSIONS: As health care demands evolve, humanities are becoming more important in medical education. Life attitude of hospital care worker is a crucial indicator of whether one embodies the ideals of a humanistic education. The revised SF-LAI has acceptable structural validity, internal consistency, and invariance across genders and professions among staff members of a teaching medical center.

The Associations among Gender, Age, eHealth Literacy, Beliefs about Medicines and Medication Adherence among Elementary and Secondary School Teachers.

Background: A lack of health literacy may negatively impact patient adherence behavior in health care delivery, leading to a major threat to individual health and wellbeing and an increasing financial burden on national healthcare systems. Therefore, how to cultivate citizens' health literacy, especially electronic health (eHealth) literacy that is closely related to the Internet, may be seen as a way to reduce the financial burden of the national healthcare systems, which is the responsibility of every citizen. However, previous studies on medication adherence have mostly been conducted with chronic disease patient samples rather than normal samples. Teachers are not only the main body of school health efforts, but also role models for students' healthy behavior. Therefore, understanding differences in eHealth literacy beliefs among schoolteachers would be helpful for improving the existing health promoting programs and merit specific research. Aims: The present study identified the relationships among gender, age, electronic health (eHealth) literacy, beliefs about medicines, and medication adherence among elementary and secondary school teachers. Methods: A total of 485 teachers aged 22−51 years completed a pen-and-paper questionnaire. The instruments included an eHealth literacy scale, a belief about medicines scale and a medication adherence scale. Results: The results showed a significant difference between genders in necessity beliefs about medication (t = 2.00, p < 0.05), and a significant difference between ages in functional eHealth literacy (F = 3.18, p < 0.05) and in necessity beliefs about medication (Welch = 7.63, p < 0.01). Moreover, age (ß = 0.09), functional eHealth literacy (ß = 0.12), and necessity beliefs about medication (ß = 0.11) positively predicted medication adherence, while concerns about medication (ß = −0.23) negatively predicted medication adherence. Conclusions: The results showed that male teachers had stronger concerns about medication than female teachers. Teachers aged 42−51 years had lower functional eHealth literacy and stronger necessity beliefs about medication than teachers aged 22−31 years. In addition, teachers who were older, had higher functional eHealth literacy, had stronger necessity beliefs about medication, and had fewer concerns about medication tended to take their medications as prescribed. These findings revealed that helping teachers develop high eHealth literacy and positive beliefs about medicines is an effective strategy for improving medication adherence.

Radiomics in Early Lung Cancer Diagnosis: From Diagnosis to Clinical Decision Support and Education.

Lung cancer is the most frequent cause of cancer-related death around the world. With the recent introduction of low-dose lung computed tomography for lung cancer screening, there has been an increasing number of smoking- and non-smoking-related lung cancer cases worldwide that are manifesting with subsolid nodules, especially in Asian populations. However, the pros and cons of lung cancer screening also follow the implementation of lung cancer screening programs. Here, we review the literature related to radiomics for early lung cancer diagnosis. There are four main radiomics applications: the classification of lung nodules as being malignant/benign; determining the degree of invasiveness of the lung adenocarcinoma; histopathologic subtyping; and prognostication in lung cancer prediction models. In conclusion, radiomics offers great potential to improve diagnosis and personalized risk stratification in early lung cancer diagnosis through patient-doctor cooperation and shared decision making.

Impact of Smoking Status on Lung Cancer Characteristics and Mortality Rates between Screened and Non-Screened Lung Cancer Cohorts: Real-World Knowledge Translation and Education.

This was a retrospective hospital-based cohort study of participants diagnosed with lung cancer in the lung cancer register database, and our goal was to evaluate the impact of smoking and screening status on lung cancer characteristics and clinical outcomes. According to the hospital-based lung cancer register database, a total of 2883 lung cancers were diagnosed in 2883 patients between January 2007 and September 2017, which were divided into four groups according to smoking and screening status. A comparison was performed in terms of clinical characteristics and outcomes of lung cancer between the four groups. For non-smokers, age, gender, screened status, tumor size, targeted therapy, and curative surgery were independent prognostic factors of overall survival for lung cancer subjects. However, screened status and gender were not significant prognostic factors for lung cancer survival in smokers with lung cancer. For the non-smoker group, about 4.9% of lung cancer subjects (N = 81) were detected by screening. However, only 0.97% of lung cancer subjects (N = 12) were detected by screening in smokers. This could be attributed to smokers' negative attitudes and low socioeconomic status preventing LDCT lung cancer screening. In summary, our real-world data suggest that effectively encouraging smokers to be more willing to participate in lung cancer screening programs with screening allowance and educational training in the future is an important issue.

Impact of low-dose computed tomography for lung cancer screening on lung cancer surgical volume: The urgent need in health workforce education and training.

ABSTRACT: This study aimed to investigate the time trend variation in the surgical volume and prognostic outcome of patients with lung cancer after the gradual prolonged implementation of a low-dose computed tomography (LDCT) lung cancer screening program.Using the hospital-based cancer registry data on number of patients with lung cancer and deaths from 2008 to 2017, we conducted a retrospective study using a hospital-based cohort to investigate the relationship between changes in lung cancer surgical volume, the proportion of lung-sparing surgery, and prolonged prognostic outcomes after the gradual implementation of the LDCT lung cancer screening program in recent years.From 2008 to 2017, 3251 patients were diagnosed with lung cancer according to the hospital-based cancer registry. The 5-year mortality rate decreased gradually from 83.54% to 69.44% between 2008 and 2017. The volume of total lung cancer surgical procedures and proportion of lung-sparing surgery performed gradually increased significantly from 2008 to 2017, especially from 2014 to 2017 after implementation of a large volume of LDCT lung cancer screening examinations. In conclusion, our real-world data suggest that there will be an increase in cases of operable early-stage lung cancers, which in turn will increase the surgical volume and proportion of lung-sparing surgery, after the gradual implementation of the LDCT lung cancer screening program in recent years. These findings suggest the importance of a successful national policy regarding LDCT screening programs, regulation of shortage of thoracic surgeons, thoracic radiologist workforce training positions, and education programs.

Use of Coronary Computed Tomography Angiography to Screen Hospital Employees with Cardiovascular Risk Factors.

The objective of this study was to determine how coronary computed tomography angiography (CCTA) can be employed to detect coronary artery disease in hospital employees, enabling early treatment and minimizing damage. All employees of our hospital were assessed using the Framingham Risk Score. Those with a 10-year risk of myocardial infarction or death of >10% were offered CCTA; the Coronary Artery Disease Reporting and Data System (CAD-RADS) score was the outcome. A total of 3923 hospital employees were included, and the number who had received CCTA was 309. Among these 309, 31 (10.0%) had a CAD-RADS score of 3-5, with 10 of the 31 (32.3%) requiring further cardiac catheterization; 161 (52.1%) had a score of 1-2; and 117 (37.9%) had a score of 0. In the multivariate logistic regression, only age of ≥ 55 years (p < 0.05), hypertension (p < 0.05), and hyperlipidemia (p < 0.05) were discovered to be significant risk factors for a CAD-RADS score of 3-5. Thus, regular and adequate control of chronic diseases is critical for patients, and more studies are required to be confirmed if there are more significant risk factors.

Performance and educational training of radiographers in lung nodule or mass detection: Retrospective comparison with different deep learning algorithms.

ABSTRACT: The aim of this investigation was to compare the diagnostic performance of radiographers and deep learning algorithms in pulmonary nodule/mass detection on chest radiograph.A test set of 100 chest radiographs containing 53 cases with no pathology (normal) and 47 abnormal cases (pulmonary nodules/masses) independently interpreted by 6 trained radiographers and deep learning algorithems in a random order. The diagnostic performances of both deep learning algorithms and trained radiographers for pulmonary nodules/masses detection were compared.QUIBIM Chest X-ray Classifier, a deep learning through mass algorithm that performs superiorly to practicing radiographers in the detection of pulmonary nodules/masses (AUCMass: 0.916 vs AUCTrained radiographer: 0.778, P < .001). In addition, heat-map algorithm could automatically detect and localize pulmonary nodules/masses in chest radiographs with high specificity.In conclusion, the deep-learning based computer-aided diagnosis system through 4 algorithms could potentially assist trained radiographers by increasing the confidence and access to chest radiograph interpretation in the age of digital age with the growing demand of medical imaging usage and radiologist burnout.