A Deep Learning Approach to Classify Fabry Cardiomyopathy from Hypertrophic Cardiomyopathy Using Cine Imaging on Cardiac Magnetic Resonance.

A challenge in accurately identifying and classifying left ventricular hypertrophy (LVH) is distinguishing it from hypertrophic cardiomyopathy (HCM) and Fabry disease. The reliance on imaging techniques often requires the expertise of multiple specialists, including cardiologists, radiologists, and geneticists. This variability in the interpretation and classification of LVH leads to inconsistent diagnoses. LVH, HCM, and Fabry cardiomyopathy can be differentiated using T1 mapping on cardiac magnetic resonance imaging (MRI). However, differentiation between HCM and Fabry cardiomyopathy using echocardiography or MRI cine images is challenging for cardiologists. Our proposed system named the MRI short-axis view left ventricular hypertrophy classifier (MSLVHC) is a high-accuracy standardized imaging classification model developed using AI and trained on MRI short-axis (SAX) view cine images to distinguish between HCM and Fabry disease. The model achieved impressive performance, with an F1-score of 0.846, an accuracy of 0.909, and an AUC of 0.914 when tested on the Taipei Veterans General Hospital (TVGH) dataset. Additionally, a single-blinding study and external testing using data from the Taichung Veterans General Hospital (TCVGH) demonstrated the reliability and effectiveness of the model, achieving an F1-score of 0.727, an accuracy of 0.806, and an AUC of 0.918, demonstrating the model's reliability and usefulness. This AI model holds promise as a valuable tool for assisting specialists in diagnosing LVH diseases.

Right ventricular scalloping index as cardiac magnetic resonance-derived marker for diagnosis of arrhythmogenic right ventricular cardiomyopathy.

BACKGROUND: The cardiac magnetic resonance (CMR) evaluation of right ventricular (RV) morphologic abnormalities in patients with arrhythmogenic right ventricular cardiomyopathy (ARVC) is subjective. Here, we aimed to use a quantitative index, the right ventricular scalloping index (RVSI), to standardize the measurement of RV free wall scalloping and aid in the imaging diagnosis. METHODS: We retrospectively included 15 patients with definite ARVC and 45 age- and sex-matched patients with idiopathic right ventricular outflow tract ventricular arrhythmia (RVOT-VA) as controls. The RVSI was measured from cine images on four-chamber view to evaluate its ability to distinguish between ARVC and RVOT-VA patients. Other cardiac functional parameters including strain analysis were also performed. RESULTS: The RVSI was significantly higher in the ARVC than RVOT-VA group (1.56 ± 0.23 vs 1.30 ± 0.08, p < 0.001). The diagnostic performance of the RVSI was superior to the RV global longitudinal, circumferential, and radial strains, RV ejection fraction, and RV end-diastolic volume index. The RVSI demonstrated high intraobserver and interobserver reliability (intraclass correlation coefficient, 0.94 and 0.96, respectively). RVSI was a strong discriminator between ARVC and RVOT-VA patients (area under curve [AUC], 0.91; 95% CI, 0.82-0.99). A cutoff value of RVSI ≥1.49 provided an accuracy of 90.0%, specificity of 97.8%, sensitivity of 66.7%, positive predictive value (PPV) of 90.9%, and a negative predictive value (NPV) of 89.8%. In a multivariable analysis, a family history of ARVC or sudden cardiac death (odds ratio, 38.71; 95% CI, 1.48-1011.05; p = 0.028) and an RVSI ≥1.49 (odds ratio, 64.72; 95% CI, 4.58-914.63; p = 0.002) remained predictive of definite ARVC. CONCLUSION: RVSI is a quantitative method with good performance for the diagnosis of definite ARVC.

Use of artificial intelligence and I-Score for prediction of recurrence before catheter ablation of atrial fibrillation.

BACKGROUND: Based solely on pre-ablation characteristics, previous risk scores have demonstrated variable predictive performance. This study aimed to predict the recurrence of AF after catheter ablation by using artificial intelligence (AI)-enabled pre-ablation computed tomography (PVCT) images and pre-ablation clinical data. METHODS: A total of 638 drug-refractory paroxysmal atrial fibrillation (AF) patients undergone ablation were recruited. For model training, we used left atria (LA) acquired from pre-ablation PVCT slices (126,288 images). A total of 29 clinical variables were collected before ablation, including baseline characteristics, medical histories, laboratory results, transthoracic echocardiographic parameters, and 3D reconstructed LA volumes. The I-Score was applied to select variables for model training. For the prediction of one-year AF recurrence, PVCT deep-learning and clinical variable machine-learning models were developed. We then applied machine learning to ensemble the PVCT and clinical variable models. RESULTS: The PVCT model achieved an AUC of 0.63 in the test set. Various combinations of clinical variables selected by I-Score can yield an AUC of 0.72, which is significantly better than all variables or features selected by nonparametric statistics (AUCs of 0.66 to 0.69). The ensemble model (PVCT images and clinical variables) significantly improved predictive performance up to an AUC of 0.76 (sensitivity of 86.7% and specificity of 51.0%). CONCLUSIONS: Before ablation, AI-enabled PVCT combined with I-Score features was applicable in predicting recurrence in paroxysmal AF patients. Based on all possible predictors, the I-Score is capable of identifying the most influential combination.

Low-dose CT screening among never-smokers with or without a family history of lung cancer in Taiwan: a prospective cohort study.

BACKGROUND: In Taiwan, lung cancers occur predominantly in never-smokers, of whom nearly 60% have stage IV disease at diagnosis. We aimed to assess the efficacy of low-dose CT (LDCT) screening among never-smokers, who had other risk factors for lung cancer. METHODS: The Taiwan Lung Cancer Screening in Never-Smoker Trial (TALENT) was a nationwide, multicentre, prospective cohort study done at 17 tertiary medical centres in Taiwan. Eligible individuals had negative chest radiography, were aged 55-75 years, had never smoked or had smoked fewer than 10 pack-years and stopped smoking for more than 15 years (self-report), and had one of the following risk factors: a family history of lung cancer; passive smoke exposure; a history of pulmonary tuberculosis or chronic obstructive pulmonary disorders; a cooking index of 110 or higher; or cooking without using ventilation. Eligible participants underwent LDCT at baseline, then annually for 2 years, and then every 2 years up to 6 years thereafter, with follow-up assessments at each LDCT scan (ie, total follow-up of 8 years). A positive scan was defined as a solid or part-solid nodule larger than 6 mm in mean diameter or a pure ground-glass nodule larger than 5 mm in mean diameter. Lung cancer was diagnosed through invasive procedures, such as image-guided aspiration or biopsy or surgery. Here, we report the results of 1-year follow-up after LDCT screening at baseline. The primary outcome was lung cancer detection rate. The p value for detection rates was estimated by the χ2 test. Univariate and multivariable logistic regression analyses were used to assess the association between lung cancer incidence and each risk factor. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of LDCT screening were also assessed. This study is registered with ClinicalTrials.gov, NCT02611570, and is ongoing. FINDINGS: Between Dec 1, 2015, and July 31, 2019, 12 011 participants (8868 females) were enrolled, of whom 6009 had a family history of lung cancer. Among 12 011 LDCT scans done at baseline, 2094 (17·4%) were positive. Lung cancer was diagnosed in 318 (2·6%) of 12 011 participants (257 [2·1%] participants had invasive lung cancer and 61 [0·5%] had adenocarcinomas in situ). 317 of 318 participants had adenocarcinoma and 246 (77·4%) of 318 had stage I disease. The prevalence of invasive lung cancer was higher among participants with a family history of lung cancer (161 [2·7%] of 6009 participants) than in those without (96 [1·6%] of 6002 participants). In participants with a family history of lung cancer, the detection rate of invasive lung cancer increased significantly with age, whereas the detection rate of adenocarcinoma in situ remained stable. In multivariable analysis, female sex, a family history of lung cancer, and age older than 60 years were associated with an increased risk of lung cancer and invasive lung cancer; passive smoke exposure, cumulative exposure to cooking, cooking without ventilation, and a previous history of chronic lung diseases were not associated with lung cancer, even after stratification by family history of lung cancer. In participants with a family history of lung cancer, the higher the number of first-degree relatives affected, the higher the risk of lung cancer; participants whose mother or sibling had lung cancer were also at an increased risk. A positive LDCT scan had 92·1% sensitivity, 84·6% specificity, a PPV of 14·0%, and a NPV of 99·7% for lung cancer diagnosis. INTERPRETATION: TALENT had a high invasive lung cancer detection rate at 1 year after baseline LDCT scan. Overdiagnosis could have occurred, especially in participants diagnosed with adenocarcinoma in situ. In individuals who do not smoke, our findings suggest that a family history of lung cancer among first-degree relatives significantly increases the risk of lung cancer as well as the rate of invasive lung cancer with increasing age. Further research on risk factors for lung cancer in this population is needed, particularly for those without a family history of lung cancer. FUNDING: Ministry of Health and Welfare of Taiwan.

Elevated serum levels of T-cell immunoglobulin and mucin-domain containing molecule 3 in patients with systemic inflammation following COVID-19 vaccination.

BACKGROUND: ChAdOx1 nCoV-19 vaccine has been widely used. Some unexpected adverse effects such as the development of systemic hyper inflammation with multiorgan involvement after vaccination, in rare cases, have been reported. However, its pathogenesis remains unclear. METHODS: This study recruited two cases who suffered from systemic inflammation following ChAdOx1 nCoV-19 vaccine and two 30-year-old male volunteers without underlying disease who have received ChAdOx1 nCoV-19 vaccine as control group. Blood samples were collected from our patients and healthy subjects before and after treatment with anti-inflammatory agent such as glucocorticoid and tocilizumab. The immune profile from our patients and healthy controls were measured using a human XL cytokine Proteome Profiler array (ARY022b, R&D Systems). RESULTS: Biochemical parameters revealed leukocytosis with segmented neutrophil dominance and elevated serum levels of C-reactive protein (CRP), erythrocyte sedimentation rate, and ferritin in these two patients. The cytokine array revealed that mean levels of T cell immunoglobulin and mucin-domain containing-3 (TIM-3) (3640.3 vs 1580.5 pixels per inch [ppi]), B-cell activating factor (BAFF) (3036.8 vs 1471.0 ppi), urokinase plasminogen activator surface receptor (uPAR) (1043.1 vs 516.8 ppi), Resistin (1783.7 vs 711.3 ppi), platelet-derived growth factor (PDGF)-AB/BB (1980.7 vs 939.7 ppi), macrophage inflammatory protein-3-beta (MIP-3ß) (911.9 vs 346.2 ppi), and interferon-inducible T-cell alpha chemoattractant (I-TAC) (1026.3 vs 419.7 ppi) were 2-fold higher in the patients than in normal subjects who received ChAdOx1 nCoV-19 vaccine. CONCLUSION: We demonstrated that systemic inflammation may occur in subjects who have received the ChAdOx1 nCoV-19 vaccination. Moreover, we proposed immune markers, which may be implicated in the pathogenesis of systemic inflammation following COVID-19 vaccination as potential diagnostic biomarkers.

Left Ventricular Apical Aneurysm in Fabry Disease: Implications for Clinical Significance and Risk Stratification.

Background A previously underrecognized phenotype of left ventricular apical aneurysm (LVAA) has been increasingly identified in Fabry disease. This study explored LVAA's clinical prevalence and its prognostic implications over a long-term follow-up. Methods and Results We retrospectively analyzed 268 consecutive patients with Fabry disease at a tertiary medical center. Patients with increased left ventricular mass index were recognized as having left ventricular hypertrophy (LVH). LVAA was identified using either echocardiography or cardiovascular magnetic resonance imaging. Two patients with ischemic LVAA were excluded. The primary end point was a composite of cardiovascular events, including heart failure hospitalization, sustained ventricular tachycardia, ischemic stroke, and all-cause mortality. Of 266 enrolled patients, 105 (39.5%) had LVH (age 58.5±11.9 years, 48.6% men), and 11 (10.5%) had LVAA. Over 49.3±34.8 months of follow-up, 25 patients with LVH experienced composite events, including 9 heart failure hospitalizations, 4 sustained ventricular tachycardia, 6 ischemic strokes, and 15 mortalities. In patients with LVH, those with LVAA had a significantly higher risk of composite events and lower event-free survival than those without LVAA (8 [72.7%] versus 17 [18.1%], log-rank P<0.001). LVAA was independently associated with an increased risk of composite events (hazard ratio, 3.59 [95% CI, 1.30-9.91]; P=0.01) after adjusting for age, sex, advanced heart failure, renal function, dyslipidemia, atrial fibrillation, left ventricular ejection fraction, left ventricular diastolic function, and left ventricular mass index. Conclusions LVAA is present in approximately 10% of patients with Fabry disease and LVH. It is associated with an increased risk of adverse cardiovascular events and may necessitate aggressive treatment.

Risk factors for pneumothorax and pulmonary hemorrhage following computed tomography-guided transthoracic core-needle biopsy of subpleural lung lesions.

BACKGROUND: Identifying the risk factors for complications may alert the physicians and help them adjust their plans before performing computed tomography-guided lung biopsies. Reportedly, a pleura-nodule distance longer than 2.0 cm is a strong predictor for pneumothorax and pulmonary hemorrhage. However, the rate and risk factors of biopsy-associated complications in subpleural lesions have not been assessed. This study aimed to identify the risk factors for pneumothorax and pulmonary hemorrhage in subpleural lesions ≤2.0 cm in depth. METHODS: Altogether, 196 patients (196 subpleural lesions, lesion depth: 0.1-2.0 cm) who underwent computed tomography-guided transthoracic core-needle biopsies between March 2017 and November 2017 were retrospectively analyzed. Univariate analysis of risk factors including patient-related, lesion-related, and procedure-related characteristics was performed for pneumothorax ≥1 cm and pulmonary hemorrhage ≥2 cm after the biopsy. Multivariate logistic regression analysis was performed to identify the independent risk factors. RESULTS: Pneumothorax ≥1 cm and pulmonary hemorrhage ≥2 cm were identified in 35 (17.9%) and 32 (16.3%) cases, respectively. In the multivariate analysis, a longer needle path (odds ratio [OR], 1.976; 95% confidence interval [CI], 1.113-3.506; p = 0.020) and low attenuation along the biopsy tract (OR, 3.080; 95% CI, 1.038-9.139; p = 0.043) were predictors of pneumothorax ≥ 1 cm. Ground-glass lesions (OR, 2.360; 95% CI, 1.009-5.521; p = 0.048) and smaller needle-pleura angle (OR, 0.325; 95% CI, 0.145-0.728; p = 0.006) were associated with pulmonary hemorrhage ≥2 cm. CONCLUSION: For subpleural lesions ≤2.0 cm in depth, a puncture route having a shorter needle path and passing through the lung parenchyma with higher attenuation may reduce the risk of biopsy-associated pneumothorax ≥1 cm. A higher needle-pleura angle may reduce the risk of pulmonary hemorrhage ≥2 cm in the short axis.

Acute-on-chronic pancreatitis complicated with mediastinal pseudocysts and cardiac tamponade: A case report and literature review.

The clinical course and severity of pancreatitis might vary largely. Pancreatitis-related thoracic complications might be life-threatening but frequently ignored. We report an alcoholic patient who initially presented to the emergency department with community-acquired pneumonia, acute respiratory failure and acute-on-chronic pancreatitis with massive pancreatic pleural effusion. Subsequently, he developed insidiously pancreatitis-related intra-abdominal, mediastinal pseudocysts, and unexpectedly sudden onset of cardiac tamponade. Although tamponade-related haemodynamic instability improved soon after timely diagnosis and emergent pericardial drainage, his recovery period was prolonged. His serum amylase and lipase were persistently elevated until definitive treatment with endoscopic retrograde cholangiopancreatography-assisted removal of pancreatic duct stones. Pancreatitis-related cardiac tamponade is rare but lethal without prompt diagnosis and management. We reviewed pancreatitis-related thoracic complications, particularly for cardiac tamponade, and discussed about the pathophysiology and management options.

Primary care staff's willingness to participate in compassionate community network and palliative care and the barriers they face: a mixed methods study.

OBJECTIVES: Compassionate community models, successfully applied in several Western countries, have not been extensively promoted in Asian countries. This study explored primary care staff's willingness to participate and factors associated with their participations in compassionate community education and network, palliative care education, providing palliative care and the barriers they faced. METHODS: Adopting a mixed quantitative-qualitative design, primary care staffs in Beitou and Shilin districts in Taiwan, including physicians, nurses, pharmacists and administrative staff aged ≥20 years who had worked in a clinic for more than 2 months, were recruited. A questionnaire survey was conducted to explore their willingness to participate in compassionate community education and networks and palliative care education and care provision. Logistic regression was used to evaluate factors associated with their willingness, and qualitative perceptions were evaluated by open questions. RESULTS: About half of the respondents were willing to participate in compassionate community education and network and palliative care education, but only 19.5% were willing to provide palliative care. Compared with other staff, primary care nurses showed significantly more willingness to participate in compassionate community education and network and palliative care education and to provide palliative care. However, physicians were significantly not willing to participate in any of the three services apart from providing care. Capability, administrative and manpower concerns, time, age and motivation were the main barriers. CONCLUSIONS: To encourage primary care staff to participate more in compassionate community education and network and palliative care education and to provide palliative care, policymakers should pay more attention towards removing the barriers to their engagement.

Prognostic histologic subtyping of dominant tumor in resected synchronous multiple adenocarcinomas of lung.

The prognostic role of histological patterns of dominant tumor (DT) and second dominant tumor (sDT) in synchronous multiple adenocarcinoma (SMADC) of lung remains unclear. SMADC patients diagnosed between 2003 and 2015 were retrospectively reviewed. DT and sDT were defined as two maximum diameters of consolidation among multiple tumors. Histological pattern was determined using IASLC/ATS/ERS classification system. DTs were divided into low- (lepidic), intermediate- (acinar, papillary) and high-grade (micropapillary, solid) subtypes, and sDTs into non-invasive predominant (lepidic) and invasive predominant (acinar, papillary, micropapillary, solid) subtypes. During mean 74-month follow-up among 149 nodal-negative patients having SMADC resected, recurrence was noted in 44 (29.5%), with significantly higher percentage in high-grade DT (p < 0.001). Five-year overall (OS) and disease-free (DFS) survivals in low-, intermediate- and high-grade DT were 96.9%, 94.3%, 63.3% (p < 0.001) and 100%, 87.2%, 30.0%, respectively (p < 0.001). Cox-regression multivariate analysis demonstrated high-grade DT as a significant predictor for DFS (Hazard ratio [HR] 5.324; 95% CI 2.570-11.462, p < 0.001) and OS (HR 3.287; 95% CI 1.323-8.168, p = 0.010). Analyzing DT and sDT together, we found no significant differences in DFS, either in intermediate- or high-grade DT plus invasive or non-invasive sDT. DT was histologically an independent risk factor of DFS and OS in completely resected nodal-negative SMADCs.

The differences in nurses' willingness to discuss palliative care with patients and their family members.

BACKGROUND: This study aimed to evaluate the differences in nurses' willingness to discuss palliative care with terminally ill patients and their family members. METHODS: The participants were randomly recruited from registered staff nurses ≥20 years of age who were responsible for clinical inpatient care in a tertiary hospital in northern Taiwan. A semi-structured questionnaire was administered to evaluate nurses' experiences of discussing do-not-resuscitate (DNR) decisions and their willingness to discuss palliative care with terminal patients and their family members. The differences in nurses' experiences regarding DNR and willingness to discuss palliative care with terminally ill patients and their family members were compared using the Chi-square test. Logistic regressions were used to analyze factors associated with nurses' willingness to discuss palliative care with patients and their families. RESULTS: More participants had experienced initiating discussions about DNR with patients' families than with patients (72.2% vs 61.9%, p < 0.001). Unadjusted logistic regression analysis showed that the experiences of actively initiating DNR discussions with patients were a significant factor associated with palliative care discussion with patients (odds ratio [OR] = 2.91, 95% confidence interval [CI]: 1.09-7.79). On the other hand, the experiences of actively initiating DNR discussions with patients and with patients' families were significant factors associated with palliative care discussion with patients' families (OR = 3.84, 95% CI: 1.22-12.06 and OR = 3.60, 95% CI: 1.19-10.90, respectively). After adjusting for covariates, no significant factors were found to be independently associated with nurses' willingness to discuss palliative care with patients and their family members. CONCLUSION: There are significant differences in nurses' willingness to discuss palliative care with patients and their family members. Further research is needed to evaluate factors associated with nurses' willingness to discuss palliative care with patients and their families to facilitate these discussions and protect patients' autonomy.

Active surveillance or early resection for ground-glass nodules that need preoperative localization.

INTRODUCTION: Few studies have investigated the impact of active surveillance on pathological outcome ground-glass nodules (GGNs). We focused on GGNs that needed preoperative localization before resection and compared the pathological results between GGNs that underwent early resection or active surveillance. METHODS: We retrospectively reviewed data of resected GGNs between January 2017 and December 2018. GGNs were classified by early resection (Group A) and active surveillance (Group B). Group B was subclassified as no (Group B1) and with (Group B2) growth, and intergroup comparison of pathological results was undertaken. RESULTS: In total, 509 GGNs (124, 275, and 110 in Groups A, B1, and B2, respectively) were included. Malignancy (primary lung cancer) ratios were 68% and 72% in Groups A and B (p = .312) and 65% and 92% in Groups B1 and B2, respectively (p < .001). The ratios of invasive carcinoma were 21.4%, 9.6%, and 35.6% in Groups A, B1, and B2, respectively. Predictors for invasive carcinoma included history of lung cancer, GGN size ≥ 10 mm, solid size ≥ 6 mm, and GGN growth. CONCLUSIONS: The pathological findings were similar for GGNs in the early resection and active surveillance groups. However, rates of malignancy and invasive carcinoma increased in the group that manifested growth during active surveillance.

Significance of preoperative biopsy in radiological solid-dominant clinical stage I non-small-cell lung cancer.

OBJECTIVES: The present study aimed to clarify the association between preoperative biopsy and surgical outcomes in clinical stage I non-small-cell lung cancer (NSCLC) with different proportions of ground-glass opacity (GGO). METHODS: Data on patients who underwent pulmonary resection for NSCLC from 2006 to 2016 were drawn from a prospective registered database and analysed retrospectively. Patient characteristics collected included tumour size, location and staging, surgical approach, consolidation-tumour ratio, histopathology and the presence or absence of preoperative biopsy to identify the independent prognostic factors of disease-free survival (DFS) and cancer-specific survival. A 1:1 propensity score matching was conducted between the preoperative biopsy and reference groups based on their baseline characteristics measured before the decision for preoperative biopsy. RESULTS: A total of 1427 patients were collected to achieve an overall 5-year DFS as 84.5% (median follow-up: 67.3 months), stratified to be 99.5% in the GGO-dominant group (n = 430) and 78.2% in the solid-dominant group (n = 997). Only 2 patients (0.5%) in the GGO-dominant group experienced tumour recurrence. For solid-dominant tumours matched with propensity scores (279 in preoperative biopsy vs 279 in reference group), the independent predictors of DFS included preoperative biopsy, sublobar resection, pathological staging and angiolymphatic invasion. Preoperative biopsy was a predictor of cancer-specific survival in univariable analysis but was not in multivariable analysis. Significant differences were also found between matched groups in those with late-delay surgery, but not in patients receiving preoperative biopsy with early-delay surgery (≤21 days). CONCLUSION: Preoperative biopsy may worsen surgical outcomes in patients with clinical stage I, solid-dominant NSCLC.

Computed tomography-based differentiation of primary pulmonary lymphoepithelioma-like carcinoma and small-cell lung cancer.

BACKGROUND: Primary pulmonary lymphoepithelioma-like carcinoma (LELC) is a rare subtype of lung cancer. Both small-cell lung cancer (SCLC) and LELC often manifest as a centrally located tumor with lymphadenopathy. This retrospective study investigated and compared the initial computed tomography (CT) features and subsequent survival outcomes of LELC and SCLC. METHODS: A total of 50 patients with a confirmed diagnosis of LELC were enrolled and matched at a ratio of 1:1 with patients with SCLC according to the tumor stage. Utilizing a consensus approach, two radiologists reviewed pretreatment CT images. Survival outcomes were analyzed. RESULTS: Well-defined tumors were significantly more common in the LELC group (LELC: 42% vs SCLC: 24%, p = 0.005). Based on the comparisons of the primary tumor with the muscles, LELC tumors exhibited a significantly higher percentage of attenuation on contrast-enhanced CT scans (21.6% ± 29% vs -14.2% ± 37%, p < 0.001). The prevalence of vascular or bronchial encasement (18% vs 40%, p = 0.028), background emphysematous changes (10% vs 60%, p < 0.001), and tumors located in upper lobes (18% vs 64%, p < 0.001) was significantly lower in the LELC group. Female gender (70% vs 12%, p < 0.001), younger age (57.6 ± 12.0 years vs 68.0 ± 11.0 years, p < 0.001), and without a history of smoking (16% vs 88%, p < 0.001) were factors more commonly found in the LELC group. The patients with LELC had a better prognosis with significantly longer median survival than did the patients with SCLC (23.4 months vs 17.3 months, p = 0.01). CONCLUSION: Because SCLC demonstrated a more aggressive disease progression, differentiating LELC from SCLC is crucial. In Epstein-Barr virus-endemic areas, the diagnosis of LELC should be considered when approaching a patient with the above-mentioned CT and clinical features.

Multidisciplinary team discussion results in survival benefit for patients with stage III non-small-cell lung cancer.

BACKGROUND: The treatment for stage III non-small cell lung cancer (NSCLC) often involves multi-modality treatment. This retrospective study aimed to evaluate whether multidisciplinary team (MDT) discussion results in better patient survival. MATERIALS AND METHODS: MDT discussion was optional before February 2016 and was actively encouraged by the MDT committee beginning February 2016. We reviewed the medical charts and computer records of patients with stage III NSCLC between January 2013 and December 2018. RESULTS: A total of 515 patients were included. The median survival of all the patients was 33.9 months (M). The median survival of patients who were treated after MDT discussion was 41.2 M and that of patients treated without MDT discussion was 25.7 M (p = 0.018). The median survival of patients treated before February 2016 was 25.7 M and that of patients treated after February 2016 was 33.9 M (p = 0.003). The median survival of patients with stage IIIA tumors and those with stage IIIB tumors was 39.4 M and 25.7 M, respectively (p = 0.141). Multivariate analysis showed that MDT or not (p<0.001), T staging (p = 0.009), performance status (p<0.001), and surgery (p = 0.016) to be significant prognostic factors. CONCLUSION: The results of the study show that MDT discussion results in survival benefit in patients with stage III NSCLC. The MDT discussion, performance status, and if surgery was performed were independent prognostic factors for patients with stage III NSCLC.

The Clinical Application of the Deep Learning Technique for Predicting Trigger Origins in Patients With Paroxysmal Atrial Fibrillation With Catheter Ablation.

BACKGROUND: Non-pulmonary vein (NPV) trigger has been reported as an important predictor of recurrence post-atrial fibrillation ablation. Elimination of NPV triggers can reduce the recurrence of postablation atrial fibrillation. Deep learning was applied to preablation pulmonary vein computed tomography geometric slices to create a prediction model for NPV triggers in patients with paroxysmal atrial fibrillation. METHODS: We retrospectively analyzed 521 patients with paroxysmal atrial fibrillation who underwent catheter ablation of paroxysmal atrial fibrillation. Among them, pulmonary vein computed tomography geometric slices from 358 patients with nonrecurrent atrial fibrillation (1-3 mm interspace per slice, 20-200 slices for each patient, ranging from the upper border of the left atrium to the bottom of the heart, for a total of 23 683 images of slices) were used in the deep learning process, the ResNet34 of the neural network, to create the prediction model of the NPV trigger. There were 298 (83.2%) patients with only pulmonary vein triggers and 60 (16.8%) patients with NPV triggers±pulmonary vein triggers. The patients were randomly assigned to either training, validation, or test groups, and their data were allocated according to those sets. The image datasets were split into training (n=17 340), validation (n=3491), and testing (n=2852) groups, which had completely independent sets of patients. RESULTS: The accuracy of prediction in each pulmonary vein computed tomography image for NPV trigger was up to 82.4±2.0%. The sensitivity and specificity were 64.3±5.4% and 88.4±1.9%, respectively. For each patient, the accuracy of prediction for a NPV trigger was 88.6±2.3%. The sensitivity and specificity were 75.0±5.8% and 95.7±1.8%, respectively. The area under the curve for each image and patient were 0.82±0.01 and 0.88±0.07, respectively. CONCLUSIONS: The deep learning model using preablation pulmonary vein computed tomography can be applied to predict the trigger origins in patients with paroxysmal atrial fibrillation receiving catheter ablation. The application of this model may identify patients with a high risk of NPV trigger before ablation.

Automated extraction of left atrial volumes from two-dimensional computer tomography images using a deep learning technique.

BACKGROUND: Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create three-dimensional (3D) geometries. METHODS: Five hundred eighteen patients who underwent procedures for circumferential isolation of four pulmonary veins were enrolled. Cardiac CT images (from 97 patients) were used to construct the LA detection and segmentation models. These images were reviewed by the cardiologists such that images containing the LA were identified/segmented as the ground truth for model training. Two DCNNs which incorporated transfer learning with the architectures of ResNet50/U-Net were trained for image-based LA classification/segmentation. The LA geometry created by the deep learning model was correlated to the outcomes of AF ablation. RESULTS: The LA detection model achieved an overall 99.0% prediction accuracy, as well as a sensitivity of 99.3% and a specificity of 98.7%. Moreover, the LA segmentation model achieved an intersection over union of 91.42%. The estimated mean LA volume of all the 518 patients studied herein with the deep learning model was 123.3 ± 40.4 ml. The greatest area under the curve with a LA volume of 139 ml yielded a positive predictive value of 85.5% without detectable AF episodes over a period of one year following ablation. CONCLUSIONS: The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry.

CT-Guided Core Biopsy for Peripheral Sub-solid Pulmonary Nodules to Predict Predominant Histological and Aggressive Subtypes of Lung Adenocarcinoma.

BACKGROUND: Adenocarcinoma is the most common type of lung cancer, and pre-operative biopsy plays an important role to determine its major subtypes. As proposed by the International Association for the Study of Lung Cancer (IASLC), American Thoracic Society (ATS), and European Respiratory Society (ERS) in 2011, the predominant histological subtype of adenocarcinoma is an indicator of outcomes and recurrence rate. However, the value of CT-guided core biopsy in predicting the predominant subtype and detecting the presence of an aggressive subtype of adenocarcinoma, peripheral sub-solid nodule, has less been discussed. METHODS: We retrospectively reviewed 318 consecutive peripheral sub-solid nodules that underwent percutaneous CT-guided lung biopsy and surgical resection, between October 2015 and December 2018 and were diagnosed as adenocarcinoma with histological subtype. The subtyping results from biopsy and surgical pathology were compared to evaluate the concordance rate. RESULTS: The overall concordance rate between biopsy and surgical pathology in determining the predominant histological subtype was 64%. Better concordance was found in small tumors (≤ 2 cm), in predicting either predominant histology (χ2 = 7.091, P = 0.008) or high grade adenocarcinoma, micropapillary and/or solid subtype, MIP-SOL (χ2 = 22.301, P < 0.001). The analysis of ground glass opacity (GGO) component (C/T ratio) obtained significantly higher accuracy in the pure GGO group than in the other two groups in predicting predominant histology or high grade adenocarcinoma (χ2 = 17.560, P < 0.001 and χ2 = 61.938, P < 0.001, respectively). CONCLUSIONS: CT-guided core biopsies provide additional value in predicting the histological subtype of lung adenocarcinoma after surgical resection, especially in small tumors (≤ 2 cm) or an initially pure GGO group.

Delayed surgery after histologic or radiologic-diagnosed clinical stage I lung adenocarcinoma.

BACKGROUND: The impact of delayed surgery on clinical outcomes after histologic or radiologic diagnosis of clinical stage I adenocarcinoma remains controversial. We evaluated the effects of delayed surgery on outcomes of patients with early-stage lung cancer. METHODS: Associations between time intervals of "histologic diagnosis-to-surgery" (HDS), "radiologic diagnosis-to-surgery" (RDS), and overall survival in clinical stage I adenocarcinoma were assessed using multivariable Cox proportional hazard analysis. RESULTS: A total of 561 consecutive patients with preoperative histologic confirmation of stage I lung cancer between 2006 and 2016 were included. Median time to HDS and RDS were 20 (2-267) and 58 (38-2,983) days. Higher Charlson comorbidity score, receiving brain magnetic resonance imaging screening, and video-assisted thoracoscopic surgery approach were significantly associated with increased risk of late HDS (>21 days). Smaller tumor size and non-radiologic solid-dominant pattern were significantly associated with increased risk of late RDS (>60 days). In the overall cohort, worse 5-year overall survival was associated with late HDS compared to early HDS (75.9% vs. 85.5%, P=0.003). No significant differences were found in later late vs. early RDS (83.7% vs. 83.3%, P=0.570). In 286 propensity-score matched patients, late HDS [adjusted hazard ratio (aHR) =2.031, P=0.038], higher Charlson comorbidity score (aHR=1.610, P=0.023), larger tumor size (aHR=2.164, P=0.031), without brain magnetic resonance imaging screening (aHR=2.051, P=0.045), and tumor with angiolymphatic invasion (aHR=4.638, P=0.001) were significantly associated with lower overall survival. CONCLUSIONS: In patients with stage I lung adenocarcinoma, delayed surgery after a histologic diagnosis is an independent predictor of overall survival after adjusting for clinical risk factors, suggesting meaningful differences in clinical outcomes between timely vs. delayed surgeries.

Aggressive End-of-Life Care and Symptom Relief Treatments in Terminally Ill Patients Who Had Discussed Withdrawal of Mechanical Ventilation: A Hospital-Based Observational Study.

OBJECTIVE: The aim of this study was to explore the status of aggressive end-of-life care and symptom relief treatments in terminally ill patients who had discussed the withdrawal of mechanical ventilation. METHODS: This research is a retrospective observational study based on a chart review. Terminal patients aged ≥20 years, who were intubated with mechanical ventilation support, who underwent hospice-shared care, and who personally, or whose close relatives, had discussed the withdrawal of mechanical ventilation with hospice-shared care team members in a tertiary hospital in Taiwan during 2012 to 2015 were included. Demographics, medical conditions, and aggressive end-of-life care, including hospitalization, use of vasopressors, artificial nutrition, tube feeding, antibiotics, and symptom relief treatments including the use of opioids, steroids, and sedatives, were identified. The modes of care and treatments of patients by the status of withdrawal of mechanical ventilation were compared. RESULTS: A total of 141 patients had discussed the withdrawal of mechanical ventilation, and 111 (78.7%) had been withdrawn. Aggressive end-of-life care was noted in all patients regardless of mechanical ventilation status. There were no significant differences in the number and pattern of aggressive end-of-life care measures between patients who had or had not been withdrawn. There were significantly higher rates of symptom relief treatments used in patients who had been withdrawn. CONCLUSIONS: Aggressive end-of-life care is common for patients who have discussed the withdrawal of mechanical ventilation. There are significantly higher rates of symptom relief medications administered in patients who have been withdrawn from mechanical ventilation.