Artificial Intelligence Improves Novices' Bronchoscopy Performance: A Randomized Controlled Trial in a Simulated Setting.

BACKGROUND: Navigating through the bronchial tree and visualizing all bronchial segments is the initial step toward learning flexible bronchoscopy. A novel bronchial segment identification system based on artificial intelligence (AI) has been developed to help guide trainees toward more effective training. RESEARCH QUESTION: Does feedback from an AI-based automatic bronchial segment identification system improve novice bronchoscopists' end-of-training performance? STUDY DESIGN AND METHODS: The study was conducted as a randomized controlled trial in a standardized simulated setting. Novices without former bronchoscopy experience practiced on a mannequin. The feedback group (n = 10) received feedback from the AI, and the control group (n = 10) trained according to written instructions. Each participant decided when to end training and proceed to performing a full bronchoscopy without any aids. RESULTS: The feedback group performed significantly better on all three outcome measures (median difference, P value): diagnostic completeness (3.5 segments, P < .001), structured progress (13.5 correct progressions, P < .001), and procedure time (-214 seconds, P = .002). INTERPRETATION: Training guided by this novel AI makes novices perform more complete, more systematic, and faster bronchoscopies. Future studies should examine its use in a clinical setting and its effects on more advanced learners.

Systematic Endobronchial Ultrasound - The Six Landmarks Approach.

Lung cancer is the leading cause of cancer mortality globally. To ensure the correct diagnosis and staging in relation to treatment options, it is crucial to obtain valid biopsies from suspected tumors and mediastinal lymph nodes and accurate identification of the mediastinal lymph nodes regarding the Tumor-Node-Metastasis (TNM)-classification. Flexible bronchoscopy combined with endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is essential in the workup and diagnosis of patients suspected of lung cancer. EBUS-TBNA from mediastinal lymph nodes is a technically difficult procedure and has been identified as one of the most important procedures that should be integrated into a simulation-based training program for invasive pulmonologists. More specific guidelines that govern training in EBUS-TBNA are needed to meet this demand. We hereby propose a systematic, stepwise approach with specific attention to six landmarks that support the endoscopist when navigating through the bronchial maze. The stepwise approach relying on the six landmarks is used in the EBUS-certified training program offered by the European Respiratory Society (ERS).

Systematic Bronchoscopy: the Four Landmarks Approach.

Flexible bronchoscopy is a technically difficult procedure and has been identified as the most important procedure that should be integrated into a simulation-based training program for pulmonologists. However, more specific guidelines that govern bronchoscopy training are needed to meet this demand. To ensure patients a competent examination, we propose a systematic, stepwise approach, splitting the procedure into four "landmarks" to support novice endoscopists navigating the bronchial maze. The procedure can be evaluated based on three established outcome measures to ensure a thorough and effective inspection of the bronchial tree: diagnostic completeness, structured progress, and procedure time. The stepwise approach relying on the four landmarks is used at all simulation centers in Denmark and is being implemented in the Netherlands. To provide instant feedback to novice bronchoscopists when training and to relieve time constraints from consultants, we suggest that future studies should implement artificial intelligence as a feedback and certification tool when training new bronchoscopists.

Withdrawal of Inhaled Corticosteroids in Patients with COPD - A Prospective Observational Study.

BACKGROUND: Inhaled corticosteroids (ICS) are widely used in the treatment of chronic obstructive pulmonary disease (COPD), but recent studies have raised doubts whether all COPD patients will benefit from ICS. This study evaluates in a real-life setting the effects of ICS withdrawal in patients with COPD. METHODS: The study was a prospective intervention study following patients with COPD for 6 months after abrupt withdrawal of ICS. FEV1 (L), blood eosinophilic count (x10E9/L) and number of exacerbations were measured at baseline, 1, 3 and 6 months after ICS withdrawal. RESULTS: Ninety-six patients (56 females (57.4%), mean age 70 years (51-94 years)) with COPD were included in the study. Eleven patients were excluded during the study period (7 patients died, 4 patients withdrew their consent during the study period). During the 6 months, 51 patients (60%) had resumed treatment with ICS, of whom 34 patients (68%) experienced an exacerbation during follow-up. No significant decline in FEV1 was seen in this group between baseline and after 6 months (ΔFEV1 0.07 L, p = 0.09). In the remaining 34 patients (40%) without ICS after 6 months of follow-up, 15 patients (44.1%) experienced an exacerbation. No significant decline was seen in FEV1 at baseline and after 6 months (ΔFEV1 0.04 L, p = 0.28). There were no statistically significant differences between the two groups in age (70.5 vs 69.6 years, p = 0.53), nor between FEV1 at baseline (0.96 L vs 1.00 L, p = 0.63) or eosinophilic count (0.25 x10E9/L vs 0.17 x10E9/L, p = 0.07). CONCLUSION: Abrupt withdrawal of ICS was possible in some patients. However, more than half of the patients resumed ICS during follow-up. Based on results from our study we were not able to foresee - from neither history of exacerbations nor eosinophilic count - whom will be able to manage without ICS and who will resume treatment with ICS.

ß-Blocker Therapy and Risk of Chronic Obstructive Pulmonary Disease - A Danish Nationwide Study of 1·3 Million Individuals.

BACKGROUND: The possible association between ß-adrenoceptor antagonists (ß-blockers) and risk of COPD is controversial. The objective of the present study was to test whether ß-blocker use is associated with susceptibility to the disease. METHODS: A total of 301,542 new users of ß-blockers and 1,000,633 new users of any other antihypertensive drugs aged 30-90 years without any history of COPD hospitalizations were included in the present study and followed in the Danish National Patient Registry for incident admissions for COPD and COPD death between 1995 and 2015. Multiple adjusted cox regression models were used to examine the association between use of ß-blockers and COPD hospitalization. Additionally, subgroup analyses based on underlying diseases at baseline or duration of treatment were performed. FINDINGS: People treated with ß-blockers continuously for more than 6 months had a lower risk of COPD hospitalization during follow-up compared to people treated with any other antihypertensive drugs (adjusted hazard ratio [HRadjusted] 0·80, 95% CI 0·79-0·82). Risk of COPD hospitalization was lowered in the groups treated with ß-blockers among patients with ischemic heart disease (0·72, 0·69-0·75), cardiac arrhythmias (0·76, 0·72-0·80), asthma (0·69, 0·61-0·79), hypertension (0·91, 0·86-0·96), and diseases of the pulmonary circulation (pulmonary embolism and cor pulmonale) (0·72, 0·59-0·87). All-cause mortality as well as risk of COPD death during follow-up was lower in the group treated with ß-blockers compared to the group treated with any other antihypertensive drugs (0·56, 0·53-0·59). INTERPRETATION: Treatment with ß-blockers seems to reduce risk of COPD hospitalization and mortality compared to treatment with any other antihypertensive drugs. FUNDING: The Danish Council for Independent Research in Denmark (grant no. 4183-00569B), The Research Foundation of Health Science in Region Zealand (grant no. RSSF2017000661 and no. 15-000342), The Research Foundation of Medical Science (A.P. Møller Foundation, grant no. 16-68), The Research Foundation in memory of King Christian 10th (grant no. 142/2017), Aase & Ejnar Danielsen's Research Foundation (grant no. 10-001946), and Lundbeck Foundation (grant no. R252-2017-1690).

Variants of the ADRB2 Gene in COPD: Systematic Review and Meta-Analyses of Disease Risk and Treatment Response.

The ß2-adrenergic receptor (ADRB2) is an important regulator of airway smooth muscle tone in chronic obstructive pulmonary disease (COPD). Variants that impair ADRB2 function could increase disease risk or reduce the response to endogenous and inhaled adrenergic agonists in COPD. We performed a systematic review and three meta-analyses to assess whether three functional variants (Thr164Ile, Arg16Gly, and Gln27Glu) in the ADRB2 gene are associated with elevated risk of disease or reduced therapeutic response to inhaled ß2-agonists in COPD. We searched the medical literature from 1966 to 2017 and found 16 relevant studies comprising 85381 study subjects. The meta-analyses found no significant association between ADRB2 genotype and COPD risk. The summary odds ratios (ORs) for COPD in Thr164Ile homozygotes and heterozygotes were 2.57 (95% confidence interval (CI): 0.54-12.4) and 1.17 (95% CI: 0.96-1.44), respectively. Corresponding summary ORs for COPD in Arg16Gly homozygotes and heterozygotes were 0.97 (95% CI: 0.76-1.22) and 1.01 (95% CI: 0.81-1.26), while summary ORs for COPD in Gln27Glu homozygotes and heterozygotes were 1.00 (95% CI: 0.80-1.25) and 0.94 (95% CI: 0.69-1.24), respectively. When stratified by ethnicity, the summary ORs for COPD did not differ from 1.0 for any of the ADRB2 variants among Asian, Caucasian, or African populations. We found no consistent associations between ADRB2 genotype and treatment response to inhaled ß2-agonists in COPD. This systematic review and meta-analyses found that COPD risk and response to inhaled ß2-agonists were not associated with Thr164Ile, Arg16Gly, and Gln27Glu genotypes. However, identified cases of Thr164Ile were few, and additional studies of rare ADRB2 genotypes are required.

Risk of asthma in heterozygous carriers for cystic fibrosis: A meta-analysis.

BACKGROUND: Patients with cystic fibrosis (CF) have a higher prevalence of asthma than the background population, however, it is unclear whether heterozygous CF carriers are susceptible to asthma. Given this, a meta-analysis is necessary to determine the veracity of the association of CF heterozygosity with asthma. METHODS: We screened the medical literature from 1966 to 2015 and performed a meta-analysis to determine the risk of asthma in CF heterozygotes vs. non-carriers. RESULTS: Aggregating data from 15 studies, the odds ratio for asthma in CF heterozygotes compared with non-carriers was significantly elevated at 1.61 (95% CI: 1.18-2.21). When analyzing the studies considered of high quality in which asthma was diagnosed by a physician, the patients were >18years, or study size was ≥500, the trend remained the same, that heterozygous carriers of CF had elevated risk for asthma. CONCLUSIONS: The results show that heterozygous carriers for CF have a higher risk of asthma than non-carriers.