Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests.

The interpretation of pulmonary function tests (PFTs) to diagnose respiratory diseases is built on expert opinion that relies on the recognition of patterns and the clinical context for detection of specific diseases. In this study, we aimed to explore the accuracy and interrater variability of pulmonologists when interpreting PFTs compared with artificial intelligence (AI)-based software that was developed and validated in more than 1500 historical patient cases.120 pulmonologists from 16 European hospitals evaluated 50 cases with PFT and clinical information, resulting in 6000 independent interpretations. The AI software examined the same data. American Thoracic Society/European Respiratory Society guidelines were used as the gold standard for PFT pattern interpretation. The gold standard for diagnosis was derived from clinical history, PFT and all additional tests.The pattern recognition of PFTs by pulmonologists (senior 73%, junior 27%) matched the guidelines in 74.4±5.9% of the cases (range 56-88%). The interrater variability of κ=0.67 pointed to a common agreement. Pulmonologists made correct diagnoses in 44.6±8.7% of the cases (range 24-62%) with a large interrater variability (κ=0.35). The AI-based software perfectly matched the PFT pattern interpretations (100%) and assigned a correct diagnosis in 82% of all cases (p<0.0001 for both measures).The interpretation of PFTs by pulmonologists leads to marked variations and errors. AI-based software provides more accurate interpretations and may serve as a powerful decision support tool to improve clinical practice.

Longitudinal clinical outcomes in a real-world population of patients with idiopathic pulmonary fibrosis: the PROOF registry.

BACKGROUND: The PROOF registry is an observational study initiated in October 2013 with the aim to monitor disease progression in a real-world population of patients with idiopathic pulmonary fibrosis (IPF). Here, we present longitudinal clinical outcomes from the PROOF registry. METHODS: Patients with IPF were enrolled across eight centers in Belgium and Luxembourg. For all patients, clinical outcomes data were collected, including mortality, lung transplant, acute exacerbations, and pulmonary hypertension. For patients treated with pirfenidone at any time during follow-up (2013-2017), for any duration of treatment (the pirfenidone-treated population): pirfenidone treatment patterns were collected; changes in pulmonary function (forced vital capacity [FVC] and carbon monoxide diffusing capacity [DLco]) were reviewed up to 24 months post-inclusion; and time-to-event analyses from the time of registry inclusion were performed. RESULTS: The PROOF registry enrolled a total of 277 patients. During follow-up, 23.1% of patients died, 5.1% received a lung transplant, 5.4% experienced an acute exacerbation, and 6.1% had comorbid pulmonary hypertension. In the pirfenidone-treated population (N = 233, 84.1%), 12.9% of patients had a temporary dose discontinuation and 31.8% had a temporary dose reduction; 4.3% of patients permanently discontinued pirfenidone due to an adverse drug reaction. Mean percent predicted FVC was 81.2% (standard deviation [SD] 19.0) at Month 0 and 78.3% (SD 25.0) at Month 24, and mean percent predicted DLco was 47.0% (SD 13.2) and 45.0% (SD 16.5), respectively. Rates of ≥ 10% absolute decline in percent predicted FVC and ≥ 15% absolute decline in percent predicted DLco over 24 months were 31.0% and 23.2%, respectively. Mean times from registry inclusion to categorical absolute decline in percent predicted FVC and percent predicted DLco were 20.1 (standard error [SE] 0.6) months and 23.4 (SE 0.5) months, respectively; mean time from registry inclusion to death was 31.0 (SE 0.9) months. CONCLUSIONS: The PROOF registry is a source of European data characterizing longitudinal clinical outcomes of patients with IPF. Over 12 months of follow-up, pulmonary function remained largely stable in patients with IPF who received pirfenidone for any duration of treatment. Pulmonary function remained similar at 24 months of follow-up, although patient numbers were lower. TRIAL REGISTRATION: PROOF is registered with the relevant authorities in Belgium and Luxembourg, with registration to Comité National d'Éthique et de Recherche (CNER) N201309/03-12 September 2013 and a notification to Comité National de Protection des Données (CNDP) for Luxembourg.

Achieving Thoracic Oncology data collection in Europe: a precursor study in 35 Countries.

BACKGROUND: A minority of European countries have participated in international comparisons with high level data on lung cancer. However, the nature and extent of data collection across the continent is simply unknown, and without accurate data collection it is not possible to compare practice and set benchmarks to which lung cancer services can aspire. METHODS: Using an established network of lung cancer specialists in 37 European countries, a survey was distributed in December 2014. The results relate to current practice in each country at the time, early 2015. The results were compiled and then verified with co-authors over the following months. RESULTS: Thirty-five completed surveys were received which describe a range of current practice for lung cancer data collection. Thirty countries have data collection at the national level, but this is not so in Albania, Bosnia-Herzegovina, Italy, Spain and Switzerland. Data collection varied from paper records with no survival analysis, to well-established electronic databases with links to census data and survival analyses. CONCLUSION: Using a network of committed clinicians, we have gathered validated comparative data reporting an observed difference in data collection mechanisms across Europe. We have identified the need to develop a well-designed dataset, whilst acknowledging what is feasible within each country, and aspiring to collect high quality data for clinical research.

Study design and characteristics of the Luxembourg European Health Examination Survey (EHES-LUX).

BACKGROUND: The European Health Examination Survey in Luxembourg (EHES-LUX) is a population based survey performed from 2013 to 2015 with the aim to establish baseline information on the general health status of the Luxembourg population aged 25 to 64 years. The paper introduces the study design, recruitment method and representativeness of the sample, and summarizes the sociodemographic characteristics of participants and the prevalence of major health outcomes. METHODS: EHES-LUX is based on a random sample representative of the population of Luxembourg based on gender, age and district of residence. The sample size of the study was determined to provide accurate prevalence estimates for major chronic conditions. During two visits, data were collected from participants through a questionnaire (personal data, health status and health care), medical examinations (anthropometric measures, electrocardiogram and spirometry) and biological analysis (blood, urine and hair). Means and frequencies were used to describe the general characteristics of the population and a one-way ANOVA to test the representativeness of the sample and the comparability of participants and non-participants. RESULTS: A total of 1529 individuals participated in this study (participation rate of 24.1%). Differences between participants and non-participants based on gender, age and district of residence were corrected by sampling weights. The mean age (±SD) of participants was 44.9 (±10.1) years, of which 52.8% were women. Based on clinical measurements, nearly 20% of participants were obese and more than one in three participants were overweight. From measurements (respectively from self-report), 22.0% (respectively 12.2%) were hypertensive, 49.3% (respectively 22.5%) had hypercholesterolemia, 3.5% (respectively 3.7%) had diabetes and 7.6% (respectively 6.0%) had depressive symptoms. CONCLUSIONS: This nationwide epidemiological study on the general health status of Luxembourg residents provides updated prevalence estimates on a range of major health conditions. This information can be used by health authorities to evaluate policies and public health initiatives. At European level, prevalence data obtained by this study following the EHES-Reference Committee (EHES-RC) recommendations, will be comparable between European countries participating in this program.

Quantification of SAA1 and SAA2 in lung cancer plasma using the isotype-specific PRM assays.

The quantification of plasma proteins using the high resolution and accurate mass (HR/AM)-based parallel reaction monitoring (PRM) method provides an immediate benefit over the conventional SRM-based method in terms of selectivity. In this study, multiplexed PRM assays were developed to analyze isotypes of serum amyloid A (SAA) proteins in human plasma with a focus on SAA1 and SAA2. Elevated plasma levels of these proteins in patients diagnosed with lung cancer have been reported in previous studies. Since SAA1 and SAA2 are highly homologous, the available immunoassays tend to overestimate their concentrations due to cross-reactivity. On the other hand, when mass spectrometry (MS)-based assays are used, the presence of the several allelic variants may result in a problem of underestimation. In the present study, eight peptides that represent the target proteins at three different levels: isotype-specific (SAA1α,  SAA 1ß,  SAA1γ,  SAA2α,  SAA2ß), protein-specific (SAA1 or SAA2), and pan SAA (SAA1 and SAA2) were chosen to differentiate SAAs in lung cancer plasma samples using a panel of PRM assays. The measurement of specific isotypes, leveraging the analytical performance of PRM, allowed to quantify the allelic variants of both target proteins. The isotypes detected were corroborated with the genetic information obtained from the same samples. The combination of SAA2α and SAA2ß assays representing the total SAA2 concentration demonstrated a superior analytical outcome than the previously used assay on the common peptide when applied to the detection of lung cancer.

Verification of the biomarker candidates for non-small-cell lung cancer using a targeted proteomics approach.

Lung cancer, with its high metastatic potential and high mortality rate, is the worldwide leading cause of cancer-related deaths. High-throughput "omics"-based platforms have accelerated the discovery of biomarkers for lung cancer, and the resulting candidates are to be evaluated for their diagnostic potential as noninvasive biomarkers. The evaluation of the biomarker candidates involves the quantitative measurement of large numbers of proteins in bodily fluids using advanced mass spectrometric techniques. In this study, a robust pipeline based on targeted proteomics was developed for biomarker verification in plasma samples and applied to verifying lung cancer biomarker candidates. Highly multiplexed liquid chromatrography-selected reaction monitoring (LC-SRM) assays for 95 potential tumor markers for non-small-cell lung cancer (NSCLC) were generated to screen plasma samples obtained from 72, early to late stage, patients. A total of 17 proteins were verified as potent tumor markers detectable in plasma and, where available, verified by enzyme-linked immunosorbent assays (ELISAs). A novel plasma-based biomarker, zyxin, fulfilled the criteria for a potential early diagnostic marker for NSCLC.

Quality of Life and Healthcare Resource Use in a Real-world Patient Population with Idiopathic Pulmonary Fibrosis: The PROOF Registry.

INTRODUCTION: The PROOF registry is a prospective, observational study that aimed to monitor disease progression in a real-world cohort of patients with idiopathic pulmonary fibrosis (IPF). Here, longitudinal quality-of-life (QoL) outcomes, healthcare resource use (HCRU), and the association between QoL and mortality in patients enrolled in the PROOF registry are presented. METHODS: QoL outcomes (St. George's Respiratory Questionnaire [SGRQ], EuroQoL-5 dimensions-5 levels Health Questionnaire [EQ-5D-5L], EuroQoL-5 dimensions Health Questionnaire [EQ-5D] visual analogue scale [VAS] and cough VAS) and HCRU were collected for all patients. Associations between baseline QoL and mortality were assessed using univariate and multivariate analyses. During multivariate analyses, individual QoL measures were adjusted for the following covariates: age, sex, percent predicted forced vital capacity, percent predicted diffusing capacity of the lungs for carbon monoxide, smoking status, and supplementary oxygen use at registry inclusion. RESULTS: In total, 277 patients were enrolled in the PROOF registry. During the follow-up period, worsening in cough VAS score, SGRQ symptom score, and SGRQ activity score was observed, while EQ-5D VAS, SGRQ total score, and SGRQ impact score remained stable. During univariate analyses, EQ-5D VAS and all SGRQ sub-scores and total score at baseline were associated with mortality; however, during multivariate analyses, only the SGRQ total score, SGRQ impact score, and SGRQ symptom score at baseline were associated with mortality. During the follow-up period, 261 (94.2%) patients required an outpatient consultation (IPF- or non-IPF-related) and there were 182 hospitalizations in total, most of which were respiratory related (66.5%). CONCLUSIONS: The PROOF registry provided valuable, real-world data on the association between baseline QoL and mortality, and longitudinal HCRU and QoL outcomes in patients with IPF over 24 months and identified that SGRQ may be an independent prognostic factor in IPF.

Factors for severe outcomes following SARS-CoV-2 infection in people with cystic fibrosis in Europe.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in people with cystic fibrosis (pwCF) can lead to severe outcomes. METHODS: In this observational study, the European Cystic Fibrosis Society Patient Registry collected data on pwCF and SARS-CoV-2 infection to estimate incidence, describe clinical presentation and investigate factors associated with severe outcomes using multivariable analysis. RESULTS: Up to December 31, 2020, 26 countries reported information on 828 pwCF and SARS-CoV-2 infection. Incidence was 17.2 per 1000 pwCF (95% CI: 16.0-18.4). Median age was 24 years, 48.4% were male and 9.4% had lung transplants. SARS-CoV-2 incidence was higher in lung-transplanted (28.6; 95% CI: 22.7-35.5) versus non-lung-transplanted pwCF (16.6; 95% CI: 15.4-17.8) (p≤0.001).SARS-CoV-2 infection caused symptomatic illness in 75.7%. Factors associated with symptomatic SARS-CoV-2 infection were age >40 years, at least one F508del mutation and pancreatic insufficiency.Overall, 23.7% of pwCF were admitted to hospital, 2.5% of those to intensive care, and regretfully 11 (1.4%) died. Hospitalisation, oxygen therapy, intensive care, respiratory support and death were 2- to 6-fold more frequent in lung-transplanted versus non-lung-transplanted pwCF.Factors associated with hospitalisation and oxygen therapy were lung transplantation, cystic fibrosis-related diabetes (CFRD), moderate or severe lung disease and azithromycin use (often considered a surrogate marker for Pseudomonas aeruginosa infection and poorer lung function). CONCLUSION: SARS-CoV-2 infection yielded high morbidity and hospitalisation in pwCF. PwCF with forced expiratory volume in 1 s <70% predicted, CFRD and those with lung transplants are at particular risk of more severe outcomes.

Incidence of SARS-CoV-2 in people with cystic fibrosis in Europe between February and June 2020.

BACKGROUND: Viral infections can cause significant morbidity in cystic fibrosis (CF). The current Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) pandemic could therefore have a serious impact on the health of people with CF (pwCF). METHODS: We used the 38-country European Cystic Fibrosis Society Patient Registry (ECFSPR) to collect case data about pwCF and SARS-CoV-2 infection. RESULTS: Up to 30 June 2020, 16 countries reported 130 SARS-CoV-2 cases in people with CF, yielding an incidence of 2.70/1000 pwCF. Incidence was higher in lung-transplanted patients (n=23) versus non-transplanted patients (n=107) (8.43 versus 2.36 cases/1000). Incidence was higher in pwCF versus the age-matched general population in the age groups <15, 15-24, and 25-49 years (p<0.001), with similar trends for pwCF with and without lung transplant. Compared to the general population, pwCF (regardless of transplantation status) had significantly higher rates of admission to hospital for all age groups with available data, and higher rates of intensive care, although not statistically significant. Most pwCF recovered (96.2%), however 5 died, of whom 3 were lung transplant recipients. The case fatality rate for pwCF (3.85%, 95% CI: 1.26-8.75) was non-significantly lower than that of the general population (7.46%; p=0.133). CONCLUSIONS: SARS-CoV-2 infection can result in severe illness and death for pwCF, even for younger patients and especially for lung transplant recipients. PwCF should continue to shield from infection and should be prioritized for vaccination.

Baseline clinical characteristics, comorbidities and prescribed medication in a real-world population of patients with idiopathic pulmonary fibrosis: the PROOF registry.

INTRODUCTION: PROOF (a Prospective Observational Registry to Describe the Disease Course and Outcomes of Idiopathic Pulmonary Fibrosis) is an ongoing, observational registry initiated in 2013 with the aim of collecting real-world data from patients with idiopathic pulmonary fibrosis (IPF). Here, we present comprehensive baseline data, which were collected from patients on registry inclusion. METHODS: Patients with IPF were enrolled across eight centres in Belgium and Luxembourg. Baseline data collected included demographics, diagnostic information and clinical characteristics, including lung function and health-related quality of life. Data on comorbidities and prescribed medication were also collected. RESULTS: A total of 277 patients were enrolled in the PROOF registry. At inclusion, 92.8% and 6.5% of patients had a definite or probable diagnosis of IPF, respectively. Mean per cent predicted forced vital capacity and carbon monoxide diffusing capacity were 80.6% and 46.9%, respectively. Mean St. George's Respiratory Questionnaire total score was 47.0, and mean Cough-Visual Analogue Scale score was 30.5 mm. The most prevalent comorbidities reported at inclusion were gastrointestinal disorders (50.2%), including gastro-oesophageal reflux disease (47.3%) and metabolism and nutrition disorders (39.7%). At inclusion, 67.2% and 2.2% of patients were prescribed pirfenidone and nintedanib, respectively, with treatment initiated either prior to, or at the time of, inclusion. Medication prescribed concomitantly with pirfenidone included antihypertensives (54.8%), statins (37.1%) and prophylactic antithrombotics/anticoagulants (36.6%). CONCLUSION: The PROOF registry provides valuable demographic and clinical data from a real-world population of patients with IPF in Belgium and Luxembourg, demonstrating the high burden of comorbidities and prescribed medication in these patients. Longitudinal data from this patient population will be investigated in future analyses. TRIAL REGISTRATION: PROOF is registered with the relevant authorities in Belgium and Luxembourg, with registration to Comité National d'Éthique et de Recherché (CNER) N201309/03 - 12 September 2013 and a notification to Comité National de Protection des Données (CNDP).