Application of an Artificial Intelligence Model to Detect Alpha-1 Antitrypsin Deficiency: Characterizing the Study Population

BackgroundTrials of disease modifying therapies in Chronic Obstructive Pulmonary Disease (COPD) provide challenges for detecting physiological and patient centred outcomes. The purpose of the current study was to monitor decline in health status in Alpha-1 antitrypsin deficiency (AATD) and determine its’ relationship to conventional physiology.MethodsPatients recruited to the UK-AATD database with a median follow up of 7 years (IQR 5–10) were studied to determine annual change in St George’s Respiratory Questionnaire (SGRQ), FEV1, gas transfer and their feasibility of use in future trials.ResultsAnnual decline in SGRQ had a wide range, was greater for patients with established COPD and correlated with decline in FEV1 (p < 0.0001). Total score decline was greater (p < 0.05) for those with accelerated FEV1 decline (median = 1.07 points/year) compared to those without (median = 0.51). Power calculations indicated effective intervention would not achieve MCID for the SGRQ unless the timeframe was extended for up to 8 years. More than 5000 patients/arm would be required for a statistically significant modest effect over 3 years even in those with rapid FEV1 decline.ConclusionDespite AATD being a rapidly declining form of COPD, deterioration in SGRQ was slow consistent with ageing and the chronic nature of disease progression. Power calculations indicate the numbers needed to detect a difference with disease modifying therapies would be prohibitive especially in this rare cause of COPD. These data have important implications for future study design of disease modifying therapies even in COPD not associated with AATD.

Aim:To evaluate all-cause and liver-associated healthcare resource utilization (HCRU) and costs among patients with alpha-1 antitrypsin deficiency (AATD) with liver disease (LD) and/or lung disease (LgD).Materials & methods:This was a retrospective analysis of linked administrative claims data from the IQVIA PharMetrics® Plus and the IQVIA Ambulatory Electronic Medical Records (AEMR) databases from 1 July 2021 to 31 January 2022. Patients with AATD in the IQVIA PharMetrics Plus database were included with ≥1 inpatient or ≥2 outpatient medical claims ≥90 days apart with a diagnosis of AATD, or with records indicating a protease inhibitor (Pi)*ZZ/Pi*MZ genotype in the IQVIA AEMR database with linkage to IQVIA PharMetrics Plus. For a patient's identified continuous enrollment period, patient time was assigned to health states based on the initial encounter with an LD/LgD diagnosis. A unique index date was defined for each health state, and HCRU and costs were calculated per person-year (PPY).Results:Overall, 5136 adult and pediatric patients from the IQVIA PharMetrics Plus and IQVIA AEMR databases were analyzed. All-cause and liver-associated HCRU and costs were substantially higher following onset of LD/LgD. All-cause cost PPY ranged from US $11,877 in the absence of either LD/LgD to US $74,015 in the presence of both LD and LgD. Among liver transplant recipients in the AATD with LD health state, liver-associated total costs PPY were US $87,329 1-year pre-transplantation and US $461,752 1-year post-transplantation. In the AATD with LgD and AATD with LD and LgD health states, patients who received augmentation therapy were associated with higher all-cause total costs PPY and lower liver-associated total costs PPY than their counterparts who did not receive augmentation therapy.Conclusion:Patients with AATD had increased HCRU and healthcare costs in the presence of LD and/or LgD. HCRU and healthcare costs were highest in the AATD with LD and LgD health state.

Factors associated with advanced liver disease in adults with alpha 1-antitrypsin deficiency

ABSTRACTIntroduction: Distinct pathologies can cause chronic obstructive pulmonary disease (COPD). Emphysema is a COPD-phenotype characterized by destruction of lung parenchyma. Alpha-1 antitrypsin deficiency (AATD) is a genetic cause of emphysema, whereas smoking is the most important risk factor of non-AATD emphysema. A general underappreciation of non-AATD emphysema has hampered progress in the field, and clinical guidelines have prohibited the use of emphysema as a diagnosis. Non-AATD emphysema, however, is far from irrelevant as it associates with dyspnea, reduced exercise capacity and relevant outcome measures.Areas covered: Mechanisms underlying enhanced tissue loss in emphysema are protease/antiprotease imbalance, increased oxidative stress, several fundamental cell biological processes such as programmed cell death and autophagy, and impaired repair mechanisms. Therapeutic options for emphysema vary from smoking cessation to lung volume reduction. Current pharmacological treatments have less favorable effects in emphysematous than in non-emphysematous COPD patients.Expert opinion: We advocate the acknowledgment of non-AATD emphysema as a clinical diagnosis and propose to end the era of bringing all pathologies that may lead to chronic airflow limitation together under the umbrella-term of COPD. Decelerating proteolysis and restoring damage should be main targets in emphysema. Vitamin A/K, hyaluronan, copper and roflumilast are promising candidates.

Background: Alpha-1 antitrypsin deficiency (AATD) is an underdiagnosed condition despite being one of the most common inherited disorders in adults that is associated with an increased risk of developing chronic obstructive pulmonary disease (COPD). The aim was to evaluate the frequency of performing AAT levels and associated factors in COPD patients in an audit conducted in 2021–2022, as well as to compare with a previous audit conducted in 2014–2015. Methods: EPOCONSUL 2021 is a cross-sectional audit that evaluated the outpatient care provided to COPD patients in respiratory clinics in Spain based on available data from medical registries. Results: 4225 patients with a diagnosis of COPD from 45 centers were audited in 2021. A total of 1670 (39.5%) patients underwent AAT determination. Being treated at a specialized COPD outpatient clinic (OR 1.88, p = 0.007), age ≤ 55 years old (OR 1.84, p = 0.007) and a FEV1 < 50% (OR 1.86, p < 0.001) were associated with a higher likelihood of being tested for AAT, while Charlson index ≥ 3 (OR 0.63, p < 0.001) and genotyping of AATD availability (OR 0.42, p < 0.001) showed a statistically significant negative association. The analysis of cases included in respiratory units that participated in both audits showed an increase in the proportion of cases with AAT serum level testing available (adjusted OR 2.81, p < 0.001). The percentage of individuals with serum AAT levels < 60 mg/dL (a severe AATD) was 4%. Conclusions: Our analysis identifies significant improvements in adherence to the recommendation to test AAT levels in COPD patients, performed in 4 out of 10 patients, being more likely at younger ages and with higher COPD severity, and with a detection of severe AATD of 4% among those tested, suggesting that clinicians still perform AAT testing in COPD patients selectively. Therefore, efforts are still needed to optimize AATD screening and establish new early detection strategies to reduce morbidity and mortality in these patients.

Background: Some evidence suggests environmental tobacco smoke (ETS) might cause chronic obstructive pulmonary disease (COPD). We reviewed available epidemiological data in never smokers. Methods:We identified epidemiological studies providing estimates of relative risk (RR) with 95% confidence interval (CI) for various ETS exposure indices. Confounder-adjusted RRs for COPD were extracted, or derived using standard methods. Meta-analyses were conducted for each exposure index, with tests for heterogeneity and publication bias. For the main index (spouse ever smoked or nearest equivalent), analyses investigated variation in RR by location, publication period, study type, sex, diagnosis, study size, confounder adjustment, never smoker definition, and exposure index definition. Results: Twenty-eight relevant studies were identified; nine European or Middle Eastern, nine Asian, eight American and two from multiple countries. Five were prospective, seven case-control and 16 cross-sectional. The COPD definition involved death or hospitalisation in seven studies, GOLD stage 1+ criteria in twelve, and other definitions in nine. For the main index, random-effects meta-analysis of 33 heterogeneous (p<0.001) estimates gave a RR of 1.20 (95%CI 1.08-1.34). Higher estimates for females (1.59,1.16-2.19, n=11) than males (1.29,0.94-1.76, n=7) or sexes combined (1.10,0.99-1.22, n=15 where sex-specific not available), and lower estimates for studies of 150+ cases (1.08,0.97-1.20, n=13) partly explained the heterogeneity. Estimates were higher for Asian studies (1.34,1.08-1.67, n=10), case-control studies (1.55,1.04-2.32, n=8), and COPD mortality or hospitalisation (1.40,1.12-1.74, n=11). Some increase was seen for severer COPD (1.29,1.10-1.52, n=7). Dose-response evidence was heterogeneous. Evidence for childhood (0.88,0.72-1.07, n=2) and workplace (1.12,0.77-1.64, n=4) exposure was limited, but an increase was seen for overall adulthood exposure (1.20,1.03-1.39, n=17). We discuss study weaknesses that may bias estimation of the association of COPD with ETS. Conclusions: Although the evidence suggests ETS increases COPD, study weaknesses and absence of well-designed large studies precludes reliable inference of causality. More definitive evidence is required.

Rationale: The genetic condition alpha-1 antitrypsin deficiency (AATD) is often unrecognized. In adults, AATD can cause common obstructive pulmonary disease and/or liver disease. We previously developed a machine learning model using claims data from a large United States database (Komodo Health), with the goal of identifying patients with AATD symptoms who were undiagnosed but likely had AATD. The objective of this study was to calibrate, refine, and evaluate the diagnostic performance of the model using deidentified patient data from the Cleveland Clinic Electronic Medical Record (EMR) for application within this clinical system. Methods: Cleveland Clinic EMR deidentified patient records from January 1, 1998 to August 15, 2024 were divided into two cohorts; 1) the positive cohort included patients with AATD, as indicated by an AATD diagnosis code and confirmed either by genetic testing or by serum alpha-1 antitrypsin levels; 2) the negative cohort included patients who had symptoms and comorbidities similar to AATD but no records of AATD diagnosis or treatments, in addition to randomly selected control patients. For model training and calibration, only data until the first AATD diagnosis or treatment were used. The data were first split into calibration and validation subsets (80% and 20%, respectively). The model was refined on the calibration data using 3-fold cross-validation, and the calibrated model was then evaluated on the hold-out validation data (unseen during training) to predict AATD. Receiver operating characteristic (ROC) and precision-recall (PR) curves, as well as areas under the curve (AUC) were generated. The final calibrated model was further validated by two Cleveland Clinic pulmonary physicians (UH, JKS) who independently reviewed 60 patient records and assigned probabilities of AATD. Results: Of 21,166 records analyzed, the calibration and the validation datasets consisted of 582 positive and 5864 negative patients. The calibrated model achieved high levels of performance (ROC-AUC=0.89, PR-AUC=0.62) on the hold-out validation subset in distinguishing AATD positive from negative cases (Figure 1). At a discrimination threshold of 0.90, the model achieved high sensitivity=0.70, high specificity=0.92, and balanced accuracy=0.81. Conclusions: A previously developed machine learning model for identifying patients with AATD was successfully calibrated and validated using patient data from the Cleveland Clinic EMR. As measured by ROC and PR on unseen validation data, the model achieved high levels of performance, demonstrating differentiation between AATD and similar conditions or randomly selected controls.

Alpha-1 antitrypsin deficiency

The Registry of the International Society for Heart and Lung Transplantation: Thirty-third Adult Lung and Heart–Lung Transplant Report—2016; Focus Theme: Primary Diagnostic Indications for Transplant

<b>Background:</b> Patients with ZZ (Glu342Lys) alpha-1-antitrypsin deficiency (ZZ-AATD) who received augmentation therapy with alpha-1-antitrypsin (AAT) in randomized controlled trials over 2-3 years, failed to show a significant reduction of the annual decline of the forced expiration volume in one second (FEV₁). <b>Aim and objectives:</b> To compare the trajectory of FEV₁ change during 4 or more years in ZZ-AATD patients with emphysema receiving or not receiving augmentation therapy <b>Methods:</b> A retrospective analysis of FEV₁ values entered in the Alpha-1 International Registry (AIR) of ZZ-AATD patients from five different European countries: Germany, UK, Spain, Italy and The Netherlands. The post-bronchodilator FEV₁ % predicted values for baseline and follow-up over time from patients receiving or not receiving augmentation therapy were analysed in linear mixed effects models. <b>Results:</b> In total 374 patients were analysed: 246 untreated and 128 treated with regular intravenous AAT augmentation therapy. The mean follow-up duration of the untreated group was 8.60 (SD ± 3.34) years and 8.59 (± 2.62) years for the treated group. The mixed effects model analysis showed a mean FEV₁ decline of -0.931% predicted per year (95% confidence interval -1.144 to -0.718) in the untreated group and -1.016 % predicted per year (-1.319 to -0.7145) in the treated group. The likelihood ratio test showed no difference between the two groups (p = 0.71). <b>Conclusion:</b> In our study population, we could not detect significant differences in the annual decline of FEV₁ with AAT augmentation treatment over an average period of 8.6 years. Other approaches are needed to validate any benefit of augmentation therapy.

Introduction: Based on limited studies, it has been proposed that alpha-1 antitrypsin deficiency (A1ATD) is associated with a risk of primary hepatocellular carcinoma (HCC) that exceeds that attributable to cirrhosis alone. Moreover, recent data suggest that PI*Z heterozygotes (e.g., PI*MZ) had an increased risk of HCC. The aim of this study was to evaluate the association between A1ATD/ Z allele and HCC in a cohort of patients with end stage liver disease (ESLD). Methods: Patients evaluated for orthotopic liver transplant at the Cleveland clinic between 2003 and 2014 were included in this retrospective study. Complete data was collected on 696 subjects. The diagnosis of A1ATD was based on phenotype abnormalities (ZZ or MZ), the presence of PAS-positive diastaseresistant (PAS+) globules on liver biopsy, or both. The diagnosis of HCC was based on imaging, biopsy, or examination of the explanted liver. All patients with A1ATD were identified and the prevalence of HCC in this population was calculated. Time-to-event analysis for interval censored data was performed to assess occurrence of HCC in patients with other causes of cirrhosis such as alcoholic liver disease, hepatitis C (HCV), or non-alcoholic steatohepatitis (NASH). Results: A total of 696 subjects were included in the analysis. Seven percent of these had A1ATD. Of subjects without A1ATD, 45% had HCV, 18% had alcoholic liver disease, 18% had NASH, and 18% had other primary diagnosis. Median follow-up time was 3.2 years (25th, 75th percentiles: 1, 5.2), during which time 29% of subjects developed HCC. Crude percentage of HCC was 8.5% in the A1ATD group compared to 30% in the no A1ATD group (p=0.004). Figure 1 presents the cumulative incidence plot for HCC. Subjects with A1ATD were found to have significantly lower HCC rates compared to subjects without A1ATD (p=0.002).Figure 1: Cumulative incidence of HCC in ESLD patients with and without A1ATD.Conclusion: A1ATD was not associated with an increased risk of HCC in a group of patients with ESLD. In fact, patients with cirrhosis and A1ATD were less likely to develop HCC compared to patients with other causes of cirrhosis.

Alpha-1 antitrypsin deficiency (AATD) is a rare genetic condition classically associated with pulmonary emphysema and liver disease. However, the potential link between AATD and other respiratory diseases, particularly bronchial asthma, remains poorly understood and highly debated. This narrative review explores the current evidence regarding the epidemiological, clinical, and pathophysiological relationship between AATD and asthma. Data from prevalence studies show marked variability in the frequency of AATD-associated alleles among asthma patients, ranging from 2.9% to 25.4%, suggesting either a true association or selection biases. Conversely, asthma prevalence among AATD patients also varies widely, from 1.4% to 44.6%, with higher frequencies observed in countries with long-standing national registries. However, methodological inconsistencies and a lack of standardized diagnostic criteria limit the interpretation of these findings. Current evidence is insufficient to support a direct causal role for AATD mutations in asthma development, and no clear impact of AATD on asthma severity or prognosis has been established. Furthermore, there is no conclusive evidence that augmentation therapy is beneficial in asthma patients carrying AATD mutations. Despite these uncertainties, screening for AATD in selected asthma populations—especially those with severe or atypical phenotypes—may be warranted, as recommended by major respiratory societies. Future research should focus on large, well-powered, prospective studies that evaluate the potential pathophysiological interactions between AATD and specific asthma endotypes, particularly T2-low asthma. These efforts may help clarify the relevance of AATD mutations in asthma pathogenesis and identify potential therapeutic targets.

BackgroundCirculating free light chains (FLCs) can alter neutrophil migration, apoptosis and activation and may be a biomarker of autoimmune disease and adaptive immune system activation. These pathogenic roles could be relevant to lung disease in alpha 1 antitrypsin deficiency (A1ATD) and chronic obstructive pulmonary disease (COPD).MethodsTotal combined (c)FLCs were measured using the FreeLite® assay in 547 patients with A1ATD and 327 patients with usual COPD in the stable state, and assessed for association with clinical phenotype, disease severity, airway bacterial colonisation and mortality. Univariate and multivariate analyses were undertaken.ResultsCirculating cFLCs were static in the stable state when measured on 4 occasions in A1ATD and twice in usual COPD. Levels were inversely related to renal function (A1ATD and COPD p = <0.01), and higher in patients with chronic bronchitis (p = 0.019) and airway bacterial colonisation (p = 0.008). After adjusting for renal function and age the relationship between cFLCs and lung function was weak. Kaplan Meier curves showed that cFLC > normal (43.3 mg/L) significantly associated with mortality in both cohorts (A1ATD p = 0.001, COPD p = 0.013).ConclusionscFLCs may be a promising biomarker for risk stratification in A1ATD and COPD.Electronic supplementary materialThe online version of this article (doi:10.1186/s12931-016-0348-1) contains supplementary material, which is available to authorized users.

Background The benefits of pulmonary rehabilitation (PR) on fatigue-resistant skeletal muscle fibre type I have been found to be smaller in COPD patients with alpha-1 antitrypsin deficiency (AATD) than in those without AATD. Alpha-1 antitrypsin (AAT) augmentation therapy was suggested as a potential factor of influence. Whether this finding mirrors different improvements in 6-min walk distance (6MWD) between both groups remains unknown. Methods 140 patients with AATD-related COPD (phenotype PiZZ, FEV 1 : 31 ± 8%pred.) and 280 COPD patients without AATD (FEV 1 : 31 ± 8%pred.) were matched for baseline 6MWD and included in a retrospective analysis. AATD patients were divided into those “on” (AATD AUG+ ) or “off” (AATD AUG- ) augmentation therapy. 6MWD was assessed pre and post an inpatient 4-week PR program. Plasma level of creatinine was analysed at baseline. Results In AATD and COPD patients with comparable initial 6MWD (331 ± 106 m and 326 ± 101 m, p = n.s.), improvements in 6MWD following PR were similar (+49 ± 49 m and +53 ± 52 m, intra-group change: p AUG+ : +51 ± 55 m, AATD AUG- : +47 ± 40 m, p = n.s.). Only in AATD group, higher baseline creatinine levels and lower 6MWD were positive predictors for the PR-related increase in 6MWD. Conclusions Independently of the genetic variant of AAT, COPD patients achieved the same training-related benefit in 6MWD. Augmentation therapy showed no effect on 6MWD adaptation during PR.

Individuals with Alpha-1 antitrypsin deficiency (AATD) have mutations in the SERPINA1 gene causing genetic susceptibility to early onset lung and liver disease that may result in premature death. Environmental interactions have a significant impact in determining the disease phenotype and outcome in AATD. The aim of this study was to assess the impact of smoke exposure on the clinical phenotype of AATD in Ireland.Clinical demographics and available thoracic computerised tomography (CT) imaging were detected from 139 PiZZ individuals identified from the Irish National AATD Registry. Clinical information was collected by questionnaire. Data was analysed to assess AATD disease severity and evaluate predictors of clinical phenotype.Questionnaires were collected from 107/139 (77%) and thoracic CT evaluation was available in 72/107 (67.2%). 74% of respondents had severe Chronic Obstructive Pulmonary Disease (COPD) (GOLD stage C or D). Cigarette smoking was the greatest predictor of impairment in FEV1 and DLCO (%predicted) and the extent of emphysema correlated most significantly with DLCO. Interestingly the rate of FEV1 decline was similar in ex-smokers when compared to never-smokers. Passive smoke exposure in childhood resulted in a greater total pack-year smoking history. Radiological evidence of bronchiectasis was a common finding and associated with increasing age.The Irish National AATD Registry facilitates clinical and basic science research of this condition in Ireland. This study illustrates the detrimental effect of smoke exposure on the clinical phenotype of AATD in Ireland and the benefit of immediate smoking cessation at any stage of lung disease.