WLWassim W. Labaki

Wassim W. Labaki

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wassim W. Labaki has a total of 350 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Chest CT-Based Machine Learning for Predicting Response to Lung Volume Reduction Surgery: A Pilot Study

    by Wassim Labaki, Kiran Lagisetty, Rishindra Reddy, Catherine Meldrum, Max Wayne, Jeffrey Curtis, Maor Sauler, Swaraj Bose, Susan Murray, John Oyer, et al.

    Background: Response to lung volume reduction surgery (LVRS) is highly variable, underscoring the need for reliable clinical tools to predict benefit. Aim: Develop chest CT-based machine learning (ML) approaches to improve patient selection for LVRS. Methods: We retrospectively studied 47 patients with upper-lung-predominant emphysema who underwent bilateral LVRS at our center. To distinguish responders (6-month post-LVRS FEV1 improvement ≥250 mL), we applied a supervised feature-agnostic dictionary learning model to pre-LVRS chest CTs (train: n=37; test: n=10). The model sampled 3D image patches (32 x 32 x 32 voxels), learned latent features, and assigned patches to response-specific dictionaries. Patch probabilities ≤0.5 were assigned to the non-benefit dictionary, and >0.5 to the benefit dictionary. Results: Patients (55% female) had a mean age 58.7 ± 8.5 years and pre-LVRS FEV1 0.79 ± 0.22 L (30.1 ± 8.0 % predicted). Overall, 22 patients (47%) were responders (17/37 in training set; 5/10 in test set). Using Youden’s index, responder classification was determined as having ≥52% of patches in the benefit dictionary. In the test set, the model correctly classified the response status of 8 patients (80%). Representative CT images with overlaid ML-derived probability maps are shown for a responder (Fig 1A) and non-responder (Fig 1B). Conclusion: Our CT ML model enables response signature discovery and shows promise for predicting LVRS outcomes. Larger cohorts are needed for validation and generalizability. erj;68/suppl_70/OA1297/F1 F1 F1

  • Open Access

    Airway Mucus Plugs in Asthma and COPD: Pathobiology, Imaging, and Implications for Clinical Trials

    by Christopher B Bosma, Shawn D Aaron, Bartolome R Celli, Grace Parraga, Sally Seymour, George R Washko, James P Allinson, Federico Baraldi, Richard C Boucher, Mario Castro, et al.

    Mucus plugs have been previously recognized as an important pathological feature in asthma and COPD, but their clinical role in these diseases has not been explored in-depth until recently. Mucus plug formation is driven by mucus hyperconcentration, changes in mucus viscoelastic properties, impaired clearance, and mucociliary collapse. Scoring systems, such as the bronchopulmonary segment mucus plug score, have been used to associate greater mucus plug burden with poor clinical outcomes. Additional scoring methods obtained through quantitative image processing are currently under development. Mucus plug burden has been associated with greater exacerbations and spirometric decline in both asthma and COPD, as well as greater mortality in COPD. Recently, mucus plug burden has been used as an endpoint in clinical trials to evaluate the effectiveness of biologic therapies in asthma; multiple biologic therapies demonstrated decreases in mucus plug burden and associated improvements in spirometry with treatment. Together, this data suggests mucus plugs may be a treatable trait in asthma and COPD. Mucus plug burden has current clinical, phenotypic, and predictive utility and shows promise as a future biomarker. Increased incorporation into clinical trials, expanded evidence of treatment effect, and standardization of methodology and imaging protocols will be needed. CT-detection of mucus plug burden is ready for greater incorporation into both research outcomes and clinical care.


  • Enhancing patient selection for lung volume reduction surgery: a novel quantitative CT approach

    by Wassim W Labaki, Charles R Hatt, Sundaresh Ram, Craig J Galbán, Swaraj Bose, Susan Murray, Catherine A Meldrum, Kiran H Lagisetty, Rishindra M Reddy, Ella A Kazerooni, et al.

  • Food Insecurity is Associated with COPD Prevalence and Mortality: Evidence from U.S. County-Level Data

    by Katherine E Goodenberger, Swaraj Bose, Susan K Murray, Christopher B Bosma, MeiLan K Han, Jeffrey L Curtis, Wassim W Labaki

    Rationale: Although unreliable access to healthy food has been linked to lower lung function, a higher burden of respiratory symptoms, and more frequent respiratory exacerbations in individuals with COPD, its association with COPD prevalence and mortality remains understudied. Objective: To determine the associations between food insecurity and COPD prevalence and COPD mortality at the county level in the United States. Methods: We obtained 2018 U.S. county-level data on food insecurity prevalence (FI%) and the Food Environment Index (FEI; lower values indicate worse food desert conditions) from County Health Rankings. We then queried the CDC’s National Environmental Public Health Tracking and WONDER databases for county-level COPD prevalence (2018) and COPD-related mortality (2018-2020), respectively. We constructed negative binomial regression models adjusted for demographic, socioeconomic, and health factors to examine the associations of FI% and FEI with COPD prevalence and mortality. The mortality model was additionally adjusted for county COPD prevalence. Results: Counties with FI% at or above the median (13.2%) and those with FEI below the median (7.6) had lower median household income, lower primary care physician density, higher average daily PM2.5 concentration, and higher prevalence of poverty, uninsured status, rural residence and cigarette smoking (P < .001 for all analyses). In fully adjusted models, a 1% higher FI% was associated with a 1.62% higher COPD prevalence (95% CI 1.40-1.83%; P < .001), and a 1-unit lower FEI was associated with a 1.85% higher COPD prevalence (95% CI 1.17-2.54%; P < .001). A 1% higher FI% was independently associated with a 3.54% increase in COPD-related mortality (95% CI 2.86-4.22%; P < .001), and a 1-unit lower FEI with a 10.05% increase in COPD-related mortality (95% CI 7.82-12.27%; P < .001). Conclusion: Unreliable food access is associated with higher COPD prevalence and mortality at the county level. These results suggest that improving food access may be a target for improving population-level COPD outcomes.


  • Respiratory mortality in chronic obstructive pulmonary disease: fixed ratio versus lower limit of normal in smokers

    by Surya P Bhatt, Sandeep Bodduluri, Mark T Dransfield, MeiLan K Han, Elizabeth A Regan, Wassim A Labaki, Spyridon Fortis, Edwin K Silverman, Arie Nakhmani


  • Mapping the trajectory from pre-COPD to COPD: predictive value of symptoms, imaging, and physiologic abnormalities

    by Nathan Zhang, Nicolas Gargurevich, Susan Murray, Christopher B Bosma, Jeffrey L Curtis, Fernando J Martinez, MeiLan K Han, Wassim W Labaki

  • Open Access

    Pre-COPD: Impact on prevention, detection, and treatment

    by Christopher B. Bosma, Wassim W. Labaki, MeiLan K. Han


  • Quantitative Computed Tomography Measures of Lung Fibrosis and Outcomes in the National Lung Screening Trial

    by Jennifer M. Wang, Swaraj Bose, Susan Murray, Wassim W. Labaki, Ella A. Kazerooni, Jonathan H. Chung, Kevin R. Flaherty, MeiLan K. Han, Charles R. Hatt, Justin M. Oldham

    Rationale: Incidental features of interstitial lung disease (ILD) are commonly observed on chest computed tomography (CT) scans and are independently associated with poor outcomes. Although most studies to date have relied on qualitative assessments of ILD, quantitative imaging algorithms have the potential to effectively detect ILD and assist in risk stratification for population-based cohorts. Objectives: To determine whether quantitative measures of ILD are associated with clinically relevant outcomes in the NLST (National Lung Screening Trial). Methods: Quantitative measures of ILD were generated using low-dose CT (LDCT) data collected as part of the NLST and processed with Computer-Aided Lung Informatics for Pathology Evaluation and Ratings (CALIPER) and deep learning–based usual interstitial pneumonia (DL-UIP) algorithms (Imbio Inc.). A multivariable Cox proportional hazard regression model was used to test the association between ILD measures (percentage ground-glass opacity, reticular opacity, and honeycombing of total lung volume and binary DL-UIP classification) and all-cause mortality. Secondary outcomes of incident lung cancer and lung cancer mortality were also explored. Results: Quantitative CT data were generated in 11,518 individuals. Mean age was 61.5 years, and 58.7% were male. An increased risk of all-cause mortality was observed for each percentage increase in CALIPER-derived ground-glass opacity (hazard ratio [HR], 1.02; 95% confidence interval [CI], 1.01–1.02), reticular opacity (HR, 1.18; 95% CI, 1.12–1.24), and honeycombing (HR, 6.23; 95% CI, 4.23–9.16). Individuals with a positive DL-UIP classification pattern had a 4.8-fold increased risk of all-cause mortality (HR, 4.75; 95% CI, 2.50–9.04). CALIPER-derived reticular opacity was also associated with increased lung cancer–specific mortality. No quantitative measures of ILD were associated with incident lung cancer. Conclusions: Quantitative measures of ILD on LDCT are associated with clinically relevant endpoints in a large at-risk population of individuals with tobacco use history.


  • Association of Lung Quantitative CT Scan Textures With Systemic Inflammation and Mortality in COPD

    by Hira A. Awan, Muhammad F.A. Chaudhary, Anthony D. El-Sokkary, Eric A. Hoffman, Alejandro P. Comellas, Junfeng Guo, Igor Z. Barjaktarevic, R. Graham Barr, Surya P. Bhatt, Sandeep Bodduluri, et al.


  • Temporal Exploration of Chronic Obstructive Pulmonary Disease Phenotypes: Insights from the COPDGene and SPIROMICS Cohorts

    by Alexander J. Bell, Sundaresh Ram, Wassim W. Labaki, Susan Murray, Ella A. Kazerooni, Stefanie Galban, Fernando J. Martinez, Charles R. Hatt, Jennifer M. Wang, Vladimir Ivanov, et al.

    Rationale: Chronic obstructive pulmonary disease (COPD) exhibits considerable progression heterogeneity. We hypothesized that elastic principal graph analysis (EPGA) would identify distinct clinical phenotypes and their longitudinal relationships. Objectives: Our primary objective was to create a map of COPD phenotypes and their connectivity using EPGA. Secondarily, we used longitudinal and external data sets to test the validity and reproducibility of this map. Methods: Cross-sectional data from 8,972 tobacco-exposed COPDGene participants, with and without COPD, were used to train a model with EPGA, using thirty clinical, physiologic and CT features. 4,585 participants from COPDGene Phase 2 were used to test longitudinal trajectories. 2,652 participants from SPIROMICS tested external reproducibility. Measurements and Main Results: Our analysis used cross-sectional data to create an elastic principal tree, where time is associated with distance on the tree. Six clinically distinct tree segments were identified that differed by lung function, symptoms, and CT features: Subclinical (SC); Parenchymal Abnormality (PA); Chronic Bronchitis (CB); Emphysema Male (EM); Emphysema Female (EF); and Severe Airways (SA) disease. 5-year data from COPDGene mapped longitudinal changes onto the tree, and longitudinal trajectories demonstrated a net flow of patients from SC towards EM and EF, including trajectories through airway disease predominant phenotypes, CB and SA. Cross-sectional SPIROMICS data projected onto the tree showed clinically similar patient groupings. Conclusions: This novel analytic methodology provides an approach to defining longitudinal phenotypic trajectories using cross sectional data. These insights are clinically relevant and could facilitate precision therapy and future trials to modify disease progression.