Faculty Bibliography

Diagnostic testing is fundamental to medicine. However, studies of diagnostic testing in respiratory medicine vary significantly in terms of their methodology, definitions, and reporting of results. This has led to often conflicting or ambiguous results. To address this issue, a group of 20 respiratory journal editors worked to develop reporting standards for studies of diagnostic testing based on a rigorous methodology to guide authors, peer reviewers, and researchers when conducting studies of diagnostic testing in respiratory medicine. Four key areas are covered, including defining the reference standard of truth, measures of dichotomous test performance when used for dichotomous outcomes, measures of multichotomous test performance for dichotomous outcomes, and what constitutes a useful definition of diagnostic yield. The importance of using contingency tables for reporting results is addressed with examples from the literature. A practical checklist is provided as well for reporting studies of diagnostic testing.

INTRODUCTION:Authors aimed to calculate the percentage up-to-date with testing in the context of lung cancer screening across 5 healthcare systems and evaluate differences according to patient and health system characteristics. METHODS:Lung cancer screening‒eligible individuals receiving care within the five systems in the Population-based Research to Optimize the Screening Process Lung consortium from October 1, 2018 to September 30, 2019 were included in analyses. Data collection was completed on June 15, 2021; final analyses were completed on April 1, 2022. Chest computed tomography scans and patient characteristics were obtained through electronic health records and used to calculate the percentage completing a chest computed tomography scan in the previous 12 months (considered up-to-date). The association of patient and healthcare system factors with being up-to-date was evaluated with adjusted prevalence ratios and 95% CIs using log-binomial regression models. RESULTS:(prevalence ratio=0.83; CI=0.77, 0.88), identifying as Native Hawaiian or other Pacific Islander (prevalence ratio=0.79; CI=0.68, 0.92), and having a decentralized lung cancer screening program (prevalence ratio=0.77; CI=0.74, 0.80) were inversely associated with being up-to-date. CONCLUSIONS:The percentage up-to-date with testing among those eligible for lung cancer screening is well below up-to-date estimates for other types of cancer screening, and disparities in lung cancer screening participation remain.

BACKGROUND:Multiple quality metrics have been recommended to ensure consistent, high-quality execution of screening tests for breast, cervical, colorectal, and lung cancers. However, minimal data exist evaluating the evidence base supporting these recommendations and the consistency of definitions and concepts included within and between cancer types. METHODS:We performed a systematic review for each cancer type using MEDLINE, Embase, and the Cumulative Index to Nursing and Allied Health Literature (CINAHL) from 2010 to April 2020 to identify guidelines from screening programs or professional organizations containing quality metrics for tests used in breast, cervical, colorectal, and lung cancer screening. We abstracted metrics' definitions, target performance levels, and related supporting evidence for test completeness, adequacy (sufficient visualization or collection), accuracy, and safety. RESULTS:We identified 11 relevant guidelines with 20 suggested quality metrics for breast cancer, 5 guidelines with 9 metrics for cervical cancer, 13 guidelines with 18 metrics for colorectal cancer (CRC), and 3 guidelines with 7 metrics for lung cancer. These included 54 metrics related to adequacy (n = 6), test completeness (n = 3), accuracy (n = 33), and safety (n = 12). Target performance levels were defined for 30 metrics (56%). Ten (19%) were supported by evidence, all from breast and CRC, with no evidence cited to support metrics from cervical and lung cancer screening. CONCLUSIONS:Considerably more guideline-recommended test performance metrics exist for breast and CRC screening than cervical or lung cancer. The domains covered are inconsistent among cancers, and few targets are supported by evidence. Clearer evidence-based domains and targets are needed for test performance metrics. REGISTRATION:PROSPERO 2020 CRD42020179139.

BACKGROUND:Deficiencies in risk assessment for patients with pulmonary nodules (PNs) contribute to unnecessary invasive testing and delays in diagnosis. RESEARCH QUESTION:What is the accuracy of a novel PN risk model that includes plasma proteins and clinical factors? How does the accuracy compare with that of an established risk model? STUDY DESIGN AND METHODS:Based on technology using magnetic nanosensors, assays were developed with seven plasma proteins. In a training cohort (n = 429), machine learning approaches were used to identify an optimal algorithm that subsequently was evaluated in a validation cohort (n = 489), and its performance was compared with the Mayo Clinic model. RESULTS:In the training set, we identified a support vector machine algorithm that included the seven plasma proteins and six clinical factors that demonstrated an area under the receiver operating characteristic curve of 0.87 and met other selection criteria. The resulting risk reclassification model (RRM) was used to recategorize patients with a pretest risk of between 10% and 84%, and its performance was assessed across five risk strata (low, ≤ 10%; moderate, 10%-34%; intermediate, 35%-70%; high, 71%-84%; very high, > 85%). Stratification by the RRM decreased the proportion of intermediate-risk patients from 26.7% to 10.8% (P < .001) and increased the low-risk and high-risk strata from 16.8% to 21.9% (P < .001) and from 3.7% to 12.1% (P < .001), respectively. Among patients classified as low risk by the RRM and Mayo Clinic model, the corresponding true-negative to false-negative ratios were 16.8 and 19.5, respectively. Among patients classified as very high risk by the RRM and Mayo Clinic model, the corresponding true-positive to false-positive ratios were 28.5 and 17.0, respectively. Compared with the Mayo Clinic model, the RRM provided higher specificity at the low-risk threshold and higher sensitivity at the very high-risk threshold. INTERPRETATION:The RRM accurately reclassified some patients into low-risk and very high-risk categories, suggesting the potential to improve PN risk assessment.

BACKGROUND:This study used machine learning to develop a 3-year lung cancer risk prediction model with large real-world data in a mostly younger population. METHODS:Over 4.7 million individuals, aged 45 to 65 years with no history of any cancer or lung cancer screening, diagnostic, or treatment procedures, with an outpatient visit in 2013 were identified in Optum's de-identified Electronic Health Record (EHR) dataset. A least absolute shrinkage and selection operator model was fit using all available data in the 365 days prior. Temporal validation was assessed with recent data. External validation was assessed with data from Mercy Health Systems EHR and Optum's de-identified Clinformatics Data Mart Database. Racial inequities in model discrimination were assessed with xAUCs. RESULTS:The model AUC was 0.76. Top predictors included age, smoking, race, ethnicity, and diagnosis of chronic obstructive pulmonary disease. The model identified a high-risk group with lung cancer incidence 9 times the average cohort incidence, representing 10% of patients with lung cancer. Model performed well temporally and externally, while performance was reduced for Asians and Hispanics. CONCLUSIONS:A high-dimensional model trained using big data identified a subset of patients with high lung cancer risk. The model demonstrated transportability to EHR and claims data, while underscoring the need to assess racial disparities when using machine learning methods. IMPACT:This internally and externally validated real-world data-based lung cancer prediction model is available on an open-source platform for broad sharing and application. Model integration into an EHR system could minimize physician burden by automating identification of high-risk patients.

High-throughput extraction of radiomic features from low-dose CT scans can characterize the heterogeneity of the lung parenchyma and potentially aid in identifying subpopulations that may have higher risk of lung diseases, such as COPD, and lung cancer due to inflammation or obstruction of the airways. We aim to determine the feasibility of a lung radiomics phenotyping approach in a lung cancer screening cohort, while quantifying the effect of different CT reconstruction algorithms on phenotype robustness. We identified low-dose CT scans (n = 308) acquired with Siemens Healthineers scanners from patients who completed low-dose CT within our lung cancer screening program between 2015 and 2018 and had two different sets of image reconstructions kernel available (i.e., medium (I30f.), sharp (I50f.)) for the same acquisition. Following segmentation of the lung field, a total of 26 radiomic features were extracted from the entire 3D lung-field using a previously validated fully-automated lattice-based software pipeline, adapted for low-dose CT scans. The lattice in-house software was used to extract features including gray-level histogram, co-occurrence, and run-length descriptors. The lattice approach uses non-overlapping windows for traversing along pixels of images and calculates different features. Each feature was averaged for each scan within a range of lattice window sizes (W) of 4, 8 and 20 mm. The extracted imaging features from both datasets were harmonized to correct for differences in image acquisition parameters. Subsequently, unsupervised hierarchical clustering was applied on the extracted features to identify distinct phenotypic patterns of the lung parenchyma, where consensus clustering was used to identify the optimal number of clusters (K = 2). Differences between phenotypes for demographic and clinical covariates including sex, age, BMI, pack-years of smoking, Lung-RADS and cancer diagnosis were assessed for each phenotype cluster, and then compared across clusters for the two different CT reconstruction algorithms using the cluster entanglement metric, where a lower entanglement coefficient corresponds to good cluster alignment. Furthermore, an independent set of low-dose CT scans (n = 88) from patients with available pulmonary function data on lung obstruction were analyzed using the identified optimal clusters to assess associations to lung obstruction and validate the lung phenotyping paradigm. Heatmaps generated by radiomic features identified two distinct lung parenchymal phenotype patterns across different feature extraction window sizes, for both reconstruction algorithms (P < 0.05 with K = 2). Associations of radiomic-based clusters with clinical covariates showed significant differences for BMI and pack-years of smoking (P < 0.05) for both reconstruction kernels. Radiomic phenotype patterns were more similar across the two reconstructed kernels, when smaller window sizes (W = 4 and 8 mm) were used for radiomic feature extraction, as deemed by their entanglement coefficient. Validation of clustering approaches using cluster mapping for the independent sample with lung obstruction also showed two statistically significant phenotypes (P < 0.05) with significant difference for BMI and smoking pack-years. Radiomic analysis can be used to characterize lung parenchymal phenotypes from low-dose CT scans, which appear reproducible for different reconstruction kernels. Further work should seek to evaluate the effect of additional CT acquisition parameters and validate these phenotypes in characterizing lung cancer screening populations, to potentially better stratify disease patterns and cancer risk.