Search

Objective: To investigate whether an artificial intelligence (AI)–based model can predict tumor invasiveness in patients with multifocal lung adenocarcinoma (MFLA). Patients and Methods: Patients with MFLA who underwent surgical resection were enrolled to a prospective registry trial (NCT01946100). Each identified nodule underwent retrospective computer-aided nodule assessment and risk yield (CANARY)–based AI to determine a quantitative degree of invasiveness. Data regarding age, sex, medical and surgical management, and survival were collected and analyzed. Pathologic review was performed by a pulmonary pathologist with comprehensive histologic subtyping. Results: From January 1, 2013, through December 31, 2018, 68 patients with MFLA underwent at least 1 surgical resection. Five-year survival for the cohort was 91%, and 10-year survival was 73.6%. No significant differences in survival were observed when separated by sex, number, or size of the nodules. A 10-year survival trend was seen when comparing patients with unilateral (100% survival) vs bilateral disease (66%). Retrospective CANARY-based AI analysis demonstrated that the majority of the nodules present at the time of diagnosis (229/302; 75.8%) were classified good, with an average score of 0.19, suggesting indolent clinical behavior and noninvasive pathology. However, AI-CANARY scores of the surgically removed nodules were significantly higher compared with those of the nonresected nodules (P=.001). Conclusion: The long-term survival for patients with N0, M0 MFLA who have undergone surgical resection may approach those of stage I non–small cell lung cancer. CANARY-based AI has the potential to stratify individual nodules to help guide surgical intervention versus observation of nodules. Trial Registration: clinicaltrials.gov Identifier: NCT01946100

Abstract While CT lung cancer screening reduces lung cancer-specific mortality, there are remaining challenges. Radiomic tools promiss to address these challenges, however, they are subject to interobserver variability if semi-automated segmentation techniques are used. Herein we report interobserver variability for two validated radiomic tools, BRODERS (Benign versus aggRessive nODule Evaluation using Radiomic Stratification) and CANARY (Computer-Aided Nodule Assessment and Risk Yield). We retrospectively analyzed the CT images of 95 malignant lung nodules of the adenocarcinoma spectrum using BRODERS and CANARY. Cases were identified at Mayo Clinic (n = 45) and Vanderbilt University Medical Center and Nashville/Veteran Administration Tennessee Valley Health Care System (n = 50). Three observers with different training levels (medical student, internal medicine resident and thoracic radiology fellow) each performed lung nodule segmentation. All methods were carried out in accordance with relevant guidelines and regulations. Interclass correlation coefficients (ICC) of 0.77, 0.98 and 0.97 for the average nodule volume, BRODERS cancer probability and Score Indicative of Lesion Aggression (SILA) which summarizes the distribution of the CANARY exemplars indicated good to excellent reliability, respectively. The dice similarity coefficient was 0.79 and 0.81 for the data sets from the two institutions. BRODERS and CANARY are robust radiomics tools with excellent interobserver variability. These tools are simple and reliable regardless the observer/operator’s level of training.

Summary: India is the third largest CO2 emitter worldwide, and its electricity demand, which is primarily supplied by coal-fired generation, is expected to increase almost threefold over the next twenty years. Here, we simulate 40 scenarios for the 2040 Indian electricity sector, considering uncertainty in future natural gas prices and costs for batteries and variable renewable energy (VRE) technologies, under different CO2 emissions limits and renewable portfolio standard (RPS) targets. We find a large-scale expansion of VRE, particularly, solar PV, in most scenarios. Furthermore, energy storage competes with natural gas and coal to provide flexibility to integrate VRE. Given a set of technology assumptions, policies that explicitly limit CO2 emissions are more cost-effective at reducing emissions than RPS policies. The former are also more effective at reducing air pollution than RPS policies by explicitly penalizing CO2 emissions, thereby reducing coal generation more substantially than RPS policies.

Abstract Background The mechanisms underlying airflow obstruction in COPD cannot be distinguished by standard spirometry. We ascertain whether mathematical modeling of airway biomechanical properties, as assessed from spirometry, could provide estimates of emphysema presence and severity, as quantified by computed tomography (CT) metrics and CT-based radiomics. Methods We quantified presence and severity of emphysema by standard CT metrics (VIDA) and co-registration analysis (ImbioLDA) of inspiratory-expiratory CT in 194 COPD patients who underwent pulmonary function testing. According to percentages of low attenuation area below − 950 Hounsfield Units (%LAA-950insp) patients were classified as having no emphysema (NE) with %LAA-950insp

Abstract Background Heartworm medications and many oral or topical flea and tick products are provided as monthly doses while a newer oral flea/tick product, fluralaner (BRAVECTO® Chew), is re-dosed at a 12-week interval. This study focused on whether there was a difference in the number of heartworm medication doses that were purchased in the 12-months follow-up period for dogs that receive either fluralaner or other flea/tick medications that are dosed monthly. Methods Clinic transaction records of heartworm medication purchases for over 200,000 dogs were examined to compare the purchase of heartworm preventative protection by dog owners that also receive flea and tick medications of differing efficacy durations. Results Annual purchases of heartworm medication for dogs by owners that receive a flea and tick medication dosed at 12-week intervals was incrementally higher than the number of doses purchased for dogs receiving monthly flea and tick medications. The average number of monthly doses per year was slightly over 7 months for both categories of product. The distribution of purchases of monthly doses was also similar between groups. Conclusions Dog owners who purchase a longer-acting flea and tick medication purchase as much heartworm medication annually for their dogs as dog owners who purchase monthly flea and tick medication. On average, dog owners who gave their dog fluralaner obtained significantly more months of heartworm preventative protection compared with dog owners who gave their dog a monthly flea and tick medication, although the biological significance of this increase in doses is very small.

Abstract Background Chronic hypersensitivity pneumonitis (CHP) has a variable disease course. Computer analysis of CT features was used to identify a subset of CHP patients with an outcome similar to patients with idiopathic pulmonary fibrosis (IPF). Methods Consecutive patients with a multi-disciplinary team diagnosis of CHP (n = 116) had pulmonary function tests (FEV1, FVC, DLco, Kco, and a composite physiologic index [CPI]) and CT variables predictive of mortality evaluated by analysing visual and computer-based (CALIPER) parenchymal features: total interstitial lung disease (ILD) extent, honeycombing, reticular pattern, ground glass opacities, pulmonary vessel volume (PVV), emphysema, and traction bronchiectasis. Mean survival was compared between both CHP and IPF patients (n = 185). Results In CHP, visual/CALIPER measures of reticular pattern, honeycombing, visual traction bronchiectasis, and CALIPER ILD extent were predictive of mortality (p 6 · 5% of the lung had a mean survival (35 · 3 ± 6 · 1 months; n = 20/116 [17%]) and rate of disease progression that closely matched IPF patients (38 · 4 ± 2 · 2 months; n = 185). Conclusions Pulmonary vessel volume can identify CHP patients at risk of aggressive disease and a poor IPF-like prognosis.

PURPOSE:Optimization of the clinical management of screen-detected lung nodules is needed to avoid unnecessary diagnostic interventions. Herein we demonstrate the potential value of a novel radiomics-based approach for the classification of screen-detected indeterminate nodules. MATERIAL AND METHODS:Independent quantitative variables assessing various radiologic nodule features such as sphericity, flatness, elongation, spiculation, lobulation and curvature were developed from the NLST dataset using 726 indeterminate nodules (all ≥ 7 mm, benign, n = 318 and malignant, n = 408). Multivariate analysis was performed using least absolute shrinkage and selection operator (LASSO) method for variable selection and regularization in order to enhance the prediction accuracy and interpretability of the multivariate model. The bootstrapping method was then applied for the internal validation and the optimism-corrected AUC was reported for the final model. RESULTS:Eight of the originally considered 57 quantitative radiologic features were selected by LASSO multivariate modeling. These 8 features include variables capturing Location: vertical location (Offset carina centroid z), Size: volume estimate (Minimum enclosing brick), Shape: flatness, Density: texture analysis (Score Indicative of Lesion/Lung Aggression/Abnormality (SILA) texture), and surface characteristics: surface complexity (Maximum shape index and Average shape index), and estimates of surface curvature (Average positive mean curvature and Minimum mean curvature), all with P

[This corrects the article DOI: 10.1371/journal.pone.0196910.].

Lung adenocarcinoma (ADC), the most common lung cancer type, is recognized increasingly as a disease spectrum. To guide individualized patient care, a non-invasive means of distinguishing indolent from aggressive ADC subtypes is needed urgently. Computer-Aided Nodule Assessment and Risk Yield (CANARY) is a novel computed tomography (CT) tool that characterizes early ADCs by detecting nine distinct CT voxel classes, representing a spectrum of lepidic to invasive growth, within an ADC. CANARY characterization has been shown to correlate with ADC histology and patient outcomes. This study evaluated the inter-observer variability of CANARY analysis. Three novice observers segmented and analyzed independently 95 biopsy-confirmed lung ADCs from Vanderbilt University Medical Center/Nashville Veterans Administration Tennessee Valley Healthcare system (VUMC/TVHS) and the Mayo Clinic (Mayo). Inter-observer variability was measured using intra-class correlation coefficient (ICC). The average ICC for all CANARY classes was 0.828 (95% CI 0.76, 0.895) for the VUMC/TVHS cohort, and 0.852 (95% CI 0.804, 0.901) for the Mayo cohort. The most invasive voxel classes had the highest ICC values. To determine whether nodule size influenced inter-observer variability, an additional cohort of 49 sub-centimeter nodules from Mayo were also segmented by three observers, with similar ICC results. Our study demonstrates that CANARY ADC classification between novice CANARY users has an acceptably low degree of variability, and supports the further development of CANARY for clinical application.

Obesity increases the risk for diabetes and cardiovascular events, with a corresponding growth in medical costs. High intensity lifestyle intervention (HILI) is the cornerstone for weight management. We assessed the effectiveness of clinic-based HILI on weight loss and associated clinical outcomes by duration of program participation and comorbid conditions.This was a retrospective cohort study of patients who enrolled in HILI weight management programs at Health Management Resources (HMR) clinics located across the U.S. Patients completed health risk assessments (HRA) and were enrolled for up to 24 months at the time of follow-up HRA. HMR programs provide weekly group coaching to achieve reduced calorie intake, increased fruit/vegetable intake, and physical activity ≥2,000 kcal/wk. A Markov model predicted avoidance of diabetes and cardiovascular events and projected cost savings due to weight loss.Of the 500 patients included in the analysis, 67% were female and mean age was 54.1 years (s.d. 11.6). The baseline weight and BMI were 243.5 lbs (range 144.0-545.0) and 38.8 kg/m2 (range 25.4-85.0), respectively. Overall, patients lost an average of 47.4 lbs (18.9% of initial body weight [IBW]); the amount of weight loss was consistent among those with diabetes/pre-diabetes (50%), high/moderate risk for dyslipidemia (60%), hypertension/pre-hypertension (86%), and severe obesity (37%). The mean IBW lost was 16.4%, 19.3%, 20.7% for ≤6 months (n = 165), 7-12 months (n = 140), 13-24 months (n = 195) of program participation, respectively. The simulation model estimated 22 diabetes and 30 cardiovascular events and $1,992,370 medical costs avoided over 5 years in the 500 patients evaluated.Patients in the HMR clinic-based HILI program achieved substantial weight loss regardless of duration of program participation, risk profile and comorbid status. The HMR program could be an effective strategy to prevent costly diabetes and cardiovascular events, particularly in high risk patients.

Diffuse parenchymal lung diseases (DPLDs) are characterized by widespread pathological changes within the pulmonary tissue that impair the elasticity and gas exchange properties of the lungs. Clinical-radiological diagnosis of these diseases remains challenging and their clinical course is characterized by variable disease progression. These challenges have hindered the introduction of robust objective biomarkers for patient-specific prediction based on specific phenotypes in clinical practice for patients with DPLD. Therefore, strategies facilitating individualized clinical management, staging and identification of specific phenotypes linked to clinical disease outcomes or therapeutic responses are urgently needed. A classification schema consistently reflecting the radiological, clinical (lung function and clinical outcomes) and pathological features of a disease represents a critical need in modern pulmonary medicine. Herein, we report a quantitative stratification paradigm to identify subsets of DPLD patients with characteristic radiologic patterns in an unsupervised manner and demonstrate significant correlation of these self-organized disease groups with clinically accepted surrogate endpoints. The proposed consistent and reproducible technique could potentially transform diagnostic staging, clinical management and prognostication of DPLD patients as well as facilitate patient selection for clinical trials beyond the ability of current radiological tools. In addition, the sequential quantitative stratification of the type and extent of parenchymal process may allow standardized and objective monitoring of disease, early assessment of treatment response and mortality prediction for DPLD patients.

Abstract Background Fermentation of xylose, the major component in hemicellulose, is essential for economic conversion of lignocellulosic biomass to fuels and chemicals. The yeast Scheffersomyces stipitis (formerly known as Pichia stipitis) has the highest known native capacity for xylose fermentation and possesses several genes for lignocellulose bioconversion in its genome. Understanding the metabolism of this yeast at a global scale, by reconstructing the genome scale metabolic model, is essential for manipulating its metabolic capabilities and for successful transfer of its capabilities to other industrial microbes. Results We present a genome-scale metabolic model for Scheffersomyces stipitis, a native xylose utilizing yeast. The model was reconstructed based on genome sequence annotation, detailed experimental investigation and known yeast physiology. Macromolecular composition of Scheffersomyces stipitis biomass was estimated experimentally and its ability to grow on different carbon, nitrogen, sulphur and phosphorus sources was determined by phenotype microarrays. The compartmentalized model, developed based on an iterative procedure, accounted for 814 genes, 1371 reactions, and 971 metabolites. In silico computed growth rates were compared with high-throughput phenotyping data and the model could predict the qualitative outcomes in 74% of substrates investigated. Model simulations were used to identify the biosynthetic requirements for anaerobic growth of Scheffersomyces stipitis on glucose and the results were validated with published literature. The bottlenecks in Scheffersomyces stipitis metabolic network for xylose uptake and nucleotide cofactor recycling were identified by in silico flux variability analysis. The scope of the model in enhancing the mechanistic understanding of microbial metabolism is demonstrated by identifying a mechanism for mitochondrial respiration and oxidative phosphorylation. Conclusion The genome-scale metabolic model developed for Scheffersomyces stipitis successfully predicted substrate utilization and anaerobic growth requirements. Useful insights were drawn on xylose metabolism, cofactor recycling and mechanism of mitochondrial respiration from model simulations. These insights can be applied for efficient xylose utilization and cofactor recycling in other industrial microorganisms. The developed model forms a basis for rational analysis and design of Scheffersomyces stipitis metabolic network for the production of fuels and chemicals from lignocellulosic biomass.

Abstract Background The nuclear receptor peroxisome proliferator-activated receptor alpha (PPARα) regulates responses to chemical or physical stress in part by altering expression of genes involved in proteome maintenance. Many of these genes are also transcriptionally regulated by heat shock (HS) through activation by HS factor-1 (HSF1). We hypothesized that there are interactions on a genetic level between PPARα and the HS response mediated by HSF1. Results Wild-type and PPARα-null mice were exposed to HS, the PPARα agonist WY-14,643 (WY), or both; gene and protein expression was examined in the livers of the mice 4 or 24 hrs after HS. Gene expression profiling identified a number of Hsp family members that were altered similarly in both mouse strains. However, most of the targets of HS did not overlap between strains. A subset of genes was shown by microarray and RT-PCR to be regulated by HS in a PPARα-dependent manner. HS also down-regulated a large set of mitochondrial genes specifically in PPARα-null mice that are known targets of PPARγ co-activator-1 (PGC-1) family members. Pretreatment of PPARα-null mice with WY increased expression of PGC-1β and target genes and prevented the down-regulation of the mitochondrial genes by HS. A comparison of HS genes regulated in our dataset with those identified in wild-type and HSF1-null mouse embryonic fibroblasts indicated that although many HS genes are regulated independently of both PPARα and HSF1, a number require both factors for HS responsiveness. Conclusions These findings demonstrate that the PPARα genotype has a dramatic effect on the transcriptional targets of HS and support an expanded role for PPARα in the regulation of proteome maintenance genes after exposure to diverse forms of environmental stress including HS.

Abstract Background Clustering techniques are routinely used in gene expression data analysis to organize the massive data. Clustering techniques arrange a large number of genes or assays into a few clusters while maximizing the intra-cluster similarity and inter-cluster separation. While clustering of genes facilitates learning the functions of un-characterized genes using their association with known genes, clustering of assays reveals the disease stages and subtypes. Many clustering algorithms require the user to specify the number of clusters a priori. A wrong specification of number of clusters generally leads to either failure to detect novel clusters (disease subtypes) or unnecessary splitting of natural clusters. Results We have developed a novel method to find the number of clusters in gene expression data. Our procedure evaluates different partitions (each with different number of clusters) from the clustering algorithm and finds the partition that best describes the data. In contrast to the existing methods that evaluate the partitions independently, our procedure considers the dynamic rearrangement of cluster members when a new cluster is added. Partition quality is measured based on a new index called Net InFormation Transfer Index (NIFTI) that measures the information change when an additional cluster is introduced. Information content of a partition increases when clusters do not intersect and decreases if they are not clearly separated. A partition with the highest Total Information Content (TIC) is selected as the optimal one. We illustrate our method using four publicly available microarray datasets. Conclusion In all four case studies, the proposed method correctly identified the number of clusters and performs better than other well known methods. Our method also showed invariance to the clustering techniques.

Abstract Background Time-course microarray experiments are being increasingly used to characterize dynamic biological processes. In these experiments, the goal is to identify genes differentially expressed in time-course data, measured between different biological conditions. These differentially expressed genes can reveal the changes in biological process due to the change in condition which is essential to understand differences in dynamics. Results In this paper, we propose a novel method for finding differentially expressed genes in time-course data and across biological conditions (say C1 and C2). We model the expression at C1 using Principal Component Analysis and represent the expression profile of each gene as a linear combination of the dominant Principal Components (PCs). Then the expression data from C2 is projected on the developed PCA model and scores are extracted. The difference between the scores is evaluated using a hypothesis test to quantify the significance of differential expression. We evaluate the proposed method to understand differences in two case studies (1) the heat shock response of wild-type and HSF1 knockout mice, and (2) cell-cycle between wild-type and Fkh1/Fkh2 knockout Yeast strains. Conclusion In both cases, the proposed method identified biologically significant genes.