scholarly journals Prediction of COPD risk accounting for time-varying smoking exposures

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248535
Author(s):  
Joanne T. Chang ◽  
Rafael Meza ◽  
David T. Levy ◽  
Douglas Arenberg ◽  
Jihyoun Jeon
Keyword(s):  
Prediction Model ◽  
Risk Prediction ◽  
Cox Regression ◽  
The United States ◽  
Risk Prediction Model ◽  
Health Study ◽  
Time Varying ◽  
Smoking Duration ◽  
Summary Measures ◽  
Time Varying Covariates

Rationale Chronic Obstructive Pulmonary Disease (COPD) is the fourth leading cause of death in the United States. Studies have primarily assessed the relationship between smoking on COPD risk focusing on summary measures, like smoking status. Objective Develop a COPD risk prediction model incorporating individual time-varying smoking exposures. Methods The Nurses’ Health Study (N = 86,711) and the Health Professionals Follow-up Study (N = 39,817) data was used to develop a COPD risk prediction model. Data was randomly split in 50–50 samples for model building and validation. Cox regression with time-varying covariates was used to assess the association between smoking duration, intensity and year-since-quit and self-reported COPD diagnosis incidence. We evaluated the model calibration as well as discriminatory accuracy via the Area Under the receiver operating characteristic Curve (AUC). We computed 6-year risk of COPD incidence given various individual smoking scenarios. Results Smoking duration, year-since-quit (if former smokers), sex, and interaction of sex and smoking duration are significantly associated with the incidence of diagnosed COPD. The model that incorporated time-varying smoking variables yielded higher AUCs compared to models using only pack-years. The AUCs for the model were 0.80 (95% CI: 0.74–0.86) and 0.73 (95% CI: 0.70–0.77) for males and females, respectively. Conclusions Utilizing detailed smoking pattern information, the model predicts COPD risk with better accuracy than models based on only smoking summary measures. It might serve as a tool for early detection programs by identifying individuals at high-risk for COPD.

scholarly journals Identification of a Ferroptosis-Related LncRNA Signature as a Novel Prognosis Model for Lung Adenocarcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Lu Lu ◽  
Le-Ping Liu ◽  
Qiang-Qiang Zhao ◽  
Rong Gui ◽  
Qin-Yu Zhao
Keyword(s):  
Regression Analysis ◽  
Prediction Model ◽  
Lung Adenocarcinoma ◽  
Tumor Cells ◽  
Risk Prediction ◽  
Prognostic Value ◽  
Cox Regression ◽  
Risk Prediction Model ◽  
Functional Enrichment ◽  
Cox Regression Analysis

Lung adenocarcinoma (LUAD) is a highly heterogeneous malignancy, which makes prognosis prediction of LUAD very challenging. Ferroptosis is an iron-dependent cell death mechanism that is important in the survival of tumor cells. Long non-coding RNAs (lncRNAs) are considered to be key regulators of LUAD development and are involved in ferroptosis of tumor cells, and ferroptosis-related lncRNAs have gradually emerged as new targets for LUAD treatment and prognosis. It is essential to determine the prognostic value of ferroptosis-related lncRNAs in LUAD. In this study, we obtained RNA sequencing (RNA-seq) data and corresponding clinical information of LUAD patients from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) database and ferroptosis-related lncRNAs by co-expression analysis. The best predictors associated with LUAD prognosis, including C5orf64, LINC01800, LINC00968, LINC01352, PGM5-AS1, LINC02097, DEPDC1-AS1, WWC2-AS2, SATB2-AS1, LINC00628, LINC01537, LMO7DN, were identified by Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression analysis, and the LUAD risk prediction model was successfully constructed. Kaplan-Meier analysis, receiver operating characteristic (ROC) time curve analysis and univariate and multivariate Cox regression analysis and further demonstrated that the model has excellent robustness and predictive ability. Further, based on the risk prediction model, functional enrichment analysis revealed that 12 prognostic indicators involved a variety of cellular functions and signaling pathways, and the immune status was different in the high-risk and low-risk groups. In conclusion, a risk model of 12 ferroptosis related lncRNAs has important prognostic value for LUAD and may be ferroptosis-related therapeutic targets in the clinic.

scholarly journals Prediction of first cardiovascular disease event in 2.9 million individuals using Danish administrative healthcare data: a nationwide, registry-based derivation and validation study

2021 ◽  
Author(s):  
Daniel Mølager Christensen ◽  
Matthew Phelps ◽  
Thomas Gerds ◽  
Morten Malmborg ◽  
Anne-Marie Schjerning ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Prediction Model ◽  
Risk Prediction ◽  
Sex Education ◽  
Cox Regression ◽  
Population Level ◽  
Risk Prediction Model ◽  
Lipid Lowering ◽  
Chronic Obstructive ◽  
Cvd Risk

Abstract Aims To derive and validate a risk prediction model with nationwide coverage to predict individual and population-level risk of cardiovascular disease (CVD). Methods and Results All 2.98 million Danish residents aged 30-85 years free of CVD were included on January 1, 2014 and followed through December 31, 2018 using nationwide administrative healthcare registries. Model predictors and outcome were pre-specified. Predictors were: Age, sex, education, use of antithrombotic, blood pressure-lowering, glucose-lowering, or lipid-lowering drugs, and a smoking proxy of smoking-cessation drug use or chronic obstructive pulmonary disease. Outcome was 5-year risk of first CVD event, a combination of ischemic heart disease, heart failure, peripheral artery disease, stroke, or cardiovascular death. Predictions were computed using cause-specific Cox regression models. The final model fitted in the full data was internally-externally validated in each Danish Region. The model was well-calibrated in all Regions. Areas under the curve (AUC) and Brier scores ranged from 76.3% to 79.6% and 3.3 to 4.4. The model was superior to an age-sex benchmark model with differences in AUC and Brier scores ranging from 1.2% to 1.5% and -0.02 to -0.03. Average predicted risks in each Danish municipality ranged from 2.8% to 5.9%. Predicted risks for a 66-year-old ranged from 2.6% to 25.3%. Personalized predicted risks across ages 30-85 were presented in an online calculator (https://hjerteforeningen.shinyapps.io/cvd-risk-manuscript/). Conclusion A CVD risk prediction model based solely on nationwide administrative registry data provided accurate prediction of personal and population-level 5-year first CVD event risk in the Danish population. This may inform clinical and public health primary prevention efforts.

scholarly journals Exploring the Intersection between Social Determinants of Health and Unmet Dental Care Needs Using Deep Learning

2020 ◽  
Vol 17 (19) ◽  
pp. 7286
Author(s):  
Man Hung ◽  
Eric S. Hon ◽  
Bianca Ruiz-Negron ◽  
Evelyn Lauren ◽  
Ryan Moffat ◽  
...  
Keyword(s):  
Prediction Model ◽  
Social Determinants Of Health ◽  
Risk Prediction ◽  
Social Determinants ◽  
Dental Care ◽  
The United States ◽  
Risk Prediction Model ◽  
Determinants Of Health ◽  
Care Needs ◽  
Dental Care Needs

The goals of this study were to develop a risk prediction model in unmet dental care needs and to explore the intersection between social determinants of health and unmet dental care needs in the United States. Data from the 2016 Medical Expenditure Panel Survey were used for this study. A chi-squared test was used to examine the difference in social determinants of health between those with and without unmet dental needs. Machine learning was used to determine top predictors of unmet dental care needs and to build a risk prediction model to identify those with unmet dental care needs. Age was the most important predictor of unmet dental care needs. Other important predictors included income, family size, educational level, unmet medical needs, and emergency room visit charges. The risk prediction model of unmet dental care needs attained an accuracy of 82.6%, sensitivity of 77.8%, specificity of 87.4%, precision of 82.9%, and area under the curve of 0.918. Social determinants of health have a strong relationship with unmet dental care needs. The application of deep learning in artificial intelligence represents a significant innovation in dentistry and enables a major advancement in our understanding of unmet dental care needs on an individual level that has never been done before. This study presents promising findings and the results are expected to be useful in risk assessment of unmet dental care needs and can guide targeted intervention in the general population of the United States.

scholarly journals Identification of Tumor Mutation Burden and Immune Infiltrates in Hepatocellular Carcinoma Based on Multi-Omics Analysis

2021 ◽  
Vol 7 ◽  
Author(s):  
Lu Yin ◽  
Liuzhi Zhou ◽  
Rujun Xu
Keyword(s):  
T Cells ◽  
Prediction Model ◽  
Risk Prediction ◽  
Immune Cell ◽  
Cox Regression ◽  
Area Under The Curve ◽  
Risk Prediction Model ◽  
Activated T Cells ◽  
Immune Infiltration ◽  
Differential Genes

We aimed to explore the tumor mutational burden (TMB) and immune infiltration in HCC and investigate new biomarkers for immunotherapy. Transcriptome and gene mutation data were downloaded from the GDC portal, including 374 HCC samples and 50 matched normal samples. Furthermore, we divided the samples into high and low TMB groups, and analyzed the differential genes between them with GO, KEGG, and GSEA. Cibersort was used to assess the immune cell infiltration in the samples. Finally, univariate and multivariate Cox regression analyses were performed to identify differential genes related to TMB and immune infiltration, and a risk prediction model was constructed. We found 10 frequently mutated genes, including TP53, TTN, CTNNB1, MUC16, ALB, PCLO, MUC, APOB, RYR2, and ABCA. Pathway analysis indicated that these TMB-related differential genes were mainly enriched in PI3K-AKT. Cibersort analysis showed that memory B cells (p = 0.02), CD8+ T cells (p = 0.09), CD4+ memory activated T cells (p = 0.07), and neutrophils (p = 0.06) demonstrated a difference in immune infiltration between high and low TMB groups. On multivariate analysis, GABRA3 (p = 0.05), CECR7 (p < 0.001), TRIM16 (p = 0.003), and IL7R (p = 0.04) were associated with TMB and immune infiltration. The risk prediction model had an area under the curve (AUC) of 0.69, suggesting that patients with low risk had better survival outcomes. Our study demonstrated for the first time that CECR7, GABRA3, IL7R, and TRIM16L were associated with TMB and promoted antitumor immunity in HCC.

scholarly journals Identification of Tumor Mutation Burden and Immune Infiltrates in Hepatocellular Carcinoma Based on Multi-Omics Analysis

2020 ◽  
Author(s):  
Lu Yin ◽  
Liuzhi Zhou ◽  
Rujun Xu
Keyword(s):  
T Cells ◽  
Prediction Model ◽  
Risk Prediction ◽  
Immune Cell ◽  
Cox Regression ◽  
Area Under The Curve ◽  
Risk Prediction Model ◽  
Activated T Cells ◽  
Immune Infiltration ◽  
Differential Genes

Abstract Background: We aimed to explore the tumor mutational burden (TMB) and immune infiltration in HCC and investigate new biomarkers for immunotherapy.Methods: Transcriptome and gene mutation data were downloaded from the GDC portal, including 374 HCC samples and 50 matched samples. Furthermore, we divided the samples into high and low TMB groups, and analyzed the differential genes between them with GO, KEGG, and GSEA. Cibersort was used to assess the immune cell infiltration in the samples. Finally, univariate and multivariate Cox regression analyses were performed to identify differential genes related to TMB and immune infiltration, and a risk prediction model was constructed.Results: We found 10 frequently mutated genes, including TP53, TTN, CTNNB1, MUC16, ALB, PCLO, MUC, APOB, RYR2, and ABCA. Pathway analysis indicated that these TMB-related differential genes were mainly enriched in PI3K-AKT. Cibersort analysis showed that memory B cells (P=0.02), CD8+ T cells (P=0.09), CD4+ memory activated T cells (P=0.07), and neutrophils (P=0.06) demonstrated a difference in immune infiltration between high and low TMB groups. On multivariate analysis, GABRA3 (P=0.05), CECR7 (P<0.001), TRIM16 (P=0.003), and IL7R (P=0.04) were associated with TMB and immune infiltration. The risk prediction model had an area under the curve (AUC) of 0.69, suggesting that patients with low risk had better survival outcomes.Conclusions: Our study demonstrated for the first time that CECR7, GABRA3, IL7R, and TRIM16L mutations were associated with TMB and promoted antitumor immunity in HCC.

scholarly journals Development of a Disease Risk Prediction Model for Downy Mildew (Peronospora sparsa) in Boysenberry

2014 ◽  
Vol 104 (1) ◽  
pp. 50-56 ◽  
Author(s):  
Kwang Soo Kim ◽  
Robert M. Beresford ◽  
Monika Walter
Keyword(s):  
High Risk ◽  
Prediction Model ◽  
Fuzzy Sets ◽  
Downy Mildew ◽  
Risk Prediction ◽  
Disease Risk ◽  
The United States ◽  
Risk Prediction Model ◽  
Correct Identification ◽  
Cart Analysis

Downy mildew caused by Peronospora sparsa has resulted in serious production losses in boysenberry (Rubus hybrid), blackberry (Rubus fruticosus), and rose (Rosa sp.) in New Zealand, Mexico, and the United States and the United Kingdom, respectively. Development of a model to predict downy mildew risk would facilitate development and implementation of a disease warning system for efficient fungicide spray application in the crops affected by this disease. Because detailed disease observation data were not available, a two-step approach was applied to develop an empirical risk prediction model for P. sparsa. To identify the weather patterns associated with a high incidence of downy mildew berry infections (dryberry disease) and derive parameters for the empirical model, classification and regression tree (CART) analysis was performed. Then, fuzzy sets were applied to develop a simple model to predict the disease risk based on the parameters derived from the CART analysis. High-risk seasons with a boysenberry downy mildew incidence >10% coincided with months when the number of hours per day with temperature of 15 to 20°C averaged >9.8 over the month and the number of days with rainfall in the month was >38.7%. The Fuzzy Peronospora Sparsa (FPS) model, developed using fuzzy sets, defined relationships among high-risk events, temperature, and rainfall conditions. In a validation study, the FPS model provided correct identification of both seasons with high downy mildew risk for boysenberry, blackberry, and rose and low risk in seasons when no disease was observed. As a result, the FPS model had a significant degree of agreement between predicted and observed risks of downy mildew for those crops (P = 0.002).

Development of Neurobehavioral Deterioration Risk Prediction Model for Welder: A Proposed Study

2018 ◽  
Vol 10 (5) ◽  
Author(s):  
Nuur Azreen Paiman ◽  
◽  
Azian Hariri ◽  
Ibrahim Masood ◽  
Arma Noor ◽  
...  
Keyword(s):  
Prediction Model ◽  
Risk Prediction ◽  
Risk Prediction Model
Sign in / Sign up

Export Citation Format

Share Document