Journal: BMC Cancer

Article Title: A lack of association between BMI and chemoimmunotherapy efficacy in advanced non-small cell lung cancer: Secondary analysis of the IMpower150 and IMpower130 clinical trials

doi: 10.1186/s12885-024-12132-w

Figure Lengend Snippet: Treatment effect estimates (chemoimmunotherapy versus chemotherapy) with continuous BMI by the method of Multivariate Fractional Polynomial Interaction with Cox proportional-hazard regression models stratified by trial for overall survival ( a ) and progression-free survival ( b ). The shaded area is the 95% CIs of the treatment effect estimated as hazard ratios (HRs) (black solid line). Vertical dotted lines mark the 5 th and 95 th percentile of BMI distribution of the pooled analysis cohort, at 19.8 kg/m 2 and 34.7 kg/m 2 respectively

Article Snippet: Continuous BMI was modelled in stratified (by RCT) Cox proportional hazards regression by the method of (Multivariable) Fractional Polynomial Interaction (MFPI) [ ].

Techniques:

Journal: Scientific Reports

Article Title: A novel strategy for forensic age prediction by DNA methylation and support vector regression model

doi: 10.1038/srep17788

Figure Lengend Snippet: ( a ) Multivariate linear regression model. ( b ) Multivariate nonlinear regression model. ( c ) Back propagation neural network model. (d) Support vector regression model. Using 11 CpG sites selected from Sequenom MassARRAY results in 49 females, the mean absolute deviation for each method was 6.4, 4.1, 3.9, and 2 years, respectively.

Article Snippet: To build a robust predictor, we used four different models, viz., multivariate linear regression, multivariate nonlinear regression, back propagation (BP) neural network, and SVR, to test the accuracy of 11 CpG sites selected from the Sequenom dataset in age prediction ( ).

Techniques: Plasmid Preparation

Journal: Scientific Reports

Article Title: A novel strategy for forensic age prediction by DNA methylation and support vector regression model

doi: 10.1038/srep17788

Figure Lengend Snippet: ( a ) The minimal MAD of predicted age as a function of the number of sites that compose the independent variables. The 11 CpG sites selected from the Sequenom MassARRAY dataset were combined to one to 11 independent variables. SVR model fit on all but one sample, and the minimal MAD of the predicted age was observed for a given number of independent variables. ( b ) Predicted versus observed age of all 49 subjects, using SVR model by six markers. MAD of 2.8 years was observed, which is slightly higher than that obtained by 11 markers. ( c ) Predicted versus observed age using multivariate linear regression by three DNA methylation markers obtained from a recent study . The original BeadChip data of these three sites were extracted to predict age by using a multivariate linear regression model, and an MAD of 6.27 years was obtained. ( d ) Predicted versus observed age using SVR by three DNA methylation markers obtained from a recent study . MAD of 4.23 years was obtained, which is better than the MAD obtained when using a multivariate linear regression (panel C), and better than the MAD obtained when using a multivariate linear regression based on pyrosequencing data in the published study (5.4 years) .

Article Snippet: To build a robust predictor, we used four different models, viz., multivariate linear regression, multivariate nonlinear regression, back propagation (BP) neural network, and SVR, to test the accuracy of 11 CpG sites selected from the Sequenom dataset in age prediction ( ).

Techniques: DNA Methylation Assay