Let us help you obtain the highest value of your biomarker data
We strive to provide our customers with the highest possible standard for our biomarker platform. We are pleased to offer our data analytics services to ensure that you get the most out of the information output by our biomarkers. Our statistics and bioinformatics team can provide you with customized data analysis and our extracellular biomarker experts can help you interpret and understand your biomarker data.
Examples of statistical analysis
Response to treatment
We use multivariable analysis to identify subgroups of patients who are more likely to respond to treatment and/or experience an event of interest.
Here are some examples of multivariable analysis using biomarker data, with treated and placebo patients.
Multivariable analysis with biomarker data
Pharmacodynamics
Mixed models are used to compare biomarker profiles between treatment arms over time. Subgroup analysis is also possible to determine if only a subset of patients show an effect of treatment over time.
This is what a mixed model analysis of pharmacodynamic biomarker data looks like.
Mix-model analysis of pharmacodynamic biomarkers
Disease progression
We use changes in biomarker profiles over time according to disease progression with the goal of early detection of disease progression.
Biomarker data showing disease progression and regression, stable status, and progression.
Disease progression with biomarker data
Identifying endotypes
Cluster analysis can be used to find relevant subgroups or endotypes in biomarker data. We use both supervised and unsupervised clustering methods.
A cluster analysis that identifies endotypes might look like this.
Cluster analysis identifying endotypes
Biomarker trajectories
We use latent class models to identify different biomarker profiles over time, with the goal of identifying subgroups of patients who progress or regress, for example.
The latent class models for biomarkers are illustrated by progressive, stable, and regressing disease states.
Latent class model biomarker trajectories
Variable selection
To identify variables associated with an outcome/response to treatment we use machine learning methods such as Elastic.
Here we show how we identify variables in a biomarker dataset.
Identify variables in a biomarker dataset
Visualize and interpret your biomarker data
We design our analyzes to give you the best tools to interpret and understand your biomarker data. That way, you can get the maximum benefit from your clinical trials.
Fast delivery. We excel at short delivery times without compromising on quality. This allows you to make quick decisions for your clinical trials.
Scalable statistical solutions. With our advanced analytics package, you have the ability to tailor your solution to your unique needs and interests.
Help from scientific experts. Our statistical biomarker experts and extracellular matrix scientific experts are available to help you formulate the specific goals of the analysis, develop a research plan, and interpret the results of the analysis.We design our analyzes to give you the best tools to interpret and understand your biomarker data. That way, you can get the maximum benefit from your clinical trials.
In need of biomarkers?
If you are planning a clinical trial or a research study related to drug development or discovery, it is always recommended to include biomarkers to increase your chances of success by selecting the right treatment for the right patients.
