Data Science: Statistical experts uncover big data insights

Cytel data scientists apply advanced statistical techniques including predictive modeling of biological processes and drug interactions to unlock the potential of big data. Our team supports biomarker discovery and diagnostic test development based on biomedical signals and images, and real world evidence analysis.

Our Services

Biomarker Discovery

Developing reliable biomarkers can guide drug development decision-making.  The application of statistical and machine learning techniques to large datasets from varied sources can assist the process of biomarker identification. Once identified, these biomarkers can be applied to population enrichment strategies and precision medicine.

Techniques

  • Hierarchical and model based clustering
  • Supervised and unsupervised regression trees
  • Semi-supervised models
  • Support Vector Machines
  • Random Forest
  • Self-organizing Maps
  • Deep Learning
  • ROC analysis
  • Genetic Algorithm

Signal Processing and Classification

Application to medical diagnostics based on biomedical signals and images.

Techniques

  • Time-Frequency Analysis of Signals (Fourier Transforms)
  • Multi-Resolution Analysis (MRA) using Wavelets
  • Feature Extraction
  • Feature Selection
    • Genetic Algorithm for Feature Selection
  • Model building and validation
  • Adaptive Design of validation studies for diagnostic devices
  • Strong experience in regulatory interaction with medical device regulatory agencies.

Data Mining

Data mining uses algorithms and techniques from machine learning and statistics to allow us to extract information from large datasets and identify patterns and trends.

Techniques

  • Data exploration using graphical tools
  • Logistic regression models
  • Survival models
  • Partial least squares models
  • Machine learning tools (RF, SVM, Deep learning)
  • Functional data analysis

Programming Languages

Cytel data scientists use high performance computing methods and software engineering techniques in a range of programming languages to create customized solutions including:


R

C++

R-shiny

Python

Perl

Julia

Matlab

Resources

Removing 'Noise' from Biomedical Signals

Biomedical signals are electrical signals collected from the body. Some of the most common ones are the electrocardiogram (ECG) and the electroencephalogram (EEG).

Read More

Pattern Recognition and 'Big Data'

The explosion in healthcare information and “big data “has been one of the most written about topics in the last few years.

Read More

Signal Management Using R

Signal management is one of the most audited pharmacovigilance processes. It also generates one of the highest findings from audits.

Read More