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.
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.
- 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.
- 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 uses algorithms and techniques from machine learning and statistics to allow us to extract information from large datasets and identify patterns and trends.
- Data exploration using graphical tools
- Logistic regression models
- Survival models
- Partial least squares models
- Machine learning tools (RF, SVM, Deep learning)
- Functional data analysis