Big data analytics
Big data analytics in pharma and health care
For more than 25 years, KPA is a world leader in generating insights through analytics, particularly in the new and developing area of big data analytics.
Our expert team knows how to handle the most challenging data analytics tasks posed today by the pharma and health care industries:
- Patient diagnostics
- Drug response prediction
- Personalized therapy
- Anomaly detection
- Efficiency and quality improvement
What do we do?
- We help you define your topics and questions for study.
- We help you design your experiments
- We analyze your big data by incorporating sophisticated statistical modeling with advanced machine learning algorithms
- We generate an efficient and friendly output and reporting system
We analyze data generated from various sources:
- Experiments based on high throughput technologies (microarrays, next generation sequencing)
- Medical records
- Costumer records
- Production line
We use predominant statistical programming languages such as R, the currently most widely used programming language for predictive analytics and statistical computing. R can scale across big data systems due to its parallel computing and distributed processing facilities.
We use advanced statistical methodologies and models such as:
- Classification models (e.g. logistic regression, decision trees, random forests, discriminant analysis, support vector machines, naïve Bayes, k-nearest neighbor, neural networks)
- Clustering models (e.g. k-means, EM algorithm, hierarchical clustering, principal component analysis, canonical correlation analysis)
- Regression models (generalized linear models, non-linear models, ANOVA models)
- Networks models (e.g. Bayesian networks)
- High-throughput statistical testing in complex studies