Big data

– Diagnostic assistance or personalized medicine via the use of historical patient data (Electronic Health Record, Real World Evidence etc.)
– Medical monitoring (processing of monitoring data, e-Health or connected health)
– Drug discovery (intelligent preselection of candidate molecules)
– Extraction of information from raw data, for example textual and creation of structured databases
– Analysis of results from clinical trials or biological databases
– Optimization of performance of healthcare establishments (processing of administrative data etc.)
– Optimization of Marketing operations (time, costs etc.)
– Supply chain
– Market access

– Database architecture and management (design, operation and administration of the database)
– Detection and management of missing, duplicated or inconsistent data
– Tools : Oracle SQL, Hadoop, Scala, R, Python

– Data visualization
– Biostatistics and consolidation
– reporting
– Tools: Table, Spotfire, R Shiny, Python, Oracle SQL, Power BI, QlikView

– Textual document : medical records, analysis results, etc.
– Structured file : clinical study, results table, etc.
– Database : patients, molecular, etc.
– Imaging : x-rays, scanner, etc.

– Fichier structuré : étude clinique, tableau de résultats, etc.
– Base de données : patients, moléculaire, etc.
– Imagerie : radios, scanner, etc.

– NLP (Natural Language Processing): text mining, exploitation and structuring of textual data such as patient files or medical reports
– ANN (Artificial Neural Network), RNN (Recurrent Neural Network): processing of historical patient data for prediction risk, monitoring for follow-up or prevention
– CNN (Convolutional Neural Network): imaging analysis
– Unsupervised learning : labeling for fraud detection
– Random forest, k-means : classification or clustering from data clinical trials
– Data mining: detection of health insurance fraud