Patient Analysis - BioXplor

Patient
Responder Analysis

Personalised medicine is the holy grail for successful patient outcomes. Most clinical trials fail to meet endpoints due to clinical trial design and treating the wrong patient sub-type while many patients do not respond to prescribed approved drugs. BioXplor's network pharmacology system uncovers novel insights to predict drug effectiveness in patient sub-populations and prioritizes the right treatment strategy based on safety and efficacy insights. The network pharmacology system incorporates medical records, clinical trials and biomedical literature insights to build a knowledge graph of the disease and drug target communities, and prioritize optimal drug combinations. Machine learning is used to analyse patient data for responder & non-responder signals. Drug combinations are prioritized based on safety and efficacy insights matching the disease and patient profiles. This approach is applied for patient pooling in value-based care analysis and for secondary analysis of clinical trials data.

Safety
Efficacy
Pathways
Genotypes
Blood Measurements
Disease Progression
Disease Duration/Stage
Co-morbidities

Clinical Responders Versus Non-Responders

New Layer

Clinical Responder Analysis Workflow

Access Case Studies

1 Clinical Responders Study: Cosentyx v Enbrel

Cosentyx (Novartis) versus Etanercept (Amgen) Clinical Responder Study on 2000 patients with 200+ data points per patient to determin which drug showed the best efficacy in which patient sub-population.

2 Real World Data Analysis from EMRs

Analysis of unstructured Electronic Medical Records from Colorectal Cancer patients to identify drug effects and safety issues.

3 Biomarker Analysis for Pancreatic Cancer

Analysis of gene expression datasets from patient biopsies, comparing treated versus untreated and healthy versus disease tissue.

4 PDL-1 Biomarker Panel Analysis for Drug Response Assay Design

Analysis of gene expression datasets from patient biopsies, comparing treated versus untreated and healthy versus disease tissue.