Life science

• De-risk trials with real-world feasibility modeling, real-time site- and provider-level visibility, and partnership opportunities with leading US health systems.
• Prevent failed trials and reduce zero-enrollment sites by dynamically modeling complex feasibility before launch, and continuously optimize post-enrollment performance with daily refreshed data.
• Extend trial value beyond the study window by generating ongoing evidence for prospective research and post-market studies, or by linking registries for long-term patient follow-up.

Testing I/E criteria to de-risk clinical programs

Sample heart failure population with inclusion/exclusion criteria applied

 Read the case study

Generate robust evidence on cost-effectiveness and outcomes to accelerate regulatory approval and reimbursement.

• Leverage linked EHR and closed claims, alongside AI, to evaluate real-world outcomes and cost effectiveness of drugs and devices.
• Generate evidence to support reimbursement decisions, including CMS national coverage determinations and label/indication expansion.
• Train AI models to predict treatment response, disease progression, and long-term outcomes.

Comparing real-world treatment effectiveness

Mean body weight change from baseline in treated, propensity score matched patients.

 Read the research

Monitor real-world treatment patterns, access barriers, and market dynamics to maximize patient reach.  

• Analyze real-world treatment patterns and barriers to timely intervention to accelerate therapy adoption.
• Evaluate disparities in access by examining utilization trends across demographics, geography, and payer types.
• Develop medical education addressing trends in patient adherence, discontinuation, and switching.

Analyzing therapy discontinuation and reinitiation trends

Proportion of patients discontinuing and reinitiating GLP-1 RAs within 2 years

Read the research

Fulfill post-market regulatory requirements and accelerate safety assessments with real-time data.

• Streamline post-market safety requirements, including PASS and PMR studies, reducing reliance on costly trials and registries.
• Quickly identify and assess potential safety signals using real-time data.
• Assess long-term safety across diverse patient populations with complete EHR data linked to closed claims, SDOH, and mortality data.
• Predict adverse event risks and simplify case processing with AI modeling.

Assessing the safety of novel interventions

Comparative bleeding incidence 7 days post-procedure for pulmonary embolism interventions

 Read the case study

• Identify clinically relevant biomarkers and precision medicine opportunities with integrated genomic and phenotypic data.
• Track real-world disease progression to optimize early-stage development.
• Train AI models to accelerate target discovery and device innovation with data from representative populations.

Genetic association Manhattan plot

Genome-wide associations linking genetic variants to disease risk and therapeutic targets