Data Analytics, Real-World Evidence & AI Driven Insights
Where complex data becomes clear, actionable strategy
Unique expertise in the All of Us dataset
Innopiphany has unique access to the All of Us Research Program, providing insight into areas ranging from genetic data and social drivers of health to how diseases affect historically underserved and underrepresented populations — and is one of the first organizations to have experience analyzing these data.
NIH research program studying individual differences in lifestyle, socioeconomics, environment, and biology.
747,000+ national participants and still growing, with a goal of 1,000,000+ people.
Biobank repository for processing, storing, and sharing bio-samples (35M+ vials).
983 questions across 8 cross-sectional surveys, ranging from overall health and quality of life to social drivers of health.
68,000+ participants with Fitbit wearable data capturing activity, heart rate, steps, and sleep.
Healthcare provider networks totaling 10 regional medical centers, 6 FQHCs, the VA, and 165 enrollment sites.
Approximate analyzable record counts available to Innopiphany within the All of Us Research Program.
RWE & Data Analytics in Action
A sample of how Innopiphany applies the All of Us dataset, advanced analytics, and machine learning to real client challenges across therapeutic areas.
Mapping CNS Patient Severity for Caregiver Burden
Worked with a pharmaceutical manufacturer to build a predictive model from survey data that classifies CNS patients by disease severity.
Access to Healthcare & Adherence
Collaborated with the University of California, Irvine to examine whether social determinants of health in the All of Us dataset impact several large indications.
CMS Coverage with Evidence Development & IRA RWE Analysis
Supported prospective RWE study design for CMS Coverage with Evidence Development in IRA negotiations; built a Medicare-focused value story from disease-specific data.
RWE Dataset Identification
Identified fit-for-purpose RWE datasets to solve key challenges across Alzheimer’s agitation, MDD, HIV, 340B, inflammation, and rare disease.
Impact of SDoH on Health Conditions
Partnered with manufacturers to run multivariate logistic and Cox regressions, quantifying how social drivers of health affect patient outcomes.
Predict Undiagnosed PTSD with ML
With up to 90% of PTSD undiagnosed, leverages sociodemographic, SDoH, clinical, and geographic data to identify at-risk patients.
Predictive Algorithm for ICER Risk
Sentinnel — a machine-learning algorithm built with ensemble techniques that incorporates FDA and ICER data to estimate ICER assessment likelihood.
Identifying RSV Hotspots in Orange County
With UC Irvine and CHOC, applied geospatial analytics, clustering, and dashboarding to visualize and monitor localized RSV burden.
Drivers of Outcomes: Rare vs. Common Kidney Disease
Conducted descriptive analysis, logistic regression, and survival analysis to identify drivers, with a subgroup analysis on lupus nephritis.
Automated Statistics & Visualization across Disease Areas
Automated functions leverage the breadth of All of Us EHR and survey data to accelerate analytic turnaround.
Predictive Algorithm & Dashboard for IPAY Risk
IRAdar — a dashboard and machine-learning workflow that predicts the likelihood of IPAY selection using Medicare, 10-K, FDA, and proprietary data.
Data-Driven Patient Recruitment
Developed a strategy using a composite set of databases to identify, recruit, consent, and retain new and diverse patient populations for trials.