The explosion of observational real-world data (RWD) in healthcare from EHRs, claims, registries, devices, de-centralized trials and others has presented an incredible opportunity to glean real-world evidence (RWE) from this data. RWE will transform value-based care, help with intervention design, drug discovery.
FDA has approved many trials and therapies based on RWE and is well on its path for incorporating RWE into broader clinical trials.
The impact of RWE into clinical trials will be transformational from reducing time to market, cost and bringing more insights before human trials as well as optimizing Phase 3 Trials, and post Market Drug Surveillance.
Our objective is for RWE to match the gold standard of RCT (Randomized Clinical Trials) by establishing causal inference and rigor in population equivalency.
Simply and quickly demonstrate efficacy, safety, and superiority for drug label extensions, novel therapeutics, and generics without the added costs of an additional traditional clinical trials
Our modeling engine incorporates data streams from sources such as EHRs, digital devices, and previous trials to identify key triggers in the patient journey that drive actions and interventions. The results of these actions would be tracked in order to improve patient engagement, medication adherence, and other key outcome drivers. This analysis can be incorporated into digital platforms to provide real time tracking and understanding of patient cohorts.
Much of this data is high dimensional including structured, semi-structured, and unstructured features, making it more complex. Current tools and platforms are challenging to use and fall short in meeting the needs of pharma. Further, existing RWE methods are ill suited for the explosion of high dimension and unstructured data.
Gilead “whole heartedly supports [Pattern Sciences’] proposed studies” to compare two FDA approved oral HIV Pre-Exposure Prophylaxis therapies, Truvada and Descovy.
Pattern Science is creating advanced analysis methods to characterize existing data including historical control data, real world data, and the generation of a companion data sets to eliminate the need for traditional placebo groups, allowing for radically more efficient clinical trials where all participants receive the treatment.
Although patients increasingly have multiple drug options available, there is often a lack of evidence from head-to-head clinical trials that allows for direct comparison of the efficacy (and/or safety) of one drug vs. another. Pattern Sciences is working to provide robust methodologies for accurate and efficient drug comparisons.
Our platform can ingest and process data streams from a myriad of sources including wearable devices, patient records, and other observational data to identify key biomarkers and interventions within cohorts.