Foundations

Improving our understanding of disease to drive new cures and treatments

GNS Healthcare partners with some of the most prestigious foundations, academic medical centers and research organizations in the world to help discover new therapies and find cures for the world’s most insidious diseases. REFS™, our causal machine learning platform, translates the growing amounts of patient data – from patient registries, clinical trials, real world data, claims, laboratory, genetic, genomic and other sources – into the cause and effect relationships that create the data to help researchers uncover new insights and accelerate the discovery of biomarkers and underlying disease mechanisms.

Our technology solutions enable researchers to understand, validate, and share vast amounts of data at scale and without bias. Creating in silico disease models from emerging and established data sources helps researches discovery potential new disease pathways, novel drug targets and drugs, and relevant biomarkers and corresponding diagnostics.

Unravel Complex Disease

Discover disease pathways, identify disease drivers and improve treatment options.

Optimize Treatment

Understand patients who respond to specific treatments and why, better develop and deliver treatments to patients.

Share Discoveries Across Health Ecosystem

Work with partners from foundations, academic medical centers, providers, biopharma and health plans to accelerate research and collaboration.

Our Partnerships

Our partnerships are yielding important, groundbreaking results on many fronts.

The ALS Association & Answer ALS

The ALS Association is using the powerful GNS causal machine learning platformREFS to leverage the largest ALS dataset, the Answer dataset which includes patient genetic, proteomic, metabolomic and environmental data on 1000 patients with ALS. By mining this robust data, GNS will uncover critical information about ALS subpopulations, molecular pathways and disease drivers, and patient disease progression trajectories.

The Alliance for Clinical Trials in Oncology

The Alliance for Clinical Trials in Oncology applied the GNS causal machine learning platform to discover that the primary tumor location plays a central role as an independent driver of overall survival in patients with metastatic colorectal cancer. The ongoing partnership involves causal modeling of molecular data from clinical trials including gene expression, somatic mutation, microsatellite instability, and blood-vessel biomarker data. By understanding the effect of primary tumor side on overall survival providers are able to better stratify patients at baseline for treatment options.

The Multiple Myeloma Research Foundation (MMRF)

The Multiple Myeloma Research Foundation (MMRF) and GNS discovered the CHEK1 gene as a causal driver and predictive biomarker of a multiple myeloma patient’s response to stem cell transplant. The GNS REFS platform reverse engineered models of 645 multiple myeloma patients from the rich MMRF CoMMpass Study, a longitudinal study of newly diagnosed patients with active multiple myeloma. Patients with low levels of CHEK1 were found to receive a 22-month progression free survival benefit from stem cell transplantation. The discovery allows researchers to investigate better treatments for CHEK1 high levels as well help patients avoid painful, costly and likely ineffective invasive surgery

The Michael J. Fox Foundation for Parkinson’s Research

The Michael J. Fox Foundation for Parkinson’s Research and GNS have discovered genetic and molecular markers of Parkinson’s Disease patients whose disease progresses faster. Disease progression is highly variable therefore current standard of care is to treat patients based on unique symptoms. By discovering this subset of patients, researchers are able to investigate pathways for drug development and pharma able to design more effective clinical trials, including reducing enrollee numbers by 20%.

The Swedish Cancer Institute (SCI)

The Swedish Cancer Institute (SCI) is employing the GNS REFS platform to build computer models and a software interface tool that will link clinical and molecular data to treatment and outcomes across SCI’s patient population. The models will support clinical decision making by simulating potential breast cancer treatments and their effects on disease outcomes to suggest optimal treatments for individual patients.