Millions of patients receive drug treatment every year, a tremendous expense for healthcare systems. Yet, medication is deemed ineffective for 38-75 % of patients with common diseases, according to the Food and Drug Administration.
This problem reflects the complexity of common diseases, which may involve altered interactions between thousands of genes, in thousands of cells. The same disease may arise from different causes in different patients. A disease may also change over time, due to natural variability or medical treatments.
There is a wide gap between this complexity and modern health care, in which diagnostics often relies on a limited number of unspecific diagnostic markers. As drug treatments grow increasingly complex, finding optimal treatment becomes more challenging.
Mavatar offers a new way of matching patients with optimal treatments. Our AI based diagnostic tool is designed to support clinicals in their daily work. Mavatar’s portfolio consists of different disease panels, including the most common and severe diseases.
We construct network models, or Digital Twins, from genomic data, phenotypic, and environmental factors relevant to disease mechanisms in individual patients. Patients are matched with optimal treatment by testing thousands of drugs on the patients’ Digital Twin computationally.
Digital twins is a concept from engineering, having been applied to complex systems such as airplane design or city planning. The key idea is to computationally model complex systems, in order to develop and test them more quickly and economically than in real life.