How it works

The xCures platform transforms complex unstructured medical data directly from the patient’s medical records into structured data suitable for analysis and machine learning. Our A.I. engine then actively cross-references this data against the vast digital library of oncology data to match patients with potential treatments and predict outcomes. This empowers patients and their oncologists to make more informed and effective treatment decisions.

Creating Real World Evidence

The xCures platform captures Real World Evidence (RWE) from patients being treated in clinical trials, compassionate use and managed access programs, virtual and decentralized studies, investigator-initiated studies, and even N-of-1 clinical studies. The platform integrates data from all these sources, effectively creating a ‘perpetual trial’ that continuously refines treatments and improves outcomes.

This RWE gives patients and oncologists more options, and researchers more valuable data. The xCures platform accelerates clinical research by capturing regulatory-grade outcomes from real world populations – data that can be directly submitted to the FDA or to support the use of novel combination therapies.

Learn More

The Team: Technology Meets Oncology

To fully integrate cancer research and care, xCures has assembled a multi-disciplinary, boundary-pushing team spanning A.I., data science, and clinical research. The team has solved three of the biggest challenges in applying A.I. to oncology:

1. Medical data processing: We automated mechanisms to get a deep clinical understanding of cancer patients and structure longitudinal data without adding any additional administrative burden to the system.
2. Treatment indexing: We created a living master catalog of all the potential cancer treatments, including individual interventions and combination regimens, expert-sourced medical rationales, and access pathways.
3. Patient-Treatment matching: We developed a suite of tools to match patients to a shortlist of appropriate options using NLP, and rank them using Bayesian predictive models operating on real outcomes data, and expert insights mined from Virtual Tumor Boards.