Integrating longitudinal multi-modal profiling of metastatic breast cancer patients for high-definition oncology

Precision Oncology has revolutionized cancer therapeutics, mostly by matching genomic alterations with molecularly targeted agents.

Yet, current predictive capacity is imperfect even in best-case scenarios (tumors driven by oncogene addiction against which a targeted agent exists).

To push the field forward, we propose to exploit recent technological advances to analyze longitudinal profiles of cancer patients that encompass dimensions beyond the genetic profile: physiological monitoring, e-health records, patient-reported outcomes, medical imaging, and multi-omics.

The integration of this multi-dimensional data with personalized genomics will allow an unprecedented level of understanding of cancer processes, identifying the features that drive patient disease trajectories, eliciting truly precision interventions.The goal of this project is to use this approach to improve the current predictive ability and break current efficacy plateaus in advanced breast cancers.

I will integrate longitudinal data of a cohort of 100 hormone receptor-positive metastatic breast cancer patients in first line of treatment with CDK4/6 inhibitors and hormone inhibitors, monitored until disease progression or treatment failure. This constitutes the largest high-definition medicine study in advanced breast cancer patients to date.

I will use data across 10 different modalities to establish disease trajectories, relate molecular features to clinical outcomes and build predictive models for prognosis.

This integrative project combines translational and clinical oncology, engineering, and data science, to transition from the current genomics-centered precision oncology approach to high-definition oncology, a model in which deep longitudinal patient monitoring achieves a comprehensive personalized oncology.