Machine learning using baseline clinical biomarkers for the prognostic stratification of patients with neuroendocrine tumours receiving 177Lu oxodotreotide therapy

Prognostic stratification of patients with advanced neuroendocrine tumours receiving 177Lu oxodotreotide therapy enables the identification of those most likely to benefit from treatment, improving cost effectiveness. Machine learning offers the opportunity to harness the predictive nature of baseline circulating biomarkers’ in treatment response. This work is an initial investigation into the predictive potential of a range of machine learning algorithms applied to this data.

The same investigative methodology is applied to predicitng Progression Free Survival (PFS) and Time to Treatment Failure (TTF) seperately which are available in two seperate Jupyter notebooks.

This work has been submitted for presentation at the European Association of Nuclear Medicine 2024 Annual Congress (EANM24).