Digital tool to help identify cancer patients at risk of serious immunotherapy side effect

Researchers at Peter Mac have developed an Australian-first digital tool that can rapidly and accurately identify cancer patients who have developed immune-related colitis, one of the most common and potentially serious side effects of immunotherapy treatment.

To alleviate this issue, we developed a clinician-verified 'digital phenotype'—a reproducible computer algorithm using existing Electronic Medical Record (EMR) data—to assist with automatically identifying affected patients with high accuracy.

This study aims to establish an interpretable machine learning model to predict immunotherapy treatment irAE (immune-related adverse events) risk in advanced NSCLC patients, thereby supporting clinical decision-making and thus improving the safety of immunotherapy.

The web tool developed based on this model is available at https:
//lingchun.shinyapps.io/web123/ and enables the early identification of patients at high risk of developing irAEs during hospitalization and supports their timely adoption of individualized management measures.

A new study published in the Journal of Clinical Oncology Clinical Cancer Informatics unveils an AI machine learning model that can predict cancer patient responses to immune checkpoint inhibitors (ICIs) using electronic health record (EHR) data and predicts the risk of serious immunotherapy side effects such as hepatitis, pneumonitis, and colitis with up to 76% accuracy.