Survival prediction models allow us to predict which individuals are likely to respond to treatments, which can inform clinical trial design and personalise patient care in oncology. Using data from a recent clinical trial in patients with non-small cell lung cancer (NSCLC), we created a machine learning integration pipeline to predict overall survival based on spatial features extracted from digital pathology images and RNA-sequencing data. Each data modality alone was a separate predictor of overall survival. Importantly, integrating the two modalities further improved the predictive power of the model. Our work demonstrates the value of integrating independent data modalities into one analysis. Join me to find out more about our modelling work and its implications.