Recent advancements in wearable devices have significantly enhanced remote patient monitoring, enabling healthcare professionals to evaluate conditions within home settings. While electronic health records (EHRs) offer extensive clinical data, they often lack crucial contextual information about patients' daily lives and symptoms. By integrating continuous self-reported outcomes related to vulnerability, anxiety, and depression from older adult cancer survivors with objective data from wearables, we can develop personalised risk models that address time-varying risk factors in cancer care. Our study combines real-world data from wearable devices with self-reported information, employing process mining techniques to analyse dynamic risk models for vulnerability and anxiety. Unlike traditional static assessments, this approach recognises that risk factors evolve. Collaborating with healthcare professionals, we analysed data from the LifeChamps study to create two dynamic risk models. This collaborative effort revealed how activity and sleep patterns influence self-reported vulnerability and anxiety among participants. It underscored the potential of wearable sensors and artificial intelligence techniques for deeper analysis and understanding, making us all part of a larger effort in cancer care. Overall, patients with prolonged sedentary activity had a higher risk of vulnerability, while those with highly dynamic sleep patterns were more likely to report anxiety and depression. Prostate-metastatic patients showed an increased risk of vulnerability compared to other cancer types.