Date: April 4, 2022
Time: 9:30 AM
Current clinical practice in oncology is undergoing a paradigm shift towards treatment personalization to improve outcomes in cancer patients. To date, patients are stratified to treatments using biomarkers that characterize tumor stage and function of nearby healthy organs. Within each stratum, treatments are typically standardized; however, the patient outcomes vary significantly, where many suffer early death. There is a dire clinical need to improve stratification metrics and incorporate interpatient heterogeneity in treatment planning to realize precision oncology. This presentation focuses on 3 main topics in this field. The first topic highlights outcome prediction models and the role of artificial intelligence in leveraging medical images, multi-omics, and other forms of clinical data to enhance patient stratification and identify high-risk patients. The second topic discusses treatment planning systems, current challenges, and potential approaches to integrate individual predicted treatment response in treatment optimization. The last topic discusses biophysical modeling that study tumor growth at preclinical level, mechanistically exploring new treatment protocols and optimal drug designs. The presentation highlights how hybridizing these topics forms a powerful machinery for accelerating precision oncology and improving outcomes in cancer patients.