Prototype System for AML Digital Twins

Project Abstract Conventional chemotherapy has reached its limits in treating Acute Myeloid Leukemia (AML), the most common leukemia in adults. Many patients who receive intensive chemotherapy followed by allogeneic hematopoietic stem-cell transplant eventually relapse. Therapeutic results remain particularly dismal for relapsed or refractory and older patients, who are often unfit for intensive therapies. Several new therapy options with the potential to improve treatment outcomes have emerged, but they suffer from heterogeneity in responses and a lack of methods for identifying patients who might benefit from such therapies. New detailed simulations called Digital Twins are starting to be implemented in many sectors including engineering, manufacturing, and medicine. Digital Twins are a simulation of a real-world system or object that allows for experimentation without real-world consequences. A patient oriented Digital Twin would simulate physiological response or disease and allow for outcome predictions following treatment. We propose to build a prototype of the ‘AML Digital Twin’ system (AML-DT), an interactive system to be used by doctors with their patients in which the patient’s clinical and molecular data, collected from bone marrow aspirates and peripheral blood, will be used to instantiate a digital twin model of the patient’s disease. The digital twin will enable the doctor and patient to explore personalized model-based predictions of drug response, using measurable outcomes in light of background knowledge generated from publicly available molecular data from AML patients. Importantly, the AML-DT system will continuously improve by learning from the experiences of patients and their digital twin models. The work, conducted jointly with clinician-scientists and computational researchers at the Institute for Systems Biology, the University of Helsinki, and Tampere University will center on patient-specific drug sensitivity prediction of venetoclax in combination with azacitidine by integrating with an ongoing clinical trial, VenEx, that includes ex-vivo patient selection and molecular data generation from bone marrow aspirates from AML patients in Finland. A prototype of the AML-DT system will be deployed at the midpoint of the 5-year project period, coinciding with the completion of the clinical trial. Following assessment of the prototype, further developments to the AML-DT will be carried out to accommodate other AML therapies and recommendations made by patient advocates and clinicians.