Acute myeloid leukemia (AML) is an aggressive cancer of the bone marrow and peripheral blood with poor prognosis mostly due to relapse. Despite decades of improvements in chemo-immunotherapy (CIT) and, more recently, the use of hypomethylating agent (HMAs) and addition of novel small molecule inhibitors (SMIs) to back-bone chemotherapy, AML treatment selection and dosage remains mostly empiric, with standard first- and second-line regimens, each with potential toxic consequences; dosing is based on body surface area, renal and hepatic function and pharmacokinetics/pharmacodynamics (PK/PD), ignoring tumor-specific parameters (tumor bulk, heterogeneity and cell cycle kinetics). Consequently, up to 60% of patients are under- or over-dosed and a further 10-40% of patients have primary refractory disease (non-responders) to gold-standard of care first-line CIT resulting in poor outcomes with high healthcare costs. Advances in genomic techniques are now able to assess AML clonal dynamics and measurable residual disease in patients throughout therapy with reasonable turn-around times. This rapid growth in diagnostic capabilities in conjunction with an ever-increasing number of available FDA-approved targeted treatments for patients with AML, present a constant and ongoing gap between practice and potential resulting in significant lag-time between use and know-how to improve outcomes. A framework for personalized treatment selection and optimization is therefore an unmet need in precision therapy for patients with AML. To address this need, “πCITTM Simulator”, a Clinical Decision Support service, was developed to assist Oncologists with treatment selection by providing (before treatment begins) simulations of disease response, progression, AML clonal evolution and normal blood count recovery in patients receiving therapy with different CIT, SMI and HMA options and combinations. In order to improve on the selected treatment for best patient outcome and reduced toxicity, “πCITTM Optimizer”, a Software as Medical Device, was developed to optimize drug, dose and schedule. πCITTM Simulator and Optimizer provide healthcare professionals with critical data, prior to treatment initiation, to prevent over- or under-dosage and administration of ineffective drugs for patients with resistant disease, thereby reducing treatment and hospitalization costs. In Phase 1 of this fast- track application, SANICKA will develop its first minimum viable product by (1) expanding πCITTM to incorporate novel SMIs/HMAs resulting in the launch to the market of πCITTM Simulator and (2) creating a web-based Clinician Portal for Oncologists to upload patient and tumor data, and visualize results. During Phase 2, SANICKA will (1) expand πCITTM Optimizer to capture AML sub-clonal kinetics and sensitivity to CIT/SMIs/HMAs using retrospectively-collected multi-center patient data for validation and (2) prospectively validate πCITTM Optimizer with an observational study in patients with AM...