2019-04-012024-05-17https://scholars.lib.ntu.edu.tw/handle/123456789/677728Acute leukemia including Acute myeloid leukemia (AML) and Acute Lymphoblastic Leukemia (ALL) is the most common hematologic malignancies and Myelodysplastic syndrome (MDS) is the most common pre-leukemia abnormalities in Taiwan. Due to the high heterogeneity of the disease, the 5-year survival rate of AML and adult ALL achieved no more than 40% despite profound breakthroughs been made in the treatment of acute leukemia. Therefore, it is crucial to have better comprehensive risk assessment tools by assessing all abnormalities known to associated with treatment failure and tailor-made individual treatment base on the abnormality and molecular/gene profile for every patient. We developed artificial intelligence techniques from large scale retrospective data of National Taiwan University Hospital (1996 to 2016) to create the following AI-enabled healthcare service: Residual disease detection: We develop an deep representational learning technique to perform multicolor flow cytometry analysis on bone marrow specimens of acute leukemia patients. The accuracy of detecting residual disease reached over 90% with interpretation time reduced to merely 7 seconds compared to conventional 20 minutes of manual interpretation. We plan to further validate our models with University of Pittsburgh Medical Center and University of California San Francisco Cancer Center, complete the user interface construction and then kick off all the preparation work needed for FDA SaMD application under the guidance and support from agencies who had prior successful experience in de novo FDA SaMD filing under this research grant.Artificial intelligenceLeukemiaFlow CytometryDiagnostic Assistance Model