Lu C.-C.Li J.-L.Wang Y.-F.BOR-SHENG KOJIH-LUH TANGLee C.-C.2021-01-062021-01-0620191557-170Xhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85077898938&doi=10.1109%2fEMBC.2019.8856524&partnerID=40&md5=e50d33aa4b539aca5b1be5ccbc3e548ahttps://scholars.lib.ntu.edu.tw/handle/123456789/538682The prognosis management is crucial for highrisk disease like Acute Myeloid Leukemia (AML) in order to support decisions of clinical treatment. However, the challenges of accurate and consistent forecasting lie in the high variability of the disease outcomes and the complexity of the multiple clinical measurements available over the course of the treatment. In order to capture the multi-dimensional and longitudinal aspect of these comprehensive clinical parameters, we utilize an attention-based bi-directional long shortterm memory (Att-BLSTM) network to predict AML patient's survival and relapse. Specifically, we gather a 10-year worth of real patient's clinical data including blood test, medication, HSCT status, and gene mutation information. Our proposed Att-BLSTM framework achieves 77.1% and 67.3% AUC in tasks of predicting the next 2-year mortality and disease relapse with these comprehensive clinical parameters, and our further analysis demonstrates that a next 0 to 3 months prediction performs equally well, i.e., 74.8% and 67% AUC for mortality and relapse respectively. ? 2019 IEEE.[SDGs]SDG3Diagnosis; Forecasting; Acute myeloid leukemia; Bi-directional; Clinical data; Clinical measurements; Clinical parameters; Clinical treatments; Gene mutations; Multi dimensional; Diseases; acute myeloid leukemia; allotransplantation; genetics; hematopoietic stem cell transplantation; human; recurrent disease; retrospective study; Hematopoietic Stem Cell Transplantation; Humans; Leukemia, Myeloid, Acute; Neural Networks, Computer; Recurrence; Retrospective Studies; Transplantation, Homologousconference paper10.1109/EMBC.2019.8856524319463952-s2.0-85077898938