Application of Deep Learning in Predicting the Prognosis of Acute Myeloid Leukemia using Cytogenetics, Age, and Mutations

• DOI: 10.31487/j.cor.2020.03.01
• Publication Date: 2020-03-31T09:51:56Z
• Authors: Andy N.D. Nguyen; Adan Rios; Andy N.D. Nguyen; Brenda Mai; Hanadi El Achi; Iris Wang; Lei Chen; Md. Amer Wahed; Mei Lin; Nfn. Aakash; Zhihong Hu
• Keywords: 0301 basic medicine; 03 medical and health sciences; 3. Good health

Objective: We explored how Deep Learning can be utilized to predict the prognosis of acute myeloid leukemia. Methods: Out The Cancer Genome Atlas database, 94 leukemia cases were used in this study. Input data included age, 10 most common cytogenetic and 23 mutation results; output was (diagnosis death). In our network, autoencoders stacked form a hierarchical model from which raw compressed organized, high-level features extracted. network written R language designed for given case death either more or less than 730 days). Results: achieved an excellent accuracy 83% predicting prognosis. Conclusion: As proof-of-concept study, preliminary results demonstrated practical application future practice prognostic prediction using next-generation sequencing data.