Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
This is an incremental application of deep learning for prognostic prediction in a specific cancer domain, potentially aiding clinicians in personalized treatment planning.
The study tackled predicting prognosis in acute myeloid leukemia using deep learning on clinical and genetic data, achieving 83% accuracy in classifying survival beyond 730 days.
We explore how Deep Learning (DL) can be utilized to predict prognosis of acute myeloid leukemia (AML). Out of TCGA (The Cancer Genome Atlas) database, 94 AML cases are used in this study. Input data include age, 10 common cytogenetic and 23 most common mutation results; output is the prognosis (diagnosis to death, DTD). In our DL network, autoencoders are stacked to form a hierarchical DL model from which raw data are compressed and organized and high-level features are extracted. The network is written in R language and is designed to predict prognosis of AML for a given case (DTD of more than or less than 730 days). The DL network achieves an excellent accuracy of 83% in predicting prognosis. As a proof-of-concept study, our preliminary results demonstrate a practical application of DL in future practice of prognostic prediction using next-gen sequencing (NGS) data.