Exploratory Introduction of Cognitive Computing to Clinical Sequencing in Hematological Malignancies

Next-generation sequencing (NGS) is an attractive tool for prospective use in the field of clinical oncology. However, for this purpose, further innovations are necessary including medical informatics which links somatic mutations to clinical intervention. This process is currently labor-intensive, involving experienced curators who pick up the relevant evidence among a growing body of knowledge and translate it into medical practice. We organized a clinical sequencing team, called as IMSUT Tumor Board, and have been integrating clinical and genomic information in hematological malignancies with the aid of a cognitive computing (CC) system. Genomic DNA was prepared from malignant cell fractions and normal tissues in each patient, and subjected to comparative NGS, mainly targeted deep sequencing with ready-made panels and, on demand, whole exome sequencing. Sequence data was analyzed using a pipeline of in-house semi-automated medical informatics, namely YOKOMON-GO. CC was used to identify candidate driver mutations and pathways in each patient, from which pathogenic information as well as applicable drug information was deduced. A summary of NGS data was reported and discussed in IMSUT Tumor Board to deliberate upon potentially actionable findings. Up to date, we have performed NGS analysis on 90 patients with AML, MDS, MPN, et al., among which informative and actionable findings could be obtained in 50 and 18 patients, respectively. Six patients actually received treatments motivated in IMSUT Tumor Board. Our preliminary results indicate that CC can be well suited to clinical sequencing.