Decoding Multi-Omics based Big Data with BI/AI Solutions in Health

Decoding Multi-Omics based Big Data with BI/AI Solutions in Health Care
Xuefeng Bruce Ling
http://translationalmedicine.stanford.edu
Stanford Univeristy,USA
Emerging multifactorial diseases are usually with poorly defined etiology and pathogenesis
mechanisms, of which the current diagnosis/prognosis is based on clinical signs and lacks
sensitivity and specificity and carries a poor prognosis for adverse outcomes. Thus, there is a
need to provide a definitive diagnosis/prognosis risk stratifications with the opportunity for better
monitoring of the condition’s progression and, thus, improved outcomes and economic benefits.
One approach is to leverage high throughput biology data sets through analytics productioneither
in house or in the common repository to discover disease fingerprint markers. We have
employed a comprehensive unbiased multi-’omics’ approach, integrating big datasets of
genomics, metabolomics, and proteomics to define the multi-omics molecular “portrait” and
relative health risk against the population baseline. Another approach is the population risk
analytics approach, integrating both structured and unstructured clinical information, to risk
stratify the population to allow preventive or targeted care. Data-driven healthcare is defined as
usage of big data, representing the collective learning in treating hundreds of millions of patients,
to provide the best and most personalized care. Big-Data based BI/AI (Business
Intelligence/Artificial Intelligence) in health care is starting to improve practice quality and
outcomes, and reduce practice-induced adverse outcomes. We share the vision of innovating
health care management at a lower cost though the disruptive Big-Data based solutions.