The following is an excerpt from Accessing and Analyzing Relevant Content in Today’s Information Chaos.
The use of analytics to drive decision making in life sciences is nothing new. Yet, as the explosion in data and information has spread pervasively across research and development organizations, putting these treasure troves of data to use has become a priority. Novartis, for instance, has spent the last several years developing a state-of-the-art advanced analytics platform centered on data science, called Nerve Live. Its goal is to embed insights-driven decision making across its drug development pipeline and to help the clinical development team access and apply trusted, relevant information more easily.
Where it comes into play
We’ve discussed how applying search, personalization, and semantic enrichment helps to narrow down the vast amounts of literature and data at our disposal. Analytics and visualization technologies — such as knowledge graphing, clustering, and ranking — are additional ways to help weed out unnecessary information and give users additional ways to explore the information and the connections between disparate sources.
It takes five minutes, on average, to read one page of technical material. Consider the impact on researchers who has one fewer scientific paper to read every day because data analytics and visualizations were applied to allow them to focus on key pieces of information and be more selective about which papers require a full read.
Knowledge graphs show secondary datasets created by analyzing and organizing underlying data. The visual element of “seeing” new connections and naming key relationships can accelerate the generation of novel insights. For example, analytics embedded within a company’s information management system could provide capabilities such as topic trending or correlating topics related to a search term. While such analytics provide time savings for researchers they also have the potential to identify previously unassociated connections and support researchers in uncovering novel insights.
Challenges and opportunities
The growing field of Literature-Based Discovery (LBD) shows us the potential for data analytics. Don R. Swanson was the first information scientist who searched scientific literature to establish a previously unknown link between a disease and a potential treatment. In a mostly manual fashion, he analyzed publicly available scientific literature related to fish oil and Raynaud’s Disease, and found that the concepts of blood viscosity, platelet aggregation, and vascular reactivity were implicitly shared yet never explicitly connected (Swanson, 1986). Subsequent clinical trials proved out Swanson’s hypothesis that fish oil could successfully treat Raynaud’s Disease, and his seminal paper published in 1986 launched LBD as a new research field.
Though easier said than done, the ability to extract knowledge from data remains a primary goal and a key competitive advantage for life science companies. Organizations should consider embedding data analytics and visualization as a strategic capability. This would require investing in data scientists, establishing new ways of working across functions, developing data literacy through training and just-in-time opportunities, and deploying data visualization tools.
The ultimate value and utility of data analytics and visualization, such as knowledge graphing, clustering, and ranking, lies in their power to unearth vast amounts of undiscovered knowledge more quickly and efficiently. Powerful analytics in information and knowledge management solutions — buoyed by the right people — not only forge but can accelerate new connections between medical concepts residing in scientific literature and data.
Keep reading Accessing and Analyzing Relevant Content in Today’s Information Chaos.
Learn more about finding applying data analytics in RightFind Navigate.