New Insights in Renal Cell Carcinoma using Artificial Intelligence

David Reeves
published on May 31, 2019

In all areas of biomedicine, it is crucial for researchers to stay up to date and informed of developments in their respective field of study. Nowhere is this more important than in the field of cancer research, which consistently tops the annual charts of research-spend and subsequent volumes of research-output. Staying abreast of new trends and recently published studies allows researchers to frame their work within the context of the state-of-the-art, and can inform, transform and inspire new research.

A limited amount of researcher time and resources makes it difficult to cope with the ever-growing amount of academic literature.

Although most biomedical databases provide new research alert systems, these are not easy to set up and will typically only include links to the titles and abstracts of new publications. Key information might very well be buried in the full text of such articles, and a busy researcher will often not have the capacity to acquire and read every full text.

Artificial Intelligence (AI) developments offer a new and innovative approach, enabling researchers to quickly and easily stay up to date with the published developments in their field. We will explore this new approach by using the Causaly AI engine to quickly discover novel insights from the cancer research community in relation to the example of Renal Cell Carcinoma (RCC). RCC is the most common type of kidney cancer in adults, and is the subject of an increasing body of research. This blog will seek to explore new insights in the RCC cancer biology domain.

Finding new insights using Causaly is simple. From the home screen we perform a search for renal cell carcinoma:

RCC_1_home_search

We are then presented with the topic overview. Part way down the page we find the New Insights section:

RCC_2_New_insights_a

From here we can interact and fully explore each new insight discovered by the AI engine. Using machine reading, Causaly presents all of the relationships found in the recently published research, categorised according to new cause or new effect, with detailed and extensive sub categories that relate to a particular area of RCC science. The bar charts pictured in the above screenshot provide a visual overview of the number of new insights within Unified Medical Language System biomedical categories.

Since we are initially interested in new insights in RCC biology, we can filter the results to display only causes indexed under the genetics and molecular sequencing filter:

RCC_3_New_insights_b

Here we see that Causaly has found 16 new insights relating to RCC genetics or nucleotide sequencing. These come directly from the most recently published literature and Causaly explicitly details the relationship between the gene and its effects on RCC. We are not simply presented with the title and abstract of a new study, but are given the actual contextual findings of the research, machine-read by the AI algorithm from within the published full text itself.

The first relationship presented by Causaly concerns the effect of the FENDRR gene on RCC. Clicking on this relationship allows us to inspect the full details, and to deep dive into the context of the new insight:

RCC_4_rel_page

We can see that there are 8 evidence assertions in the recent literature which link FENDRR with RCC. Taking the first example, Causaly highlights that ‘FENDRR overexpression inhibited cell migration and invasion of RCC cells, suggesting that FENDRR serves a regulatory function in RCC cell migration’. The researcher can continue to explore the other listed relationships.

New and contextually relevant insights from recently published literature can be delivered within mere seconds, with complete control over the areas of research interest (e.g. down to the effects of a particular gene on RCC).

Causaly offers a fast and efficient solution for researchers wishing to stay up to date across vast and complex body of oncology literature, while providing more control over the process.

A researcher could spend 10 minutes scanning for interesting relationships, or dive deeper into the evidence if necessary. The process, more sophisticated than simply scanning the titles and abstracts of the newly published literature, is delivered in a more interactive and intuitive way. The AI model employed by Causaly empowers researchers by keeping them up to date with all indexed literature with an unprecedented efficiency and accommodating interface for browsing the new evidence.

Using AI to answer clinical questions: COPD Case Studies
use case

Using AI to answer clinical questions: COPD Case Studies

Leverage Artificial Intelligence to assist clinicians to find answers to two COPD related clinical scenarios using the Causaly Platform

AI for Clinical Decision Support – What conditions cause female infertility?
use case

AI for Clinical Decision Support – What conditions cause female infertility?

Top causes of female infertility using AI supported clinical decision systems

Can AI enhance traditional clinical literature research methods?
Application

Can AI enhance traditional clinical literature research methods?

The process of finding and evaluating existing clinical research is central to all areas of biomedicine, providing the foundations upon...

Be the first to know

Sign up for Causaly Newsletter