Next Generation AI Solution Supports Content Creation in Scientific Communication for Better Knowledge Management

A global Pharma company has transformed their scientific writing leveraging data extraction, definition of business rules, and natural language generation. This AI-powered solution, developed by Ontotext and Wipro, saves significant time and manual effort and empowers the Pharma company’s scientific writing experts to deliver high-value analytic documents.

  • Over 75% of time saved on scientific writing
  • 60% effort reduction due to workflow automation
  • 30-fold increase in efficient knowledge management
  • Improved user experience providing easy and standard access to high-quality data


A top 5 global Pharma company needed to improve the process of effective scientific writing from already available information. They wanted to create a smart knowledge discovery solution that would help their researchers find the relevant information needed to analyze while creating a clinical trial synopsis document. This information was locked in huge volumes of data stored across various structured (proprietary or public registers) and unstructured (clinical study protocols and reports, etc.) sources. This made it extremely difficult to find the most relevant information in all the related clinical documents that would help them prepare the scientific article draft.

As the existing process made the work of their clinical trial researchers very challenging, the Pharma company wanted to implement an AI-based solution that would help them:

  • access all textual information relevant to a particular clinical study
  • identify relevant information easily and accurately
  • generate new informative content with high quality on the fly

The Challenges

One of the main challenges was the data variety. The data was stored in different types of documents (clinical protocols, TFL, scientific articles, etc.) and various file formats (Text, PDF, Scanned images, etc.). This information was also often provided in different levels of detail. All this required a lot of manual effort to get to the relevant information, with the possibility of missing something important.

As the information was scattered among different documents and described with different granularity, researchers spent too much effort in collecting the required data points, analyzing the information, and summarizing it into meaningful conclusions. Often, the information was ambiguous and duplicated, which additionally slowed down the process.

The authoring process had to ensure the generation of unique content out of the available source data. While most of the information was already present in the source documents and could be reused for scientific writing, it required a certain level of uniqueness of the produced text while keeping the meaning intact.

The Solution: A Smart Scientific Writing Solution

The smart AI solution jointly developed by Ontotext and Wipro helped the Pharma company transform and enhance their scientific writing process. This allowed for automatic data extraction, definition of business rules, and natural language generation.

Data extraction

Using advanced natural language processing pipelines, Ontotext extracted specific key categories such as introduction, method data (Study Design, Study Population, etc.), and result data (Patient Disposition, Patient Demographics, Safety, etc.). Then the clinical trial data extracted from the documents was populated into a custom-built knowledge graph and interlinked with the Pharma company’s clinical trials public data. As a result, all the Pharma company’s data was semantically normalized to specific clinical concepts (treatment, conditions, etc) and could be used for the automatic generation of human-readable text.

Definition of Business Rules

On top of this high-quality structured data, Wipro’s domain experts applied business rules associated with the medical information needs. They also reviewed the extracted content and put the resulting information into the context of the rest of the data.

Natural Language Generation

Pulling all this together within the knowledge graph, Ontotext applied data analytics techniques to extract the important facts and generate meaningful natural language summarizations for each knowledge category. Now the Pharma company researchers could specify the context in which they wanted to filter the huge volumes of existing documents to a manageable subset of relevant documents. This semantically normalized high-granularity data was a powerful knowledge discovery enabler.

Business Benefits

  • More than 75% of time-saving
  • 60% effort saving due to workflow automation
  • 30-fold increase in efficient knowledge management
  • Easy and standard access to high-quality data

Why Choose Ontotext and Wipro

With the smart scientific writing solution developed by Ontotext and Wipro, the Pharma company researchers now:

  • Integrate data better from multiple systems managed by multiple stakeholders
  • Reduce time for accumulating content for scientific communication
  • Access easily available high-quality data, including knowledge previously locked in multiple data silos
  • Utilize information faster to empower better-informed decision making
  • Minimize costs and save time spent on studies needed for product approval and registration, etc.
Do you think this case resembles your particular needs?
New call-to-action

Contact Us Now