Client:Leading Pharmaceutical Company

Industry:Healthcare and Life Sciences

Location:European Union

Capabilities: Enterprise Agility, Data-Driven Enterprise, Next-Gen IT

Situation
Healthcare leaders are investing heavily in technology, as the global digital health market is projected to reach $504.4 billion by 2025. Digitization is a key focus for pharmaceutical companies,whose supply-chain ecosystems must quickly evolve from manualcollection and analysisto automated processes. Having led the market for decades, one of Europe’s largest pharmaceutical companies faced digitizing millions of documents and nearly 1,100 different types of files. With constraints on resources and time, the leader sought to digitize its files quickly, fix existing errors, ensure the data’s compliance with regulatory requirements, and deploy a new platform that could meet the velocity demands of the clinical-trial industry over time.

Collaboration
Pharmaceutical companies often spend significant revenue digitizing files that are later used by clinical researchersand other global stakeholders.With $53.2 billion in annual revenue, this EU leader wanted an innovative solution that would rewrite that model while making its internal processes more scalable.

The pharmaceutical company and Wipro, with support from several subject-matter experts, reimagined the entire documentation processto support artificial intelligence (AI) learning. Powered by Wipro’s Cognitive Content Automation solution, the new platform would replace the company’s traditional system of manually cataloguing, classifying and processing data. 

Wipro’sAI-based Cognitive Content Automation solution applied classification algorithms, extracted relevant keywords and meta data, and processedall current and future clinical-trial documentation. This enabled the pharmaceutical company to migrate 4 million clinical-trial documents from the legacy system to a new open-text platform in a fraction of the time and with greater accuracy. As a result, the the firm saved hundreds of full-time resources and bolsteredits compliance rates by eliminating mistakes historically caused by human-input errors.

The solution had four components: a smart OCR engine, document classification, information extraction and a rules engine that leveraged AI andmachine learning. This combination enabled the enterprise to use advanced AI to process and classify data with unmatched efficiency, while giving human experts the ability to double-check data if it was flagged by the algorithms as at-risk for errors.

Outcomes

This unmanned document-processing solution automated nearly 90% of the trial-data classification activities, reducing the required time by 65% compared to previous manual processes.It also allowed the migration of clinical-trial documents to 48 total languages. The impact was a platform that favorably positioned the company to develop, test, analyze and iterate new clinical trials, while improving the data’s reusability by internal and external stakeholders alike.