New AI Solution Reads Biomedical Articles in Under a Second, Sends Findings to Experts
BERKELEY, Calif., Oct. 3, 2018 — A serious and time-consuming challenge for pharmaceutical companies is analyzing and reviewing the thousands of pages of scientific journal articles published every year. The content is complex, requires domain expertise, and the review process is prone to errors due to the repetitive nature and dense materials which must be read, catalogued and passed on to the appropriate stakeholders.
Researchably, a startup in the highly-selective UC Berkeley SkyDeck accelerator program, announces the only AI solution which uses natural language processing (NLP) to read and review these scientific articles, summarize them, and determine which departments they are relevant to faster, making far fewer errors than expert readers. The new solution cuts the time to scan and review a paper from an average of 13 minutes per paper when done by a person, to less than one second. Currently the French pharmaceutical company Sanofi is running a pilot with Researchably, as are other major pharmas which cannot be named.
Using an AI platform and machine learning, Researchably first categorizes scientific papers at a high level, determining, for example, whether the paper is an observational study or an experimental study. Following that, the platform reads it for specific details and sends researchers a custom stream of appropriate papers culled for specialty and interests.
Sanofi’s trial with the Researchably platform is through its medical communications team in China which is tasked with keeping doctors informed about the latest developments in their fields.
”Working with Researchably is looking into the future of the pharmaceutical industry. Reviewing scientific information is fundamental to everything we do, and they are disrupting how that happens, making it much faster, far simpler and much more accurate,” said a Sanofi communications lead involved with the pilot.
”Biomedical research communicated in published literature underpins the pharma industry. Our AI platform makes the entire process of research review exponentially more efficient,” said Maciej Szpakowski,CEO, Researchably. ”The improvement at Sanofi is remarkable. The small team doing this work previously spent an average of more than 1500-person hours annually. Our platform is freeing up that time. Added to the time-savings is the high value of not making errors; typically, there are three of 10 papers incorrectly categorized, which means important information is not being funneled to the right people who need it. Researchably practically eliminates those errors.”
”If AI can assist with reviewing this huge amount of biomedical information, then the pharma domain experts doing this work may be better utilized on other projects,” Przemyslaw Zientala, Researchably CTO, explained. ”With the speed of Researchably, we are also preventing bottlenecks as journals pile up so those who need the information are not kept waiting.”
Researchably is the next generation NLP framework for life sciences. Its AI technology extracts insights from research papers, clinical trials or any text, much faster than any human reviewers and with far fewer errors. The company’s technology is focused on reading, reviewing and analyzing scientific journals and papers for the pharmaceutical industry. Researchably is one of the elite startups selected as a UC Berkeley SkyDeck accelerator company and has been named one of the ”20 Most Promising Pharma and Life Sciences Tech Solution Providers 2018” by CIO Review. For more information, visit https://researchably.com.