How to Build a Private ChatGPT Using Open-Source Technology? Download our free white paper.

How Juisci saved 100 hours automating the synthesis of large volumes of texts

How [.orange]Juisci[.orange] saved [.purple]100 hours[.purple] automating the synthesis of large volumes of texts

130k

prefessionals on the app

700k

digests consulted

200

content analyzed each day

45

medical specialties covered

Build your project with us

About Juisci

The amount of medical content is doubling every 73 days, with papers, studies, and guidelines being published faster than any professional will ever be able to read. While processing relevant medical updates is crucial for all healthcare professionals, it has become complex, time & energy-consuming. Juisci simplifies medical content discovery, allowing professionals to better process, discuss, and co-create content. Juisci analyses content from thousands of sources, covering 20+ medical specialties and process them through our innovative AI technology to deliver reliable, updated, and digestible information.

Automating the synthesis of a large volume of texts

Juisci is a mobile app that allows healthcare professionals to keep up to date with the latest publications and clinical studies available. The company was founded in 2020 by Robin Roumengas, a serial healthcare entrepreneur, and Dr. David Luu, a heart surgeon and entrepreneur.

Easily access scientific publications and journal

Every year, healthcare professionals have to navigate through nearly 2.5 million scientific papers! It is easy to understand how difficult it is to keep up to date with the latest advances and to decipher important information through the masses.Juisci wants to summarize the different scientific papers and make them available to its users via an ergonomic and "fun" mobile application.

Freshly squeezed, straight from the source

To meet these technology challenges, the Juisci team brought together complementary expertise, at the crossroads of mobile development, UX Design, and experienced surgeons. The missing element was an NLP technology allowing to structure and analysis of the different scientific papers in an automated way. This is precisely the task that Lettria's technology was brought to bear on.

Lettria's contribution to the Juisci project: a fruitful collaboration

For several weeks, Lettria developed tools to synthesize these scientific papers (for more technical details on text synthesis, click here). The deliverable, in API format, was perfectly integrated into the Juisci application. Each scientific paper selected by Juisci is then directly sent to Lettria's analysis engine, which transforms a document of several dozen pages into less than 15 lines.To check the quality of the abstracts, a Lettria abstract of 100 papers was compared with an abstract of 100 handwritten papers. The information quality of a Lettria abstract is identical, if not better than the handmade abstract. The time saving is also considerable: the solution designed to summarize 100 scientific papers took 200 times less time than its handmade equivalent (100 hours). The application has been acclaimed by users and has obtained an NPS score of 8.5."The team of data scientists at Lettria was able to quickly understand the language processing challenges at Juisci and come up with a solution that allows for the efficient and scalable synthesis of scientific papers."Robin Roumengas, co-founder and CEO of Juisci

Next steps in our collaboration

After this extremely successful first phase, Juisci does not intend to stop there and will strengthen its collaboration with Lettria. The average volume of articles for a synthesis will increase considerably, from about a hundred to several thousand. New functionalities, as well as other medical fields, will be developed.‍

Callout

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.

This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.

What are the key results?

What are the next steps?

Build your NLP pipeline for free
Get started ->