Pharmaceutical industry

Forum analysis

A pharmaceutical player needed to understand the real problems of patients with Sjögren's syndrome — not those of clinical trials, those that patients express to each other. We built the NLP system that can extract trends, themes, and weak signals from thousands of forum discussions.

Problem

Medical forums contain what no clinical study captures: the raw voices of patients. Their frustrations, their unreported side effects, the alternative treatments they are trying, the questions they are afraid to ask their doctor. For the client, this information was a strategic gold mine, but completely unusable as it was. Hundreds of thousands of messages, unstructured, written in everyday language, without any tools to collect them, organize them and extract actionable trends.

Vue rapprochée d’une coupe transversale colorée d’une géode montrant des couches concentriques de minéraux en jaune, marron, rouge et vert.

Solution

What we built

We designed a comprehensive NLP collection and analysis system to turn forum discussions into strategic insights.

Step 1 — Automated collection. Scraping 216,000 posts on the sjogrensworld.org forum and structured insertion into a MongoDB database. A collection pipeline designed to be reproducible on other sources.

Step 2 — Descriptive analysis. Overview of the data collected: volume of publications, engagement rate, links between posts, mapping of the most active users and community dynamics.

Step 3 — Topic modeling and sentiment analysis. Automatic discovery of patient-specific themes via topic modeling, coupled with a feeling analysis to measure the emotional impact of each subject. Identifying and dissecting current and past trends.

Step 4 — Extraction of latent knowledge. Use of word embeddings techniques to detect weak signals: emerging problems, undocumented drug-side effect associations, changes in the perception of treatments.

Projects in the same category

See all projects

Supply Chain Optimization Application

A pharmaceutical distribution player had to rethink its entire supply chain: pharmacy assortment, inventory management and delivery channels. Operational research alone was no longer enough. We built the application that transformed its operations.

Social media trend detection

In a market where consumer behaviors change faster than decision cycles, a customer needed to anticipate trends instead of experiencing them. We built the platform that turns social media noise into actionable signals.

Yield of agricultural fields

The climate subsidiary of a French insurance leader needed to predict field yields across Germany to price a new drought insurance offer. Internal data was not enough. We built the predictive models that made the product marketable.

Customer needs analysis platform

A large French group needed to understand the current and future needs of its customers by aggregating a massive volume of consumer data. After a POC of 8 weeks, we industrialized a complete platform deployed on all French entities and is now being extended at the group level.

Skin scoring and analysis

A major player in luxury cosmetics had developed a skin scoring algorithm. Problem: no one could verify what the AI was based on to make its diagnosis. We built the visualization system that makes predictions transparent and deployable in stores and on mobile.

Beaconing detection

A large group's security team needed to identify beaconing signals, regular network traffic sent by potentially compromised machines to servers controlled by attackers. The volume of logs made manual detection impossible. We built the anomaly detection system capable of processing this data on a large scale.