We are a team of data scientists, engineers and consultants committed to harnessing the vast powers of machine learning to solve distinct problems. Founded in 2012 and backed by leading investors and industry practitioners, we are experts at combining human intelligence with artificial intelligence to build custom solutions for each of our clients.
VOICE OF PHYSICIANS AND PATIENTS
PharmaSignals by SetuServ is the first specialized healthcare industry text analytics platform that captures Voice of the Physician and Patient and serves up rich insights to Pharmaceutical companies and healthcare institutions. The cloud-based platform provides access to insights such as opinions of Key Opinion Leaders (KOLs)/physicians on drugs/clinical trials, experiences and unmet needs expressed by physicians/patients, early market drug reception, emerging trends, patient discovery for rare diseases, and competitor website tracking for messaging changes.
Mining Insights and Signals from Pharma Data
Pharma brands have access to rich data and are sophisticated with their analysis. However, most of the data sources have a lag of a few weeks to months. Mining publicly available social feedback and publications data yields near real-time insights. Examples from data sources include:
- Volume of Discussions (e.g. ~1 MM tweets on Leukemia alone)
- Audience Variety: Discussions from several stakeholders
- Data Velocity: Tracks organic topics from online stakeholders on a near real time bases for immediate trends and feedback
Common Challenges in Pharmaceutical Industry
- Noisy data – Quite a few discussions contain data that is not relevant to the drug or topic in question.. Finding valuable insights in such data is similar to the problem of “finding needles in a haystack”.
- Deep insights – Machine Learning alone can not provide the required depth of insights
- High accuracy – Given the limited training data, machine learning models can not be trained to provide high accuracy levels and need to be completed with human curation
Get deep and accurate signals & insights
We understand the limitations of fully automated text analytics models pertaining to inaccuracy in results. Our solution mitigates them by combining both manual research and automated text analytics models designed for different drug types to increase the accuracy of signals and insights. Thus, helping in delivering more actionable insights.