How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap

Summary

Sempre Health handles thousands of inbound patient text messages daily to manage medication adherence and prescription discounts. Although an existing rule-based system caught around 80% of inbound texts, the team required statistical machine learning to improve message parsing and reduce manual workload. Collaborating with Hugging Face through the Expert Acceleration Program, the engineers received guidance on labeling strategies, problem formulation, and model selection. They deployed a natural language processing pipeline into production to automatically classify and respond to incoming messages or initiate automated actions like refill requests. Since deployment, the new NLP system automatically handles nearly 20% of incoming messages that previously required operational support tickets.

Context

Sempre Health receives thousands of patient text messages each day for medication adherence and dynamic prescription pricing. Their legacy rule-based system caught approximately 80% of incoming texts, but manual handling of the remainder created high ticket volumes for the patient operations team.

Approach / What changed

Through Hugging Face's Expert Acceleration Program, the team formulated an NLP solution, obtained guidance on gathering representative and accurate text labels, and selected language models to build an automated classification and response pipeline.

Takeaways

• Deploying the new NLP pipeline allowed Sempre Health to automatically process nearly 20% of inbound messages that previously required manual operations tickets.
• Hugging Face experts assisted the team with labeling strategies and model selection, reducing research time when transitioning from rule-based parsing to statistical NLP.
• Automated text handling encompasses simple automated replies as well as automated backend actions, such as calling pharmacies for prescription refill requests.

Related reading