How a US healthcare provider automated phone calls QA with AI

Opportunity

The QA (Quality Assessment) process is crucial across many industries, particularly in call centers where it is highly manual and labor-intensive. Phone calls are transcribed and analyzed against evaluation templates, a process that is both time-consuming and expensive for companies aiming to maintain high-quality communication with customers.

However, with advancements in AI, this process can now be significantly automated. Modern speech-to-text technology has advanced to a level in which it can transcribe entire phone conversations with greater accuracy than human transcribers. Large Language Models (LLMs) can then evaluate these transcriptions against specific criteria much faster and at a fraction of the cost of manual evaluations.

Specialized models like Deepgram Nova 2 Medical have emerged, outperforming benchmarks by 20% in word accuracy. From retail to healthcare, companies are leveraging AI to automate the analysis of phone calls. Discover how we can transform your business processes too.

Solution

A publicly-traded US-based healthcare provider collaborated with Stack AI to automate their call center QA process. They developed a fully functional assistant that combined a speech-to-text model with an LLM to handle QA at scale.

Transcription: The Deepgram Nova 2 Medical model transcribed phone call conversations with high accuracy.

Evaluation: The Anthropic Claude 3.5 Sonnet LLM accessed multiple knowledge bases on internal procedures and evaluation criteria to conduct the QA process. The overall logic of the evaluation helped assess the following:

• Did the doctor follow all the guidelines?
• Did the doctor reach a recommendation?
• Did the patient describe the issue?
• Was the patient satisfied?

Results Upload: The results were returned in JSON format and uploaded to the company’s database via API call.

The assistant was developed using HIPAA-compliant components (e.g., Anthropic LLM). Remarkably, the call center manager was able to develop this assistant independently in under a month.

Results

Automating the QA process led to a ~70% reduction in costs and a ~10% increase in customer satisfaction due to improved call quality, which in turn boosted revenue.

Furthermore, the deployment of this assistant, at 80% less cost than a full in-house development team, encouraged the organization to explore additional use cases such as physician co-pilots and SOAP notes automation. The user-friendly nature of Stack AI significantly enhanced the company's AI ambitions, making business process automation more feasible and quicker to implement.