Intelligent Healthcare Call Center Custom-Built on AWS

Leveraging Amazon Transcribe and QuickSight to Extract Business Intelligence from Healthcare Call Center Data

The Opportunity

Regardless of industry, and despite modern online methods of communication, call centers continue to receive an overwhelming number of phone calls. Many organizations record calls which are a potential gold mine of rich insights about customer satisfaction, customer churn, competitive intelligence, service issues, agent performance, and campaign effectiveness. However, the sheer volume of phone calls, especially in overburdened healthcare organizations, exceeds a contact center’s ability to review and analyze them in order to glean those valuable insights. That means only a small fraction of calls, reviewed manually using unsophisticated analysis, are relied upon to see the bigger picture.

The customer at the heart of this case study, a leading and renowned diagnostics company with a widespread operational network, was experiencing this exact challenge. Its healthcare lab call center was receiving over 100,000 calls per month to their customer support center. Although each call was recorded, the audio files were simply stored and not reviewed for call quality or outcomes. High-level details about the calls were available, like quantity, duration etc., but there was low visibility on call quality, and no insights on resolution of customers inquiries.

The diagnostics company engaged SourceFuse, as an AWS Advanced Consulting Partner with AWS Healthcare Competency, for custom application development, creating a contact center solution that would overcome their core challenges:

  • High operational costs associated with the high call volume
  • Less than satisfactory customer service experience and agent performance
  • Inability to measuring campaign effectiveness using incoming calls

The Solution

During the initial discovery phase of this project, SourceFuse found that of 106,170 calls reviewed, 20% were <1 minute long, 30% dropped or noise-disrupted, and only 10% in English. Our proof of concept (PoC) project involved identifying and proposing solutions to overcome the three main challenges:

  • Channel
    The calls were recorded on a single channel, rather than a stereo file (where the left channel is typically the first speaker and the right channel is the second speaker). In order to provide call center specific transcription, both agent and customer should be recorded in their own channel.
    SOLUTION: Since we could not split the call recording using channels, we implemented AWS Transcribe API, which identifies who was talking using speaker diarization, and transcribes speech-to-text.
  • Language
    The customer has diagnostic centers spread across the country and hence incoming calls are in multiple languages. In these scenarios, the customer either speaks in the local language or may switch between English and a local language. We investigated the use of AWS Translate, to transcribe calls in local languages and translate to English. We also explored AWS Transcribe to support automatic language detection, using a custom language model, to detect the most dominant language used. In both cases, the overall non-English call transcription accuracy was low, once language was identified and translated.
    SOLUTION: For the purposes of the PoC, only calls where the customer and agent conversed in English were manually identified and used in the dataset.
  • Speaker
    Due to the channel issue, the transcription could only identify speakers as Speaker 1 and Speaker 2 That meant it was impossible to automatically determine which speaker was the call center agent.
    SOLUTION: At a later stage, we would custom-build a speaker classification model to better identify the speakers.

The resulting PoC process was as follows:

Call Identification

Manually identify calls that are in English only


Leverage AWS transcribe to convert audio to text

Text Analysis

Cleaning and processing the text output to identify: Speaker sentiment Top words Call category


Visualise the results using AWS Quicksight

As well as AWS Transcribe, we implemented AWS Quicksight for presenting actionable insights and business intelligence via interactive and appealing dashboards. In addition, we leveraged AWS Lambda for serverless, event-driven computing, without the need to provision or manage the customer’s infrastructure.

The Results

Automation of Qualitative Analysis

Using this software, the customer was able to automate the process of checking every single conversation, rather than sampling just 1-2% of calls. Analysts would no longer have to spend hundreds of hours listening to calls, eliminating the risk of erroneous inputs when manually logging results. AI does the hard work as well as identify any further areas of improvement.

The dashboard enables the quality analyst and management to understand the underlying theme of the calls, topics of conversation, key queries, and view emerging category trends.

Fig 1: Call volume trends and call topics

The solution offers the ability to review the overall sentiment of the call along with the sentiment based on the agent and the customer. This helps filter calls where customer interaction was not up to the mark to further identify areas for agent training and help provide a better customer experience.

Fig 2: Sentiment analysis

Gain Unmatched Intelligence

The automated call review pipeline enables the business to review 100% of customer conversations to find propositions that offer the most value to customers.

By gaining valuable market intelligence and better insights, the organization could provide enhanced guidance to the agents, leading to more effective conversations. This helps revolutionize engagement rates and minimize churn.

Fig 3: Market intelligence

Lower Operational Costs

The solution transcribes 100% of recorded calls to automatically discover and analyze words, phrases, categories, and themes. With speech analytics, it could:

  • Enhance contact center performance with insights to reduce agent handle time and repeat calls
  • Discover customer insights regarding satisfaction, business issues, competitive intelligence, and marketing campaigns
  • Reduce churn by discovering root causes and predicting at-risk customers via contact center recordings
  • Improve quality monitoring by reviewing large samples and specific call types

For large contact centers such as this one, minimizing wrap time is crucial, reducing menial work when agents could be talking. Our solution performs much of the job automatically, for example, assigning a call category without the need for entering data manually. This helped to eliminate potential for human error from the information collection process.

Building Better Support

With the power of speech analytics, building a better ecosystem for call centers can:

  • Enhance CX and reduce churn
  • Train and motivate agents
  • Improve compliance and quality monitoring

With speech analytics, the exact points in each script that are underperforming or causing calls to be dropped can be pinpointed, enabling more effective optimization. At the same time, the delivery of scripted material can be analyzed, which isn’t normally possible without manual QA. This empowers end-users to provide more constructive feedback to call center agents, to get the most beneficial results from pre-prepared content.

Pay Per Usage

Deploying and running applications generally have significant associated costs. However, this solution was designed specifically to have minimum impact on the current infrastructure, and costs now scale on demand.

Improve Customer Experience

While having the ability to transcribe and analyze huge call volumes is incredibly powerful, being able to develop an emotional profile of customers is even more relevant. With better insights comes more effective conversations, eliminating the need for post-call surveys to monitor customer satisfaction. Knowing what to say, and how to say it revolutionizes engagement rates and customer loyalty.

Managing Compliance

Speech analytics can ensure that agents are meeting the organization’s obligations with regards to regulatory compliance and cold-calling policies. For example, ensuring that agents have let the customer know who they are speaking to and why at the beginning of each conversation. Leaving nothing to chance, speech analytics software can check each and every call for potential breaches.


For this leading diagnostics organization experiencing extremely high call volumes, high operational costs, and wanting to improve customer satisfaction, overcoming these challenges required a unique solution.

SourceFuse was able to custom build a business intelligence platform and carry out a successful proof of concept, incorporating microservices and AWS tools and services, to automatically analyze and present meaningful and actionable insights from qualitative data.

The end result was a bespoke solution that reduced operational costs while enhancing both the call handling agents’ and customers’ experience by providing better support and compliance.

About The Customer

The customer, a leading and renowned Indian diagnostics company, owns a chain of diagnostic centers across India, South Asia, Africa and the Middle East. Over the years, the company has carved a niche for itself with a loyal customer base, reflecting its strength as a brand offering superior diagnostic tests and services.

With its widespread operational network, the company offers a comprehensive range of clinical laboratory tests and profiles. These tests and profiles are used for prediction, early detection, diagnostic screening, confirmation and/or monitoring of the disease. It plays a pivotal role in raising the bar of diagnostic accuracy, technological equipment, customer experience and research-driven empathetic service in the industry.

First published in AWS Partner Network Nov 2022

Download Case Study PDF