Caylent Services
Customer Experience Transformation
From Legacy Contact Center to Intelligent CX at Scale
How a Healthcare Provider Improved Patient Outreach Efficiency by 300% Through Automated Workflows
Cloud Native App Dev
Artificial Intelligence & MLOps
At a glance
New York Cancer & Blood Specialists (NYCBS), one of the nation's largest community oncology and hematology practices, partnered with Caylent to modernize patient outreach and prescription refill operations. Together, NYCBS and Caylent implemented automated outreach campaigns and AI-powered self-service experiences with Amazon Connect, creating a scalable contact center foundation that increased patient enrollment, reduced manual workload for clinical staff, and expanded access to care through 24/7 self-service capabilities.
For a healthcare provider, every phone call is a touchpoint that can affect a patient's care. New York Cancer & Blood Specialists (NYCBS), one of the nation's largest community oncology and hematology practices, runs a contact center that handles hundreds of thousands of calls each month across more than a hundred specialized queues. As the practice grew, two high-volume workflows were straining the team:
- Proactive outreach to patients enrolled in Chronic Care Management (CCM)
- Inbound prescription refill requests
Business Challenge
Both workflows were almost entirely manual. Staff dialed CCM patients by hand, and refill requests tied up agents who had to verify each patient, look up their medications, and route the request downstream. With Caylent, NYCBS built two solutions on Amazon Connect to automate these workflows while keeping clinical data accurate and protected.
"Before automation, much of our outreach effort went toward manual calling. Today, that time goes toward live patient conversations, and CCM enrollments increased by more than 50% within eight weeks. We move quickly and expect the same from our partners. Caylent and Amazon Connect met those expectations through consistent availability, flexibility as requirements changed, and clear communication throughout the engagement. That made all the difference. And we're just getting started."
Paul Kazemier
Senior Vice President of Patient Communications
Solution
Automated Chronic Care Management outreach
Each night, NYCBS's patient system exports a monthly check-ins and enrollment candidates list into an Amazon S3 bucket, kicking off an event-driven flow. The new file triggers an AWS Lambda function that normalizes the data, assigns priority so the most urgent patients are dialed first, and writes the result to a second location. That file triggers an AWS Step Functions workflow that runs campaign setup as one observable sequence: ingest the records into Amazon Connect Customer Profiles, build a targeting segment, create the outbound campaign, associate the Contact Flow, and start it. Outbound Campaigns then dial during business hours, using answering-machine detection to tell a live patient from voicemail. A single Contact Flow routes live answers to an agent with a screen pop of the patient's record, and after every contact a Lambda function writes the outcome back to the patient system so it stays current.
Using Amazon Connect Outbound Campaigns with answering machine detection (AMD) let the practice raise dial throughput sharply while reserving agent time for live conversations.
Customer Profiles gave each call its patient context without custom lookups in the flow, and Step Functions made the multi-step setup resilient and easy to observe. Because the pipeline runs on S3 events and Lambda, there are no servers to manage and nothing runs except when a file arrives.
AI-powered prescription refills
Refill requests previously tied up an agent for even the most routine case. Now, patients complete a refill through an AI-driven self-service experience in Amazon Connect, with a live agent as a fallback rather than the default.
It has two halves: a data layer that keeps patient and pharmacy information ready for fast lookup, and the runtime conversation that uses it.
- NYCBS's patient system uploads patient and pharmacy data to Amazon S3.
- An S3 event triggers a Lambda function that parses and validates each file and publishes records to Amazon SQS;
- A second Lambda function transforms them and writes them to Amazon DynamoDB.
The conversation itself follows a short, well-defined path.
The self-service agent collects the patient's date of birth and phone number and hands it off to a Lambda function that verifies them against DynamoDB, then calls the clinical records system's FHIR API for their active prescriptions and linked pharmacies. The patient selects a medication and pharmacy by voice, and the confirmed refill is written to Amazon S3. An on-premises integration engine polls that location every 30 seconds and ingests the order, closing the loop into existing clinical systems without a tightly coupled integration.
Results
- 300% improvement in outreach efficiency. Automated dialing at 109 to 110 calls per minute replaced manual effort.
- 145 patient enrollments in a single day — an all-time CCM program record
- 10,000+ daily attempt capacity, up from ~800, enabling 10,500+ monthly CCM calls and 1,100+ enrollments
- Dramatically reduced manual workload for clinical staff as automated dialing, voicemail, and documentation replaced manual workflows
- Improved call-to-bill ratio through consistent, accurate documentation
- 24/7 prescription refill access via AI self-service reduced inbound call volume and wait times
- Eliminated human errors — duplicate documentation, missed notes, and inconsistent records removed from the workflow
Why It Matters
For an oncology practice, every minute a nurse spends manually dialing is a minute not spent on patient care. By automating outbound campaigns and prescription refills with Amazon Connect, NYCBS turned two of its most resource-intensive workflows into scalable, autonomous operations while keeping clinicians in control of the patient relationship and maintaining full HIPAA compliance.
