Patient onboarding · Production

ASISPO uses Botpress conversational AI to manage patient journeys pre and post surgery

The problem

Doctors struggle to follow up with patients at scale due to busy schedules and phone-tag, making pre and post operative care difficult to deliver consistently without consuming excessive physician time.

Workflow diagram · grounded in source
1
Patient record creation
trigger
“When a patient is scheduled for care in the ASISPO application, a provider can create a record for that patient, ensuring that pre and post operative messages will be sent to the patient at the right time”
2
Patient authentication
validation
“Upon receiving the first message, patients authenticate themselves using their birthdate”
3
Pre-surgery background check
ai_action
“From there, they follow a pre-surgery medical background check”
4
Post-surgery NLU analysis
ai_action
“After the surgery, the chatbot uses natural language understanding (NLU) to understand any pain the patient might be experiencing or any questions they might have about their treatment”
5
Intent and entity extraction
ai_action
“Botpress can extract and pass along entities such as a type of pain the patient is experiencing, and going back to work or the gym type of inquiries”
6
Escalation to medical provider
routing
“escalate a conversation from a chatbot to a medical provider”
7
Satisfaction survey
output
“The patient is also sent a satisfaction survey at the end of their session”
Reported outcome

ASISPO achieved a 70% adoption rate, and one doctor's caseload of 600 patients over eight months required only 10 over-the-phone follow-ups, dramatically reducing physician time spent on routine patient contact.

Reported metrics
Adoption rate70%
Physician time spent on patient follow-up (baseline)six to eight hours per week
Phone follow-ups required out of 600 patients over eight months10 out of 600
Physician time savedsaves doctors a tremendous amount of time
Reported stack
BotpressNLU
Source
https://botpress.com/customers/asispo
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

ASISPO achieved a 70% adoption rate, and one doctor's caseload of 600 patients over eight months required only 10 over-the-phone follow-ups, dramatically reducing physician time spent on routine patient contact.

What tools did this team use?

Botpress, NLU.

What results were reported?

Adoption rate: 70%; Physician time spent on patient follow-up (baseline): six to eight hours per week; Phone follow-ups required out of 600 patients over eight months: 10 out of 600; Physician time saved: saves doctors a tremendous amount of time (source-reported, not independently verified).

How is this patient onboarding AI workflow structured?

Patient record creation → Patient authentication → Pre-surgery background check → Post-surgery NLU analysis → Intent and entity extraction → Escalation to medical provider → Satisfaction survey.

Related patient onboarding cases