Referrals and care coordination: the administrative workflows around care

Clinicians spend a significant part of their day on work that isn't clinical: referral letters, pre-authorization requests, follow-up coordination, chasing results and scheduling across providers. Patients experience that work as waiting.

The care coordination family in the Atlas focuses on these administrative and coordination workflows. It doesn't touch clinical decision-making, and it's designed so it cannot drift into it.

Workflows covered

• Referral intake: referrals arrive from primary care, other hospitals or payers, and are checked for completeness.
• Triage and routing: referrals go to the right service and are prioritized according to clinical rules defined by the provider.
• Pre-authorization: requests are assembled with the required documentation, submitted to payers and tracked.
• Scheduling coordination: appointments are linked across departments and providers.
• Care pathway tasks: follow-ups, results, patient communication and hand-offs, each with an owner and due date.
• Closure and feedback: outcomes communicated back to the referring provider.
• Reporting: waiting times, bottlenecks and service-level performance.

Where AI helps

• Document extraction: pull structured data from referral letters and attachments.
• Completeness checks: identify missing information before a referral reaches a coordinator.
• Summaries: a concise case summary for coordinators, drawn from the documents.
• Drafting: pre-authorization justifications and patient communications, for staff to review.
• Queue prioritization: suggestions based on the provider's own rules, never the model's opinion of clinical urgency.

Where it must not

AI output in this family never replaces clinical judgement. Clinical triage rules are configured by the provider and applied deterministically, and any AI suggestion that touches clinical content is shown to a qualified person before it has effect. Each AI output is labelled and its acceptance recorded.

Privacy and hosting

Health data demands strict handling:

• in-country hosting where regulations require it
• role-based access down to record level
• full access logging
• a data-minimization default for AI features: models see only what the task needs
• a documented choice of AI provider, including private or self-hosted models where required

Integrations

EHR and HIS systems (typically via HL7 or FHIR interfaces), payer portals and APIs, scheduling systems, patient messaging, and the identity provider.

Who uses it

Referral coordinators, care coordinators, pre-authorization teams, department administrators, clinicians (for review and sign-off) and operations leadership.

First scope

One referral pathway with a visible waiting-time problem. Measure time from referral to first appointment and the share of referrals returned incomplete. Scope it in a Solution Definition Sprint.

See healthcare, explore the Atlas, or bring us your pathway.