UC29: Physician Schedule Optimiser

The Problem

Physician cancellations leave revenue-generating appointment slots empty. A cardiologist cancels clinic due to an emergency consult; the cancelled clinic slot (often 4 to 6 hours of fully booked appointments) is not filled by another provider, costing $5K to $15K in lost revenue. Waitlists exist but manually matching waitlisted patients to cancelled slots is slow; many slots go unfilled.

What the Agent Does

Monitors physician schedule in real-time: detects cancellations as they occur
Queries waitlist: identifies patients matching cancelled slot criteria (same specialty, visit type, urgency)
Applies matching logic: confirms patient availability (can arrive on short notice), ensures clinical appropriateness (chief complaint matches cancelled provider's expertise)
Fills cancelled slot with waitlisted patient; notifies patient of new appointment time (SMS, phone call)
Balances provider templates: recognises when a provider is over-booked; suggests rescheduling non-urgent patients to open slots to reduce physician workload
Tracks utilisation: appointment fill rates, cancellation reasons, waitlist conversion rates

Data Requirements

Data Sources:

Scheduling System (Epic Cadence, athenahealth) , Physician availability, appointments, cancellations, slot durations
Waitlist (Epic Cadence, Meditech) , Waitlisted patients, chief complaint, clinical speciality, preference dates
Patient Contact Info , Phone, SMS, email for urgent re-scheduling notification
Provider Templates , Standard schedule, protected times, specialty scope
Historical Utilisation , Appointment fill rates, cancellation patterns by provider

Data Classification:

Scheduling data: Sensitive, Internal, Structured
Waitlist data: Sensitive, Internal, Structured
Contact information: Sensitive, Internal, Structured
Provider templates: Internal, Structured

Data Quality Requirements:

Scheduling data: updated in real-time as appointments are booked/cancelled
Waitlist data: accurate and current (patients removed if no longer interested)
Contact information: verified at check-in; phone numbers validated
Provider templates: current and reflecting actual provider scope

Integration Complexity: Medium

Scheduling system API (Epic Cadence API, athenahealth API)
Waitlist query and patient matching logic
SMS notification system integration
Slot availability calculation (calendar parsing)

Score Breakdown

Criterion	Weight	Score (1-5)	Weighted
Time Recaptured	15%	4	0.60
Error Reduction	10%	4	0.40
Cost Avoidance	10%	4	0.40
Strategic Leverage	5%	4	0.20
Data Availability	15%	4	0.60
Process Clarity	15%	4	0.60
Ease of Implementation	10%	4	0.40
Fallback Available	10%	4	0.40
Audience (Int/Ext)	10%	4	0.40
Composite	100%		3.80

Why It Scores Well

Schedule optimisation directly improves revenue capture: filling even 50% of cancelled slots reclaims $50K to $500K annually. The data is highly structured (schedules, waitlists); matching logic is rule-based. Outcomes are easily measured (slot fill rates, revenue recovery).

Regulatory Alignment

HIPAA: Patient contact information and scheduling are semi-sensitive; PHI must be handled per privacy rules
Telehealth Laws: State-specific rules on re-scheduling; some states require patient consent before changing appointment details
Physician Practice Agreements: Provider schedules may be contractually protected; cancellation policies vary

Sprint Factory Fit

Sprint 0 (2 weeks) + 3 build sprints (6 weeks)

Schedule optimisation runs continuously: monitor for cancellations and fill slots in real-time. The initial 2-week sprint focuses on cancellation detection and waitlist matching; subsequent sprints add template balancing, SMS integration, and utilisation tracking. This is a medium-complexity use case suitable for scheduling/operations teams.

Comparable Implementations

Deploy This Use Case with the Sprint Factory

From zero to a governed, production agent in 6 weeks.

Sprint Factory Schedule a Briefing

Related Use Cases

Batch Clinical Operations

Staffing & Nurse Ratio Optimiser

Score: 3.8/5.0

Batch Clinical Operations

No-Show Prediction & Intervention

Score: 3.75/5.0

Real-Time Clinical Operations

Bed Management "Traffic Controller"

Score: 4.15/5.0

Governance Risks to Consider

Before deploying this use case, review these agentic AI risks from the Corvair Risk Catalogue. Each is scored on the DAMAGE framework and mapped to regulatory expectations.