5-Provider Clinic Reduces No-Shows by 71% and Recovers $12,800 Per Month with AI Automation
A 31% no-show rate was costing the clinic $280 per empty appointment slot. Four hours per day went to manual reminder calls, confirmation follow-ups, and rescheduling. AI automation — built around their existing Jane App practice management system — fixed both problems simultaneously, paying back in 22 days from recovered appointment revenue alone.
Key Results
71%
No-show rate reduction
31% → 9%
$12,800
Revenue recovered/month
from filled slots
40 min
Daily scheduling admin
was 4 hours/day
22 days
Full payback period
from appointment revenue
The Client
A five-provider physiotherapy and sports medicine clinic in a major metropolitan area serving approximately 340 active patients per month. Services ranging from post-surgical rehabilitation to athletic performance treatment, with appointment lengths of 45–90 minutes and an average revenue of $280 per appointment.
The clinic had been using Jane App as their practice management system for three years. Scheduling was managed by two front-desk staff. The clinic was at capacity — 6-to-8-week wait lists for new patients — but consistently losing revenue to no-shows and last-minute cancellations that couldn't be filled fast enough.
The Problem: Revenue Leaking Through Empty Slots
The audit surfaced a compounding problem. The clinic had a 31% no-show rate — significantly above the 15–20% healthcare industry average. Each no-show represented a $280 lost appointment that couldn't be recovered after the fact. With 340 appointments per month, a 31% no-show rate meant approximately 105 empty slots and $29,400 in monthly revenue that was scheduled but not delivered.
The secondary problem was the labor cost of managing the no-show rate manually. Front desk staff spent approximately four hours per day on reminder calls, confirmation follow-ups, and rescheduling — reactive work that hadn't solved the underlying problem in three years of operation.
No structured reminder sequence
Staff called patients 24 hours before appointments when time allowed. No systematic 72-hour or 2-hour reminders. No SMS. Calls were often not returned, leaving no-show probability unchanged.
Cancellations not triggering waitlist fills
When a patient cancelled, the slot was logged as available in Jane App — but the front desk had to manually identify waitlist patients, call them, and coordinate rebooking. By the time a replacement was secured, the slot was often less than 4 hours away — too short to fill reliably.
No systematic patient recall process
Patients who hadn't booked in 60+ days — lapsed patients who still needed treatment — received no outreach. The recall process was entirely manual and happened only when staff had spare time, which was rarely.
Post-appointment follow-up absent
No systematic follow-up after appointments to check patient progress, share home exercise materials, or prompt rebooking for ongoing treatment plans. Continuity of care suffered; rebooking rates were lower than the clinical presentation warranted.
The Solution: Automated Reminders, Waitlist Filling, and Patient Recall
Tech Stack
Jane App API
Patient scheduling data, appointment status, waitlist management
n8n (self-hosted)
Workflow orchestration — reminder sequences, cancellation triggers, recall timing
Twilio SMS + Voice
Patient-facing communications — reminders, confirmations, recall messages
GPT-4 via API
Personalized recall message generation by treatment type and provider
Sendgrid
Email fallback for patients without mobile numbers; post-visit care materials
Custom waitlist logic
Priority scoring for waitlist fills based on slot duration match + patient distance
The reminder system ran three touchpoints per appointment: SMS at 72 hours requesting confirmation, SMS at 24 hours with a direct cancel/rebook link, and a final reminder 2 hours before. Patients who didn't confirm by the 24-hour mark were flagged for front-desk follow-up — staff called only the non-responsive patients, not all patients.
When a cancellation occurred, the automation queried the waitlist immediately — matching patients by appointment duration, provider preference, and travel distance — and sent SMS offers to the top three matches simultaneously. First to respond got the slot; the others were automatically moved to next-priority. The average gap between cancellation and waitlist fill dropped from 3.2 days (when staff managed it) to 47 minutes.
The recall sequence triggered automatically when a patient had not booked within 45 days of their last appointment. GPT-4 generated a personalized message referencing their treatment type and provider — not a generic clinic message. Open rates on recall messages were 68%; booking rates from opened messages were 41%.
Implementation: 4 Weeks from Audit to Full Deployment
Scheduling Audit (Week 1)
Mapped all reminder, cancellation, recall, and post-visit workflows. Analyzed 6 months of appointment data to identify no-show patterns by day of week, provider, appointment type, and patient demographic.
Communication Design (Weeks 1–2)
Built reminder message sequences, waitlist notification templates, and recall message frameworks. Tested GPT-4 recall personalization against sample patient profiles until front-desk staff rated messages as 'likely to prompt a booking.'
Integration Build (Weeks 2–3)
Connected Jane App API → n8n → Twilio. Built the waitlist priority scoring logic. Configured cancellation webhooks. Tested all reminder sequences against a subset of actual upcoming appointments with manual override available.
Go Live (Week 4)
Full deployment. First two weeks monitored closely — front desk reviewed all outbound messages before they sent to verify tone and accuracy. After no issues across 200+ messages, moved to autonomous operation with exception alerts only.
What Didn't Go Smoothly
Three friction points appeared during build and rollout. Each required a workaround before the system met the agreed go-live criteria.
Twilio HIPAA BAA execution delayed the SMS workflow by 9 days
Twilio requires an executed Business Associate Agreement for accounts handling PHI in SMS. The clinic's compliance officer flagged two clauses on indemnification and breach notification that needed counsel review. Workaround during the gap: built the workflow against a sandbox number and ran it in dry-run mode (logging the message body to an internal channel rather than sending) until the BAA executed.
Jane App SOAP-note structured-field migration was the longest single task
PROMs automation (LEFS, DASH, NDI) depended on outcome scores being captured in structured fields, not free-text. About 60% of historical notes had them in free-text. We did not attempt a retroactive migration; instead the automation started from the go-live date forward, and historical outcomes data was excluded from the dashboard for the first three months while structured-field discipline became habitual.
Workers comp visit-cap edge cases caused the first two billing errors
The first two workers comp patients had visit caps that the front desk had manually overridden in Jane App, but the override was stored as a note field rather than a structured cap value. The automation read the structured field, saw remaining visits, and let the patient book past the actual cap. Fixed by adding a pre-booking check that surfaces any free-text override notes to staff for confirmation before the booking writes.
Results: 30-Day and 90-Day Measurements
9%
No-show rate
Down from 31%; industry average is 15–20%
$12,800
Monthly revenue recovered
From no-show reduction + waitlist fills
40 min
Daily scheduling admin
Down from 4 hours; staff call only non-responders
47 min
Waitlist fill time
Down from 3.2 days manual process
41%
Recall booking rate
Of opened recall messages result in a booking
22 days
Full payback period
From recovered appointment revenue alone
Frequently Asked Questions
Does this approach work for workers compensation and motor vehicle accident (MVA) patients with insurance pre-authorization requirements?
Yes — but the reminder logic differs. Workers comp and MVA patients often have visit caps imposed by the insurance carrier (typically 8–24 visits). The automation tracks remaining authorized visits per patient against Jane App appointment history, and triggers a re-authorization workflow at the 75% threshold: a task is created for the front desk to contact the carrier for additional visits before the patient runs out of coverage. This prevented 14 patients from hitting an authorization wall mid-treatment in the first 60 days — each previously would have resulted in a treatment gap that hurt outcomes and rebooking rates.
How does the system handle physiotherapy home exercise program (HEP) delivery and compliance tracking?
After each visit, the system pulls the prescribed HEP from the Jane App SOAP note (provider tags exercises with a structured field), generates a patient-facing PDF with images and instructions via GPT-4 + a stock exercise image library, and sends it via SMS link or email. A 3-day check-in SMS asks the patient to rate adherence on a 1–5 scale. Adherence data flows back into Jane App as a custom field — providers see HEP compliance history in their note prep and can adjust progression accordingly. Patients who report low adherence two visits in a row trigger a provider alert for in-session discussion.
How does automated outcome questionnaire collection (LEFS, DASH, NDI) work for physiotherapy patients?
The system schedules patient-reported outcome measures (PROMs) at the appropriate cadence per protocol — typically initial visit, every 4 visits, and at discharge. The relevant questionnaire is sent via SMS link 24 hours before the visit (Lower Extremity Functional Scale for knee/ankle, DASH for upper extremity, Neck Disability Index for cervical cases). Responses populate the SOAP note automatically before the provider walks into the room. This eliminated 6–8 minutes of intake admin per visit and produced complete outcome data across 94% of episodes vs. 38% pre-automation — material for billing third-party payers requiring PROM evidence of medical necessity.
Does the system integrate with Jane App, Cliniko, SimplePractice, and Kareo for physiotherapy practices specifically?
Jane App is the primary integration here — it has the strongest API for physio practices including SOAP note structured fields, treatment plan tracking, and care plan adherence flags. Cliniko has equivalent API coverage and is common for Australian and UK clinics. SimplePractice and Kareo are more weighted toward behavioral health and primary care respectively, so the API mapping differs (no native HEP fields, requires a custom field layer). For PT-specific functionality (visit caps, PROMs, HEP delivery), Jane App and Cliniko require fewer custom adaptations than the others.
Are SMS communications to physiotherapy patients HIPAA-compliant when they reference treatment specifics?
HIPAA-compliant SMS requires (1) patient consent to receive PHI via SMS, captured at intake and stored in the patient record; (2) a Business Associate Agreement (BAA) with the SMS vendor — Twilio offers a BAA on its HIPAA-eligible plan; (3) minimum necessary content — messages reference appointment time, provider, and treatment category (e.g., 'knee rehab session') but not detailed clinical content. For HEP delivery, the system uses encrypted links rather than embedding clinical content in the SMS body. The clinic's HIPAA officer reviewed and signed off on all message templates before go-live.
Related
AI for Healthcare Clinics: Automate Patient Intake and Scheduling
ROI of AI Automation: What to Expect in 90 Days
Case Study: Agency Adds $112k ARR After Automating Client Reporting
Case Study: RIA Firm Cuts Onboarding by 83%, Recovers 470 Hours/Year
Case Study: HVAC Contractor Cuts Missed Jobs 74% With AI Scheduling
Case Study: Vet Practice Reduces No-Shows 66% and Recovers $7,100/Month
See All Case Studies →
AI Lead Follow-Up Automation: Never Lose a Prospect Again
Aditya Ranjan
Lead Software Engineer · Swift Headway AI
Lead Software Engineer at Swift Headway AI. Builds AI agents and automation systems for SMBs. Writes about agentic workflows, governance, and the operating discipline that turns pilots into production.
Your Clinic
See What Scheduling Automation Looks Like for Your Practice
Book a free Operations Audit. We calculate your no-show revenue loss, map your scheduling workflows, and show you exactly what automation would deliver for your patient volume and practice management system.
Get My Free AI Growth Audit →