Skip to main content

CAPABILITY · VERTICAL-SPECIFIC

Patient Follow-up (Physical Therapy)

Post-visit recap, HEP adherence sequence, and no-show recovery without staff involvement.

$9,500 build · $3,000–5,500/mo

Talk to us about a Patient Follow-up (Physical Therapy) build →

What it does

Sends post-visit recaps and home exercise program reminders keyed to each patient plan. Runs no-show recovery sequences and routes NPS responses to Google review requests. Writes outcomes back to WebPT or Prompt EMR. HIPAA-covered on AWS Bedrock.

Physical therapy has a completion problem. A patient comes in after a knee replacement, makes real progress through weeks two and three, starts feeling better, and quietly stops scheduling. They got enough relief to feel functional. The full prescribed course — the visits that would've gotten them to full range of motion and long-term strength — goes unfinished. The clinic loses the remaining billable visits. The patient loses the outcome their surgeon actually ordered.

This is the dropout curve that most PT practices know by feel and almost none have solved with process. Manual follow-up calls are the usual answer, and they don't scale. Front desk staff have check-in queues, rescheduling calls, and insurance follow-ups burning their time. A personal check-in call to every patient who missed a visit — or every patient whose home exercise compliance is slipping — doesn't happen consistently because it can't.

The build Golden Horizons delivers here is a HIPAA-covered outreach cadence that runs on AWS Bedrock and integrates directly with the clinic's EHR — WebPT, Clinicient, or TheraOffice. After each visit, the system sends the patient a plain-language recap of what was worked on and what they should be doing at home before the next appointment. If a scheduled visit goes without check-in, a recovery sequence runs: a text first, then a second touch if no response, then a flag to the front desk with the patient context already pulled so the staff member making the call has what they need in ten seconds instead of two minutes of chart hunting.

The follow-up cadence is keyed to the clinical protocol per patient — a post-surgical patient on a twelve-week course gets a different message cadence and a different set of check-in questions than someone on a six-visit sports injury program. When a patient reports a symptom change — increased pain, swelling, or unexpected limitation — the system flags the record for clinician review the same day. The automation handles the communication layer. Clinical judgment stays with the therapist.

Consent for SMS and email outreach is collected at intake and stored in the EHR. The system operates under a Business Associate Agreement on AWS Bedrock. No PHI touches any model endpoint without the contractual protections required under HIPAA. The clinic's compliance team gets the full data flow diagram before go-live.

Use cases

  • Post-surgical knee rehab: patient completes three of eight prescribed visits, then cancels twice without rescheduling. The system sends a check-in on day five of no contact, surfaces the gap to the front desk with a reschedule link pre-populated, and the patient books back in the same day.
  • Chronic low-back program: patient reports major pain reduction after four visits and stops booking. Automated outreach asks two questions on home exercise compliance. Clinician sees responses flagged in the EHR same afternoon and calls with an adjustment — patient re-engages.
  • Sports injury return-to-play: high school athlete on a six-week hamstring protocol. Weekly check-in messages confirm home exercise completion and flag any new soreness for therapist review, keeping the athlete and parent informed without adding to front desk call volume.
  • Stroke rehab outpatient: caregiver included in outreach cadence alongside the patient. Post-visit recap goes to both contacts, home exercise reminders use plain language sized for varying health literacy, and any reported functional change routes to the treating therapist within the hour.
  • Balance and falls program for seniors: weekly check-in confirms balance exercise completion and flags any reported fall for same-day clinician review. Non-responders after 48 hours get a front desk escalation with the patient's emergency contact already surfaced.

What’s included

  • Fixed scope with written acceptance criteria before any build starts
  • Customization layer for your brand voice and business rules
  • Clean handover with documented runbook and live training
  • Monthly ROI report for three months post-delivery
  • Source code delivered to your GitHub on handover

What’s NOT included

  • Third-party API subscription costs (billed to your accounts)
  • Data migration from legacy systems
  • Ongoing infrastructure costs after handover

Retainer

Monthly retainer covers monitoring, prompt tuning, config refinement, and minor integration additions. Range: $3,000–5,500/mo.

HIPAA-covered when sold to a clinical entity. Pinned to AWS Bedrock with executed BAA before go-live.

How clients use this

Fixed-scope build with clean handover, then an optional monthly retainer covering maintenance, monitoring, and minor changes. Most clients move to retainer within 60 days of delivery.

Questions Patient Follow-up (Physical Therapy) clients ask

Is this system actually HIPAA-compliant, and do we need to sign a BAA?

Yes, and yes — you will sign a Business Associate Agreement before any PHI touches the system. The outreach infrastructure runs on AWS Bedrock, which operates under AWS's HIPAA-eligible services program and BAA. Twilio, which handles SMS delivery, also offers a BAA for covered entities. We configure every integration under a signed BAA, map every PHI data flow in writing before the build begins, and hand that documentation to the clinic's compliance contact for review. The workflow does not pass patient health information to any model endpoint that hasn't been scoped under HIPAA-eligible contractual terms. If your compliance officer wants to review the architecture diagram or the BAA terms before you commit to the engagement, that review happens before the build starts, not after.

Which EHR systems does the follow-up cadence integrate with?

The primary EHR integrations are WebPT and Prompt EMR, both of which expose API access for appointment data, patient demographics, and visit notes. Clinicient and TheraOffice are supported as well, though Clinicient's API access depends on the client's contract tier with Clinicient directly — we audit that access during the scoping call before quoting the build. The system reads the appointment schedule and clinical protocol from the EHR, writes outreach event logs back to the patient record, and surfaces flagged responses as task items inside the EHR where possible. We do not build against screen-scraping or unsupported workarounds — if a clinic's EHR doesn't expose the access needed, we tell them before the build, not after.

What does the AI actually do versus what the therapist still handles?

The system handles the communication layer: scheduling the outreach, sending the messages, collecting the responses, logging the events to the EHR, and routing flags to the right person. It does not make clinical decisions. When a patient reports a symptom change — increased pain, unexpected swelling, a fall — that response gets routed to the treating therapist as a same-day flag. The therapist decides what to do with it. The system never tells a patient whether their symptom is normal or concerning. It never modifies a care plan. It never advises a patient to stop or change an exercise. All clinical judgment stays with the licensed practitioner. The automation's job is to make sure the therapist sees the information they need without waiting for a phone tag cycle to resolve.

How is patient consent for SMS and email outreach handled?

Consent is collected at intake, before any automated outreach runs. The intake form includes explicit opt-in language for both SMS and email communication, consistent with the Telephone Consumer Protection Act requirements for automated messaging. The consent record is stored in the EHR against the patient's chart. Patients can opt out of automated messages at any time by replying STOP to any SMS, which immediately suppresses outreach for that patient and logs the opt-out in the EHR. The system does not send automated messages to patients who haven't opted in or who have revoked consent. If a clinic's current intake process doesn't capture this consent, we help scope a compliant intake update before the follow-up build goes live.

What does better visit completion actually do for a clinic's revenue?

The revenue math is straightforward: every patient who completes their prescribed course represents the difference between what they actually paid and what a full course generates. For a practice averaging forty to sixty active patients on multi-visit protocols, even a modest improvement in completion rate across the roster adds up inside a single month. We don't quote a specific lift percentage because every clinic starts from a different baseline — a practice with strong front desk bandwidth and an existing recall process will see a smaller delta than one where follow-up is entirely inconsistent. The scoping call looks at current visit completion rates, average prescribed course length, and existing follow-up process before we tell you what the realistic range looks like for your specific operation. What we can say is that the clinics running no systematic follow-up are leaving the most on the table, and the build addresses that gap directly.

Start with an audit →