UC58: Physical Therapy Progress Tracker

The Problem

Home exercise compliance for physical therapy is poor (~30 to 50% adherence). Patients don't remember exercises, perform them incorrectly, or lose motivation between PT visits. Remote monitoring and correction can improve compliance and outcomes. Computer vision analysis of exercise form from smartphone video enables real-time coaching.

What the Agent Does

PT orders home exercise program (HEP) for patient (e.g., "knee flexion exercises, 3 sets of 10 reps, daily")
Agent provides patient with video library of prescribed exercises: clear demonstration of proper form, breathing, range of motion
Patient performs exercise at home; records short video using smartphone
Agent analyzes video using computer vision: detects body position, joint angles, movement quality
Provides real-time feedback: "Good form on the first 5 reps; slow down on reps 6 to 8 to control the movement"
Tracks completion: patient logs exercise, agent marks as done; tracks completion streak
Gamification: "Great job! 7-day streak. Keep going!"
Reports to PT: weekly summary of exercise compliance, form assessment, patient-reported pain scores
PT reviews and can adjust exercise prescription based on progress

Data Requirements

Primary Data Sources: PT exercise prescriptions (exercises ordered, frequency, reps), patient-recorded exercise videos, patient-reported pain scores (0 to 10 scale), patient demographics (age, diagnosis, prior injury history), PT treatment notes
Classification: PHI/PII (patient identifiers, exercise videos, treatment data)
Quality Metrics: Exercise form assessment accuracy >85% (validated against PT visual inspection); compliance tracking accuracy >95%; patient satisfaction >4.0/5
Complexity: Very High (computer vision for joint angle detection, form assessment, real-time coaching)
Systems: MedBridge (PT platform), Epic (EHR integration)

Score Breakdown

Criterion	Weight	Score (1-5)	Weighted
Time Recaptured	15%	5	0.75
Error Reduction	10%	3	0.30
Cost Avoidance	10%	3	0.30
Strategic Leverage	5%	3	0.15
Data Availability	15%	4	0.60
Process Clarity	15%	4	0.60
Ease of Implementation	10%	3	0.30
Fallback Available	10%	3	0.30
Audience (Int/Ext)	10%	3	0.30
Composite	100%		3.45

Why It Scores Well

Outcome Improvement: Higher compliance → better functional recovery; reduced pain
Patient Engagement: Video guidance and real-time feedback motivate adherence
PT Efficiency: PT monitors from distance; focuses on complex cases
Scalability: Applies to all home PT programs
Evidence Base: Tele-PT with remote monitoring shows outcomes equivalent to in-person PT for some conditions

Regulatory Alignment

FDA: Exercise guidance tool may or may not require premarket approval depending on autonomy and medical claim specificity. Advisory-only form feedback typically exempt; diagnosis or treatment recommendations may require review.
State Physical Therapy Practice: PT must order exercises; agent provides guidance. PT retains clinical responsibility.
State Telehealth Laws: Remote exercise guidance generally permissible; PT license requirements vary by state
HIPAA: Exercise video is PHI; must be encrypted and securely stored

Sprint Factory Fit

3 to 4 sprints (computer vision model training, exercise video library, real-time feedback logic, PT interface, FDA pathway review)

Sprints Required: 3 to 4 sprints (computer vision model training, exercise video library, real-time feedback logic, PT interface, FDA pathway review)
Timeline: 8 to 10 weeks from requirements to pilot
Governance: PT director review of exercise form assessment accuracy in first 50 patients; validate against PT visual inspection
Success Metrics: Exercise form assessment accuracy >85%; compliance >70%; patient satisfaction >4.1/5; functional improvement comparable to in-person PT

Comparable Implementations

MedBridge: PT platform with remote monitoring
PT Health: telehealth PT with video guidance
Research: Computer vision for exercise form assessment (emerging area)

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

Real-Time Clinical

Sepsis Early Warning Agent

Score: 3.85/5.0

Real-Time Clinical

Radiology Preliminary "Second Look"

Score: 3.7/5.0

Real-Time Clinical

Wound Care Progress Monitor

Score: 3.55/5.0