Use cases · Primary care
Long-term condition review
Chronic disease reviews take time, especially for patients with several conditions, and their readings and results are scattered. Most patients don't know all their numbers. Before a diabetes, blood pressure or cholesterol review, TESSA asks about home readings, how each medicine is taken, side effects and concerns, then combines the answers with the lab results and records already on file, so the doctor starts with one summary.
At a glance
- Does
- Information gathering, Summarisation, Patient education
- Setting
- Primary care
- Specialty
- GP / Family medicine / Primary care
- Who
- Patient-facing
Also searched as
chronic disease management · chronic care review · diabetes / hypertension / cholesterol review
Questions
What does TESSA do in long-term condition review?
Chronic disease reviews take time, especially for patients with several conditions, and their readings and results are scattered. Most patients don't know all their numbers. Before a diabetes, blood pressure or cholesterol review, TESSA asks about home readings, how each medicine is taken, side effects and concerns, then combines the answers with the lab results and records already on file, so the doctor starts with one summary. It does this through information gathering, summarisation, patient education.
Does TESSA diagnose the patient?
No, TESSA never gives a patient a diagnosis. It collects and collates the information the patient provides, asks probing questions and performs risk assessment; a clinician reviews the summary and decides, and no diagnosis, summary or management plan reaches the patient until the clinician signs.
What happens if the patient mentions a warning sign?
Warning or worrying signs that require immediate attention or action go straight to the care team without alarming the patient. For time-critical presentations, TESSA supports the clinician only and is not currently intended for patient use.
How is patient information protected?
The patient surface runs on session codes, not names, and each institution's data is kept apart with a full audit trail. Our own Anonesia by TINYHealth is a proprietary software and code that removes PIIs, e.g. names, ID numbers and contact details from text before it reaches an AI model.
How do we start with this use case?
Each new use case is built and validated with clinical teams, on your own pathways and guidance. Book a meeting with us to start.
