Compare use cases

Drop two or three slugs into the URL — for example ?slugs=demo-mia-breast-screening,demo-idx-dr-retinopathy — or pick from the validated catalogue below.

Pick from validated:

AI imaging triage for the acute stroke pathway AI second reader for breast cancer screening Autonomous diabetic retinopathy screening in primary care Pre-operative risk-stratification model for major surgery Self-referral assistant for NHS Talking Therapies Type-2 diabetes long-term outcome predictor

Clear selection

	Type-2 diabetes long-term outcome predictor Netherlands	Self-referral assistant for NHS Talking Therapies United Kingdom	Autonomous diabetic retinopathy screening in primary care Netherlands
Trust badge	Validated	Validated	Validated
Evidence strength	Robust evidence	Developing evidence	Robust evidence
Pipeline stage	Validated	Validated	Validated
Intended use	Estimates 5-year risk of major diabetes-related complications (cardiovascular, renal, retinal) from longitudinal primary-care records to support care-plan intensification.	Supports patient self-referral by collecting clinical information conversationally and routing referrals, reducing administrative wait time.	Provides an autonomous screening decision for more-than-mild diabetic retinopathy from retinal fundus images, referring positive cases to ophthalmology.
Specialty	Endocrinology	Psychiatry	Other
Autonomy	Informs a human (advisory)	Human in the loop (human acts)	Autonomous (acts without a human)
Deployment	Active deployment	Active deployment	Active deployment
EU AI Act tier	High-risk	Limited risk	High-risk
EU MDR class	Not a device	Not a device	Class IIb
CE marking	Not required	Not required	CE marked
NICE ESF tier	Tier C — treat / diagnose / calculate risk	Tier B — inform / monitor	Tier C — treat / diagnose / calculate risk
Headline metric	AUC / AUROC: 0.82	Accuracy: 0.93	Sensitivity: 0.87
Subgroup assessed	Yes	Yes	Yes