Pulse.

a daily field guide to health research that matters

◆ Console

‹ Sun · 14 Jun 2026
Promising but preliminary

Early intensive antihypertensive treatment in high-risk population of intracerebral haemorrhage expansion identified by artificial intelligence (ARCHES): study protocol for a multicentre randomised controlled trial

An AI tool can identify stroke patients most likely to benefit from aggressive blood pressure control, allowing better targeting of intensive treatment.

The ARCHES trial will randomize 680 ICH patients identified by an AI-based haematoma expansion prediction score to intensive vs. standard blood pressure reduction, testing whether AI-guided patient selection improves outcomes in this high-mortality condition. The protocol is novel in integrating a validated deep learning CT scoring system to enrich for patients most likely to benefit from aggressive BP lowering.

What the study was

Study design
RCT protocol (multicenter, n=680)
Population
ICH patients within 6h of onset at high risk of haematoma expansion by AI-based 5-point prediction score
Sample size
680
Category
Diagnostics
Maturity
Exploratory
Journal
Trials

Why it surfaced

Important methodological advance in AI-guided trial design for stroke; score limited by protocol-only status (no results). NCT06242938 registered.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.