Peach IntelliHealth

Every hour a patient deteriorates without clinical intervention is an hour that costs them — in outcomes, in recovery time, in the probability of a worse prognosis. In a busy hospital ward, the challenge isn't that clinicians don't care. It's that the information they need to act early isn't visible until it's almost too late.

Peach IntelliHealth built an AI/ML engine that changed that — a predictive system capable of identifying acute deterioration risk up to 24 hours before symptoms manifested. My job was to design the interface that put that intelligence in the hands of the people who could act on it.

Working alongside the design lead and development team at LKMX, I redesigned key UI components and created the detailed mockups that turned a powerful algorithmic tool into something a time-pressured clinician could use without friction, at any hour, on a mobile device.

Goal

Design a clinical mobile interface that delivers AI-driven patient risk insights to hospital staff in a format they can act on — quickly, accurately, and at the point of care.

Target Audience

Medical specialists and assistants in a Singaporean hospital requiring real-time, data-driven insights to prevent acute patient deterioration.

My Role

Digital Designer. Redesigned key UI components and created detailed mockups in collaboration with the design lead and development team.

Design Process

Explore the interactive high-fidelity prototype to experience the intended user flow:
Peach Hi-Fi Prototype.

Clinical Impact

The numbers tell the story clearly — and they were validated with clinical rigor:

• 30% reduction in patient Length-of-Stay (LOS): During the 9-month intervention period, average LOS fell by 30%. When the application was phased out, LOS returned to pre-intervention levels — a controlled reversal that confirmed the design's causal contribution to the outcome, not just a correlation.

• 24-hour early warning: The mobile interface gave healthcare professionals round-the-clock access to predictive risk scores, enabling care escalation and resource allocation a full day before symptoms would have otherwise prompted action.

• Care beyond the bedside: By making critical patient information accessible anywhere in the hospital — not just at nurse stations — the design extended the reach of clinical judgment to wherever it was needed.