Bayer: Research and Interface Design for ICU ARDS Monitoring

User Research & Insights

1. Interviews: I spoke with ICU physicians and nurses about the problems they faced while managing ARDS.
2. Observation: I observed ICU work, mapped the existing workflows and noted where information or time was lost.
3. Surveys: A wider group of ICU staff answered questions about alarm fatigue, system usability and medication compliance.
4. Wireframe testing: A pilot group tested the early flows against the clinical requirements and safety-critical tasks.

Workflow synthesis

I translated clinical requirements into reviewable ARDS-monitoring workflows that the clinical and product teams could inspect together.

I separated the clinician-facing bedside view from the investigator view so each team could focus on the decisions it needed to make.

I made changing disease stage, medication response and patient status easier to scan without losing the supporting context.

I used prototype reviews to test whether the information hierarchy supported the next clinical or research action.

Interaction and risk modelling

The interaction work focused on behaviour that could affect a clinical decision:

1. ARDS stage: Each stage, including at risk and severe, had a distinct visual treatment for faster recognition.
2. Alert priority: Urgent alerts appeared first so clinicians could separate them from lower-priority notifications.
3. Medication tracking: A dedicated section showed administration times and doses.

Prototyping & User Feedback Loop

We built interactive prototypes for admission, medication scheduling and real-time vital-sign monitoring.

1. Structured testing: ICU staff and principal investigators worked through the prototypes in moderated sessions.
2. What we heard: Doctors wanted adjustable alert thresholds. Nurses asked for shorter data-entry forms. IT staff needed clear security controls for clinical data.

Context & Problem Statement

ARDS is a life-threatening condition that requires timely, informed decisions in intensive care. The teams we studied did not have one real-time view connecting patient monitoring with the ARDS medication workflow.

Key Challenges

1. Fragmented monitoring: Clinicians had no single view of vital signs, disease stage and medication response.
2. Data spread across systems: Nurses and doctors checked several systems to understand a change in patient status.
3. Research data: Principal investigators had to combine separate sources before they could analyse treatment outcomes across patient groups.

Stakeholder Analysis: Who We’re Designing For

Doctors

1. Need: A reliable view of ARDS progression that supports treatment decisions.
2. Problem: Important changes could be buried in a large volume of patient data.

Nurses

1. Need: An interface that fits daily ICU work without adding unnecessary steps.
2. Problem: Alarm fatigue and slow data entry took time away from patient care.

Principal Investigators

1. Need: A shared dataset for comparing medication response across ARDS stages and patient groups.
2. Problem: Separate data sources made larger clinical analyses slower and more prone to error.

Impact Metrics & Outcomes

The evaluation focused on the following outcomes:

Faster review of critical changes

1. Validation focus: Whether clinicians could recognise a critical change and decide what to review next without searching across separate views.
2. Finding: Real-time visual cues helped teams decide which changes needed attention first.

Less switching between systems

1. Workflow focus: Bring disease progression, vital signs, medication response and alerts into one clinical view.
2. Finding: The combined dashboard reduced the need to switch between separate monitoring views.

Patient-outcome boundary

This portfolio documents the research and interface work. It does not claim that the design caused a measured change in patient outcomes.

The design intent was to make warning signs and supporting data visible sooner, so clinicians could decide what to investigate next.