Educational simulation environment. Do not enter real patient information. AI content supports learning and reflection; it does not replace clinical judgment, local policy, or escalation pathways.

Explainability Bench

A learning signal is evidence to be interrogated, never an instruction. Work the four questions before you respond to anything on this platform.

Four questions

Interrogate the signal

Worked example uses a synthetic acute-care record. Open each question to see what to inspect.

Worked example

“Pattern consistent with clinical deterioration over the next 12 hours in this synthetic record.” It is a statement about a pattern, not about a diagnosis or a required action.

Inspect before you respond
  • Output type: ranked learning signal, not a validated score
  • Time horizon the signal was framed around
  • Population the training example described
Common pitfall

Reading a pattern statement as a clinical conclusion.

Human in the loop

Where meaning is made

The signal is not the intervention. The nurse's assessment and action are the intervention.

  1. Step 1 — Review context
    Timeline

    Synthetic vitals, symptoms, labs, medications, notes and treatment history assembled into one reviewable story.

  2. Step 2 — Learning signal
    Prioritised, never automatic

    A transparent rule fires and shows contributing factors in context. Nothing is closed, ordered or actioned by the system.

  3. Step 3 — Explainability panel
    Inputs, gaps, limits

    Horizon, contributing signals, missing data, known limitations and links to institutional guidance.

  4. Step 4 — Nurse action
    Meaning is made here

    Validate, assess, reassess, communicate, escalate per local policy and document clinical reasoning.

    Nurse authority
Across settings

Same discipline, different context

Each setting states its own boundary. None of these are decision-support claims.

Acute care

Deterioration pattern recognition with reviewable worklists to support timely escalation.

A single screening score is never sufficient on its own.

Oncology

Symptom-burden trends across long, complex longitudinal records.

Never infer an adverse drug event or recommend a medication change.

Community health

Outreach priorities and missed-care patterns to support equity-focused prevention.

Social-determinant variables require documented equity review before use.

Transitional care

High-risk transitions and medication complexity flagged for education and follow-up.

Flags support teaching and handover only, not discharge decisions.

Risk register

What goes wrong

Biased training data

Performance gaps by race, ethnicity, age, language or geography that overall accuracy hides.

Control: Measured subgroup performance, published in the Transparency Passport.

Automation bias

The plausible suggestion is accepted because it is on screen, not because it fits this person.

Control: Mandatory rationale, and disagree / need-more-data as first-class choices.

Alert burden

Volume erodes attention until real signals are dismissed with everything else.

Control: No alarm styling, no sounds, ranked review lists instead of interruptions.

Model drift

Populations and care patterns move; an artifact quietly stops describing them.

Control: Scheduled re-review dates and append-only change history per registry record.

Reminder

Fairness is measured, not assumed

Overall accuracy tells you nothing about how an artifact behaves for a subgroup. Where subgroup performance has not been measured, this platform says so rather than implying it is fine.