Healthcare AI · Prompt Engineering · LLM Architecture
When Seconds Matter, Doctors Shouldn't Have to Hunt for Information
How a language model transforms fragmented patient records into a glanceable clinical card.
Role
Lead UX Designer · Prompt Engineer
Type
Concept Prototype · Ongoing
Stack
LLM · Prompt Architecture · React
Status
Ongoing. Zero hallucination output achieved.
The Problem
"A physician has 60–90 seconds to scan a patient's history before entering the consultation room."
63%
Physician burnout rate
12M
Diagnostic errors annually (US)
~7 items
Working memory capacity
The source data is raw EHR: unformatted, inconsistent, and dense. Physicians aren't missing information because it doesn't exist. They're missing it because the interface buries it. The problem isn't clinical. It's architectural.
"14 of 21 major studies directly link clinician burnout to clinically significant medical errors. The AMA frames this as a system failure. Not a lack of physician resilience."
Source: PubMed burnout–error meta-analysis; Armstrong Institute (Johns Hopkins)
The Solution
The Patient Summary Card
I designed a prompt engineering architecture that uses an LLM as a Clinical Logic Engine. The system extracts only what's clinically relevant, surfaces critical flags first, and outputs a clean structured card. No hallucination. No interpretation. Clinical judgment stays with the physician.
Margaret H., 54
Female · GP visit · Dr. A. Osei
Alerts
HbA1c overdue, 14 months
Guideline: retest every 6 months for Type 2 DM
Cardiology referral unresolved
Referred 8 months ago, no outcome recorded
Visit Reason
Fatigue and shortness of breath, onset 6 weeks ago, gradual
Active Conditions
Current Medications
Patient Voice
"The tiredness is affecting my work. I'm worried the breathing could be something serious."
Data Quality
DEFAULT STATE · ALL DATA PRESENT
David K., 67
Male · GP visit · Dr. A. Osei
Alerts
Allergy record incomplete
Sulfa allergy logged, no reaction severity documented
Visit Reason
Routine review, knee pain management
Active Conditions
Current Medications
Patient Voice
No patient-stated concern found in record
Data Quality
INCOMPLETE DATA STATE · MISSING FIELDS SURFACED
Yusra M., 71
Female · GP visit · Dr. A. Osei
Alerts. Review Before Entering.
Warfarin + new Ibuprofen script, interaction risk
Prescribed by out-of-hours GP 3 days ago, not reviewed by this practice
INR result outstanding, 19 days
Last INR: 3.8 (above therapeutic range). Retest overdue.
Falls risk, 2 incidents in past 4 months
Formal falls assessment not completed
Renal function, last checked 11 months ago
Relevant given Warfarin dosing and age
Visit Reason
Dizziness and unsteadiness on feet, onset 2 weeks ago
Active Conditions
Patient Voice
"I feel unsteady when I stand up. I am frightened of falling again."
ALERT-HEAVY STATE · CRITICAL FLAGS PRIORITISED
The Architecture
Prompt Engineering as UX
The logic layer does what a good UX system always does: it makes decisions so the user doesn't have to. Five rules govern every output.
Zero filler
No introductory text, no hedging language. Output begins immediately with the first JSON key.
Alert-first ordering
Overdose risks, unresolved allergies, and missing critical data surface before any summary content. A doctor must see risks before context.
Confidence calibration
The model does not diagnose, recommend, or interpret. It structures and surfaces. Clinical judgment remains with the physician.
Human layer
One patient-stated concern extracted verbatim from notes. If none exists, marked as missing. Never inferred.
Confidence ceiling
The model does not diagnose or interpret. It surfaces, and flags what it doesn't know.
FIG A. CLINICAL LOGIC ENGINE. Prompt architecture across input, logic, data, and component layers.
Research Grounding
The Evidence Base
Working memory ceiling
~7 items
A typical pre-consultation EHR data load far exceeds working memory capacity, forcing physicians into triage mode before the patient enters the room.
CLT in medicine (AMEE Guide No. 86)
AI vs full record review
50% less review time · 80% accuracy
LLM-generated summaries match or exceed clinician accuracy at half the review time.
Comparing AI- vs. Clinician-Authored Summaries (medRxiv, 2025)
Diagnostic safety
63% burnout · 14/21 studies · 12M errors/year
Burnout drives production pressure, which drives path-of-least-resistance decisions. The AMA frames this as a system failure. Fix the interface, not the person.
PubMed meta-analysis; Armstrong Institute; AMA research
Quality of interaction, not duration
18% → 92.7% satisfaction rate
Patients who feel "seen" have higher enablement scores. The human layer in the card gives physicians the raw material to create that moment, even in 15 minutes.
Enablement After Consultation in Primary Healthcare (Dove Press, 2025)
Next
"Expanding to multi-patient queue view and shift handover summaries."