Problem
Full-stack maternal health prototype supporting symptom logging, AI-driven risk assessment, personalized trimester guidance, and a real-time clinician dashboard that sorts patients by risk level.
FastAPINext.js 16TypeScriptTailwind CSSPathwayCase study / interactive demo
Case study
From problem to working system
My role
AI product engineer and full-stack developer
Solution
Full-stack maternal health prototype supporting symptom logging, AI-driven risk assessment, personalized trimester guidance, and a real-time clinician dashboard that sorts patients by risk level.
Architecture
The implementation combines the following technologies and system concerns.
FastAPINext.js 16TypeScriptTailwind CSSPathway
How it was built
- Built a full-stack maternal health platform on FastAPI and Next.js 16 with symptom logging, trimester-aware guidance, and a clinician-facing triage dashboard.
- Implemented risk scoring over logged symptoms and vitals, weighting the signs that change clinical urgency rather than treating all entries equally.
- Wrote guidance that adapts to trimester, since the same symptom carries different weight at different stages.
Security decisions
- Implemented risk scoring over logged symptoms and vitals, weighting the signs that change clinical urgency rather than treating all entries equally.
- Sorted the clinician dashboard by risk so the highest-acuity patient is first, which is the whole point of a triage view.
Major challenges
- Sorted the clinician dashboard by risk so the highest-acuity patient is first, which is the whole point of a triage view.
- Streamed updates through Pathway so a newly logged symptom re-scores the patient immediately instead of on the next page load.
- Treated the output as decision support with explicit escalation language, never as a diagnosis, which is the correct posture for a health prototype.
Verified evidence
Results and measurable impact
- Sorted the clinician dashboard by risk so the highest-acuity patient is first, which is the whole point of a triage view.
- Streamed updates through Pathway so a newly logged symptom re-scores the patient immediately instead of on the next page load.
- Wrote guidance that adapts to trimester, since the same symptom carries different weight at different stages.
- Treated the output as decision support with explicit escalation language, never as a diagnosis, which is the correct posture for a health prototype.
No separate numeric outcome is documented, so this section shows shipped technical evidence without inventing metrics.
Screenshots and access
Product view
Interactive Demo
A scoped, fully functional recreation of this project's core feature runs below, live in your browser. Reset it, resize it, or expand it to full screen.
bloomguard.zainkhalilkhan.com
BloomGuard
Product workspace
Sandbox workspace
BloomGuardWorkspace6 updates
BloomGuard
Zain Khalil Khan
Client-side sandbox. State is in memory and nothing is sent to a server.