MeDo Screenshot
MeDo Screenshot

SenseAI — AI-Powered Rural Healthcare Assistant

Bringing intelligent, real-time clinical guidance to community health workers — even without internet.

Inspiration

Access to timely healthcare guidance remains a major challenge in rural and low-resource areas. Community Health Workers (CHWs) often have to make critical decisions with limited tools, delayed diagnostics, and poor connectivity.

We were inspired to build a solution that could assist them with real-time risk assessment and actionable guidance — even without internet access.

What It Does

SenseAI is an AI-powered rural healthcare assistant that helps assess patient conditions and provide structured medical guidance. It supports multiple conditions including:

Maternal Hemorrhage
Tuberculosis Adherence
Pesticide Exposure
Diabetic Foot Ulcers (DFU)

The system collects patient inputs, processes them through specialized AI agents, and outputs:

Output	Description
Risk Score & Level	Quantified severity assessment
Clear Explanation	Human-readable reasoning
Actionable Checklist	Step-by-step guidance for CHWs
Missing Data Indicators	Flags incomplete assessments

It works across multiple platforms:

Mobile App (Flutter)
WhatsApp Chatbot
Voice Call Agent

How We Built It

SenseAI uses a hybrid AI architecture designed for real-world, low-resource environments.

Frontend

Flutter mobile application for Community Health Workers

Backend

Flask APIs handling different diagnosis agents

AI Models

Model	Role
DeepSeek	Reasoning and structured decision-making
VisionPro + Custom Segmentation	DFU image analysis
Gemma 2B (quantized)	Offline inference via `llama.cpp`

Integrations

WhatsApp Cloud API — Chat-based interaction
ElevenLabs — Voice-based AI agent

Each condition is handled by a dedicated agent with structured scoring logic to ensure reliable and consistent outputs.

SenseAI Dashboard — Clinic Management Layer (Medo)

While the Flutter app serves Community Health Workers in the field, SenseAI is complemented by Medo — a browser-based clinic management dashboard built for NGO administrators and clinic supervisors who need to oversee operations, track worker activity, and analyze case data at a higher level.

What Medo Adds

The Flutter app handles the point-of-care side: CHWs assess patients, generate risk scores, and receive actionable checklists in real time. Medo closes the loop on the administrative and analytical side, giving clinic admins visibility into everything happening across their workforce.

Layer	Tool	Users
Field (point-of-care)	Flutter Mobile App	Community Health Workers
Clinic (management & oversight)	Medo Web Dashboard	Clinic Admins / NGO Supervisors

What Medo Does

Medo is a mobile-responsive, browser-based dashboard that requires no backend server — all data is stored in the browser's local storage, making it deployable in low-infrastructure environments without any server setup.

Authentication & Clinic Setup

Clinic admins register their clinic (name, NGO name, location, contact) and receive an auto-generated Clinic ID
Role-based login detects whether the user is a Clinic Admin or Healthcare Worker
All data is strictly scoped to each clinic's ID — one clinic cannot access another's data

Worker Management

Admins can add, edit, and remove CHWs under their clinic
Each worker gets an auto-generated Worker ID and can log in with their credentials
Worker profile pages show individual stats: total patients handled, entries submitted, disease breakdown, and a daily submission streak

Patient Entry Tracking

CHWs submit daily patient entries logging: disease type, patient count, and severity distribution (Low / Medium / High / Critical)
Severity counts are validated to sum to the total patient count before submission
Admins can view all entries across their clinic with drill-down to full entry details

Analytics

Disease-wise patient counts (bar chart)
Daily patient trends over time (line chart)
Severity distribution (pie chart)
Worker performance comparison (bar chart)
All charts support cumulative filtering by date range, disease type, and worker

Reports & Export

Admins can filter and preview aggregated reports, then export them in CSV, Excel, or PDF format — entirely client-side

Daily Reminder System

Workers who have not submitted an entry for the current day are flagged on both the admin dashboard and the worker's own dashboard, ensuring no data gaps

Supported Disease Types Medo tracks the same four conditions covered by the SenseAI Flutter app:

Maternal Hemorrhage
Tuberculosis
Pesticide Exposure
Diabetic Foot Ulcer

How Medo Complements the Flutter App

The Flutter app is built for speed and offline use in the field — it gives CHWs fast risk assessments and clinical checklists when they need them most. Medo is built for oversight and accountability — it gives supervisors the data they need to understand patterns, manage their workforce, and report outcomes to NGOs and health authorities.

Together, they form a complete end-to-end healthcare workflow:

CHW in the field (Flutter)
  → Assesses patient, generates risk score and checklist
  → Logs daily patient entry into Medo

Clinic Admin (Medo Dashboard)
  → Monitors worker activity and submission streaks
  → Analyzes disease trends and severity distributions
  → Exports reports for NGO reporting and funding accountability

Challenges We Ran Into

Running AI models offline on low-end devices due to RAM and storage limitations
Managing real-time switching between online and offline modes
Ensuring AI outputs were not random by enforcing structured scoring logic
Integrating multiple platforms (Flutter, WhatsApp, Voice) into a single workflow
Handling image-based diagnosis reliably with limited datasets

Accomplishments We Are Proud Of

Built a fully functional hybrid AI system (online + offline fallback)
Developed multi-channel access (mobile app, WhatsApp, voice calls)
Implemented clinical-style scoring instead of generic AI responses
Successfully integrated image-based DFU analysis
Paired the Flutter field app with the Medo clinic dashboard for full end-to-end workflow coverage
Created a scalable solution tailored for rural healthcare challenges

What We Learned

Prompt engineering alone is not enough — structured reasoning is critical
Offline AI deployment requires strong optimization and trade-offs
Simplicity in UI/UX is essential for real-world adoption
Multi-platform systems need strong coordination and data consistency
Building for real-world constraints is very different from building demos
A field tool without a management layer creates a data black hole — the two must work together

What's Next for SenseAI

[ ] Optimize offline models to run on low-end devices
[ ] Expand support to more diseases — malaria, anemia, child health
[ ] Add real-time doctor consultation and telemedicine integration
[ ] Improve image analysis with better datasets and model training
[ ] Support more regional languages and voice interactions
[ ] Reduce dependency on paid APIs using open-source alternatives
[ ] Sync Medo dashboard data with the Flutter app in real time via a lightweight backend
[ ] Enable offline data queuing in Medo for low-connectivity clinic environments

Tech Stack

Frontend (Field)   → Flutter (Mobile App)
Frontend (Clinic)  → React.js + Tailwind CSS (Medo Dashboard)
Backend            → Flask (Python)
AI (Online)        → DeepSeek, VisionPro
AI (Offline)       → Gemma 2B via llama.cpp
Messaging          → WhatsApp Cloud API
Voice              → ElevenLabs
Image Analysis     → Custom Segmentation Model
Data Storage       → Browser Local Storage (Medo)

Built for the communities that need it most.