QSense — Hospital Queue Prediction

Predict Your Wait Time

Select a hospital and department to get your estimated waiting time across all three stages of your visit.

Your Details

Hospital

Department

Visit Type

Time of Visit

⏱️

No prediction yet

Fill in the form on the left and click Calculate.

Find Nearest Hospital

See all hospitals on the map and find the closest one to you.

Compare Hospitals

Side-by-side estimated wait times across all hospitals for a given department.

Hospital	Total Wait	Registration	Consultation	Pharmacy	Occupancy	Doctors (AM)	Verdict
Loading…

System Dashboard

Network-wide view of hospital load and department status — all values read directly from data.json.

🏥

—

Hospitals tracked

⏳

—

Avg wait (mins)

🔴

—

High-load departments

👨‍⚕️

—

Morning-shift doctors

Department Load

Predicted Hourly Queue (Emergency)

Outlined bar = current hour · From hourlyPeakProfile in data.json

All Hospitals — Status Overview

About This Project

Hospital Queue Time Prediction and Optimization System

Project Overview

This system predicts patient waiting times in hospitals based on current queue conditions. It uses a simple queue-based formula and simulated data to provide approximate wait time estimates across multiple stages of a hospital visit — registration, consultation, and pharmacy.

Developed By

...
ADYPSOE
BE - FE · 2026

The Formula

Waiting Time = (Number of Patients ÷ Number of Doctors) × Average Consultation Time

Total Wait = Registration Wait + Consultation Wait + Pharmacy Wait

How the System Works

The prediction formula, data structure, system config, and known limitations.

Core Prediction Formula

Wait per Stage = (Patients in Queue ÷ Doctors on Duty) × Avg. Consultation Time

Total Estimated Wait = Registration Wait + Consultation Wait + Pharmacy Wait

01

Data Layer (data.json)

All hospital profiles, department queues, doctor shift counts, and system config — time multipliers, visit type modifiers, thresholds — live in a single JSON file, completely separate from the app logic.

02

Multi-Stage Calculation

Three stages are modelled per visit: Registration, Consultation, and Pharmacy. Each is calculated independently, adjusted by time-of-day and visit type multipliers, then summed for a total.

03

Optimization Logic

After prediction, the system scans all hospitals for the same department, checks off-peak time slots, and flags high-load conditions — surfacing concrete, time-saving suggestions.

Limitations & Future Scope

⚠️

Simulated DataUses predefined profiles in data.json. Real-world use needs live hospital APIs or data partnerships.

⚠️

No Emergency InterruptionsCritical cases that bypass the queue are not modelled — this can significantly change ER wait times.

⚠️

Approximate ResultsThe model assumes steady patient flow. Real queues are bursty and unpredictable.

🚀

Future: Machine LearningA model trained on historical data, day-of-week patterns and seasonal trends would give far better predictions.

🚀

Future: Live Tracking & BookingReal-time patient flow plus slot booking would let patients reserve and receive push notifications.

data.json — Live Snapshot

First hospital entry loaded from your data file: