Registration Vitals & Complains (RVC) Slip

Where this fits

These slips aren't a separate data-entry step — they're the output of two modules that already ran. Registration captures who the patient is; the Vitals IoT Kiosk captures their height, weight, and vital parameters and records which symptoms they selected. As soon as both are in the system, it prints these two slips automatically, with nothing further for staff to type.

The two slips

Sample data shown below — this is what the patient (or attendant) physically carries from the registration counter to the doctor's chamber.

Sample registration slip showing patient name, age, sex, address, department, unit consultants, CR number, and a barcode — Registration Details — from the Registration Module

Sample slip showing vital parameters (BP, pulse, SpO2, temperature, height, weight, BMI, blood sugar) alongside the chief complaints the patient selected — Vital Parameters & Chief Complaints — from the Vitals IoT Kiosk

Why print both

The doctor starts the consultation already knowing why the patient has come and what their vitals are — instead of asking from scratch and writing it all down by hand. The barcode on the registration slip also means the same record can be pulled up digitally at the doctor's desk, rather than re-typed.

Where this data could go next

The symptoms and vitals on this slip are exactly the fields a triage-prediction model would need — nothing from later in the visit, since neither the doctor's exam nor any investigation has happened yet at this point.

Diagram: From Patient Data to Smart Triage and Department Prediction. Stage 1, Patient Data in a hospital database with columns Patient ID, Age, Sex, Symptoms, Final Department, Triage Label. Stage 2, train machine learning models using demographics, symptoms and vital signs only, no lab results or history, with an XGBoost classification model for triage (Red, Yellow, Green) and a separate multiclass department-prediction model. Stage 3, for a new patient, the two models output a triage prediction and a department prediction, combined into one output: triage priority and recommended department. Benefits listed: faster triage, right department recommendation, better resource utilisation, improved patient outcomes.

From Patient Data to Smart Triage & Department Prediction — illustrative model architecture

Age, sex, symptoms, and vitals — the same fields on this slip — train two separate models: an XGBoost classifier for triage priority (Red / Yellow / Green), and a multiclass model for which department the patient should be sent to. For a new patient, the same fields captured at registration and the vitals kiosk are fed into both models, producing a triage priority and a recommended department before the patient even reaches the doctor. This is illustrative architecture, not a trained system — it would need real, accumulated slips like this one to actually train on.