Overview

PediaMetrics is a pediatric health tracking system based on simulated (false) data. It enables healthcare professionals and researchers to analyze and manage pediatric patient data efficiently. The system automates patient triage, lab result generation, and disease analysis, storing the data on Amazon S3 and Google Drive using AWS and GCP APIs. The data in Google Drive is connected to Tableau Public for live dashboards and reports.

Certain scripts run using cron jobs to generate patient visit data throughout the week (Monday to Friday, 7 AM to 4 PM EST; 1 patient every 2 hours), somewhat similar to a real-life pediatrician. This data is presented on the site’s homepage. A Flask web app allows users to view patient data and download visit summaries as PDFs, which are generated by more automated scripts.

NOTE: The patient data used in this project is RANDOMLY GENERATED or FAKE. None of the data presented belongs to nor resembles any individual.

Access the Website:
To start exploring basketball player stats and impact metrics, visit pediametrics.universe-j.com.

Features

1. Patient Data Management

• Automated generation of patient profiles, including demographics, height, weight, BMI, and ethnicity.

• Randomized yet realistic patient attributes based on age and gender.

2. Triage and Initial Evaluation

• Assigns heart rate, respiratory rate, blood pressure, temperature, and activity levels based on patient characteristics.

• Logs symptoms and assigns visit types dynamically.

3. Lab Test Simulation (Pre-Alpha)

• Generates simulated blood test results tailored to patient age and gender.

• Includes values for lead levels, hemoglobin, hematocrit, glucose levels, cholesterol, and oxygen saturation.

4. Disease Likelihood Analysis

• Matches patient symptoms and vitals against a predefined disease database.

• Calculates likelihood scores for various conditions using a weighted scoring system.

• Identifies the most probable disease and recommends treatment based on medical protocols.

5. BMI Calculation and Categorization

• Computes BMI using height and weight data.

• Classifies BMI based on age-specific thresholds.

6. Visit Summary Generation

• Produces structured visit summaries in PDF format.

• Includes patient demographics, vitals, symptoms, and treatment recommendations.

7. Data Cleaning and Processing

• Removes unnecessary columns from CSV files.

• Cleans malformed data entries.

• Filters non-alphabetical entries to maintain dataset integrity.

Usage Guide

1. Generating Patient Data

• The patientGenerator.py script creates simulated patient profiles and appends them to a master CSV file.

• Each patient receives a unique ID, birthdate, ethnicity, and BMI classification.

2. Performing Triage Evaluations

• The patientTriage.py script processes generated patient data and assigns medical evaluations.

• Evaluates vitals, activity levels, and symptoms.

3. Running Lab Test Simulations

• The labGenerator.py script generates simulated lab results for selected patients.

• Data is stored in structured CSV files for historical tracking.

4. Analyzing Patient Conditions

• The patientResults.py script compares patient data to disease criteria.

• Identifies the most likely disease and provides a likelihood score.

5. Generating Visit Summaries

• The patientSummary.py script formats patient data into structured reports.

• Outputs a PDF for clinical review.

Technical Details

Core Technologies

• Python: Core programming language.

• Flask: Web application framework for patient data visualization.

• Pandas: Data manipulation and analysis.

• NumPy: Statistical computations.

• Boto3: AWS S3 cloud storage integration.

• Google Drive API: Cloud storage for Tableau integration.

• Loguru: Logging framework for process tracking.

• Apache Airflow: Automates data updates and transfers.

Data Storage & Processing

• Data is stored on Amazon S3 and Google Drive.

• Google Drive is linked to Tableau Public for live dashboards and reports.

• Automated cleaning and preprocessing scripts ensure data consistency.

Scheduled Data Generation

• Cron jobs run patient visit generation scripts from Monday to Friday, 7 AM to 4 PM.

• Five new patient visits are created daily and logged.

Logging & Debugging

• All scripts generate logs stored in structured directories.

• Errors and warnings are logged for debugging and auditing.

Troubleshooting & Support

• For further assistance, contact jmge.work@gmail.com.

Summary

PediaMetrics provides an automated approach to pediatric data management and analysis, using simulated data for triage, diagnosis, and tracking. Data is securely stored on Amazon S3 and Google Drive, with seamless integration into Tableau Public for real-time analytics. Automated cron jobs ensure continuous data generation, while the Flask web app allows users to interact with patient records and download visit summaries as PDFs. By streamlining structured data processing and automated reporting, PediaMetrics enhances pediatric evaluations with efficiency and accuracy.