PEX Scheduling athena hackathon
Data reconciliation and weighted scoring framework prototype for AI-driven patient scheduling optimization
Project Overview
Data reconciliation and weighted scoring framework prototype for AI-driven patient scheduling optimization
Key Features
Data Reconciliation
Cross-source analysis identifying data quality issues and establishing validation rules
Weighted Scoring Framework
Multi-factor algorithm balancing patient preferences, provider availability, and resource efficiency
Snowflake Analysis
Large-scale data querying and statistical analysis for scheduling patterns
GraphQL Integration
API layer for flexible data access and integration with existing healthcare systems
Impact & Highlights
Hackathon Completion
End-to-end prototype delivered within tight timeline demonstrating practical viability
Stakeholder Validation
Positive feedback from healthcare professionals on approach and implementation
Production Foundation
Established groundwork and framework for continued development into production system
README.md
Project Overview
A hackathon project focused on optimizing patient scheduling through data-driven approaches. Conducted comprehensive data reconciliation and prototyped a weighted scoring framework to enable AI-driven scheduling recommendations.
Key Contributions
Data Reconciliation
- Analyzed patient scheduling data across multiple sources
- Identified data quality issues and inconsistencies
- Established data validation rules
Weighted Scoring Framework
- Designed scoring algorithm considering multiple factors
- Patient preferences and constraints
- Provider availability optimization
- Resource utilization efficiency
Technical Implementation
- Python: Data analysis and prototype development
- Snowflake: Large-scale data querying and analysis
- GraphQL: API integration for data access
- Data Analysis: Statistical analysis and pattern recognition
Impact
- Prototyped foundation for AI-driven patient scheduling
- Demonstrated feasibility of weighted scoring approach
- Identified key data points for scheduling optimization
- Created framework for future production implementation
Hackathon Achievements
- Completed end-to-end prototype within hackathon timeline
- Demonstrated practical application of data analysis
- Received positive feedback from stakeholders
- Established groundwork for continued development