AI-Enabled Clinical Data Management

From Manual Data Cleaning to Intelligent Data Operations

Autores/as

  • Keerthi Manne 502 Pin Oak Ct, Springcity, PA-19475.

DOI:

https://doi.org/10.66838/sauc.6558

Palabras clave:

Clinical Data Management, Artificial Intelligence, Data Cleaning, Anomaly Detection, Medical Coding, Central Statistical Monitoring, Risk-Based Quality Management, ICH E6(R3).

Resumen

Clinical data management (CDM) ensures that trial data are accurate, complete, and traceable, yet much of it still depends on manual cleaning: programmed edit checks, source data verification, query tracking, hand coding of medical terms, and a laborious path to database lock. Revised good clinical practice guidance and new regulatory principles for artificial intelligence (AI) encourage risk-proportionate, technology-enabled quality management. This paper proposes a framework for intelligent data operations that combines a maturity model, an architecture for AI-assisted detection, prioritization, and coding, a CRISP-DM-based lifecycle, and a credibility-based governance process, and it tests three components in a simulation. The simulation uses a synthetic trial of about 1,500 participants at 40 sites with about 84,000 data fields, 2% of which were corrupted, and a synthetic adverse-event dictionary; it demonstrates the method and does not report real trial data...

Descargas

Los datos de descargas todavía no están disponibles.

Estadísticas globales ℹ️

Totales acumulados desde su publicación
0
Visualizaciones
0
Descargas
0
Total

Descargas

Publicado

2024-08-30

Cómo citar

Keerthi Manne. (2024). AI-Enabled Clinical Data Management: From Manual Data Cleaning to Intelligent Data Operations. Street Art & Urban Creativity, 10(2), 112–126. https://doi.org/10.66838/sauc.6558

Número

Sección

Artículos