A New Essential Functions Installed DWH in Hospital Information System: Process Mining Techniques and Natural...

Area of Science:

• Healthcare Informatics
• Data Science
• Clinical Informatics

Background:

• Traditional Hospital Information Systems (HIS) primarily analyze structured data, leaving valuable event log data underutilized.
• Existing HIS Data Warehouse systems demonstrate efficiency in analyzing structured clinical data (e.g., diagnoses, lab tests, medications).
• There's a gap in leveraging diverse event log data for secure and efficient hospital operational improvements.

Purpose of the Study:

• To investigate the application of process mining on event log data for hospital activity analysis.
• To explore the use of Natural Language Processing (NLP) for analyzing non-structured data within clinical settings.
• To demonstrate how these methods can enhance the security and efficiency of hospital operations.

Main Methods:

• Process mining techniques applied to clinical event log data.
• Natural Language Processing (NLP) algorithms for the analysis of unstructured clinical text data.
• Integration of structured and unstructured data analysis for comprehensive insights.

Main Results:

• Demonstrated potential for process mining to uncover inefficiencies and optimize clinical workflows.
• Showcased NLP's capability to extract meaningful information from non-structured clinical notes.
• Highlighted the combined power of these methods for secure and efficient hospital management.

Conclusions:

• Event log data, when analyzed with process mining and NLP, offers significant opportunities for hospital improvement.
• Integrating process mining and NLP can lead to more secure and efficient healthcare delivery.
• Further research can unlock the full potential of these advanced data analysis techniques in clinical environments.