Leveraging natural language processing artificial intelligence for automated data extraction of ejection fraction and strain from cardiovascular imaging reports

Key Points

• The aim is to evaluate the effectiveness of AI in extracting ejection fraction and strain from imaging reports.
• Utilized natural language processing algorithms to analyze cardiovascular imaging reports.
• Compared automated extraction results with manual data entry by professionals.
• Assessed extraction accuracy and time efficiency.
• Automated extraction achieved an accuracy rate of 92%, significantly higher than manual methods.
• Data extraction time was reduced by 70%, indicating enhanced efficiency with AI.
• No significant discrepancies were reported in clinical relevance between methods.