Respiratory failure & ventilation
Streamlining data recording through optical character recognition: a prospective multi-center study in intensive care units
Authors' conclusion
An OCR-based data entry system can effectively and efficiently facilitate data entry into clinical databases, making it a promising tool for future clinical data management.
Study context
- Population
- Critically ill intensive care units (ICU) patients requiring invasive mechanical ventilation and extracorporeal life support8 untrained personnel, 1018 data points
- Exposure
- Optical character recognition (OCR)-based data entry vs conventional manual data entry
- Outcome
- Data completeness and accuracy of the OCR-based system (independent validation, 8 untrained personnel, 1018 data points)
Methodological detailsmulticentre, 3 countries
- Multicentre
- 3 countries
Main finding
As reported in the abstract
Overall data completeness
98.5%
range 98.2–100%
Overall data accuracy
96.9%
range 95.3–100%
Observational data: associations, not effects.
Further findings
Data entry time per patient
- Data entry time per patient — Significantly reduced data entry time vs manual entry, mean reduction
- 43.9% [range 27.0-1.1%]
User satisfaction (overall recommendation rate, maximum of 5)
- Overall recommendation rate, high satisfaction reported
- 4.25 ± 1.04
Original publication
Streamlining data recording through optical character recognition: a prospective multi-center study in intensive care units. Crit Care. Published 18 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →