A proof of concept for microcirculation monitoring using machine learning based hyperspectral imaging in critically ill patients: a monocentric observational study
Authors' conclusion
Based on this proof of concept, the integration of automated and standardized ROIs along with automated skin HSI analyzes, was able to differentiate between healthy individuals and patients with sepsis.
Study context
- Population
- Critically ill patients with sepsis in intensive care and healthy controls
- Participants
- 75 vs 30
- Comparison
- Sepsis vs Healthy controls
- Sepsisn = 75
- Healthy controlsn = 30reference
- Outcome
- Automated ML identification of hand regions of interest (ROIs) to distinguish healthy individuals from critically ill sepsis patients using HSI
Methodological detailsobservational, monocentric, proof of concept, machine learning, hyperspectral imaging (HSI) with TIVITA® Tissue System; fully automated ROI detection (palm, fingertips) with MediaPipe; Mann-Whitney-U test with Benjamini, Krieger, and Yekutieli (BKY) correction; Random Forest models trained using bootstrapping
- Observational
- Monocentric
- Proof of concept
- Machine learning
- HSI with TIVITA® Tissue System; fully automated ROI detection (palm, fingertips) with MediaPipe; Mann-Whitney-U test with BKY correction; Random Forest models trained using bootstrapping
Performance
As reported in the abstract
Discrimination of sepsis patients from healthy controls
AUC, combined palm and fingertip analysis
0.92
Original publication
A proof of concept for microcirculation monitoring using machine learning based hyperspectral imaging in critically ill patients: a monocentric observational study. Crit Care. Published 10 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →