The accuracy of fully-automated algorithms for the surveillance of central venous catheter-related bloodstream infection in hospitalised patients.
Moa Karmefors IdvallHideyuki TanushiAndreas BergePontus NauclérSuzanne Desirée van der WerffPublished in: Antimicrobial resistance and infection control (2024)
Both fully-automated surveillance algorithms for CVC-BSI performed well and could effectively replace manual surveillance. The simpler algorithm, using only microbiology data, is suitable when BCx testing adheres to recommendations, otherwise the algorithm using symptom data might be required. Further validation in other settings is necessary to assess the algorithms' generalisability.
Keyphrases
- machine learning
- deep learning
- big data
- public health
- artificial intelligence
- end stage renal disease
- electronic health record
- newly diagnosed
- ejection fraction
- chronic kidney disease
- peritoneal dialysis
- high throughput
- prognostic factors
- patient reported
- escherichia coli
- multidrug resistant
- patient reported outcomes