Bloodstream infection: Derivation and validation of a reliable and multidimensional prognostic score based on a machine learning model (BLISCO) - 13/11/24
, Benedetta Gottardelli, PhD c, Tommaso Novellino d, Carlotta Masciocchi, PhD e, Silvia Lamonica a, Rita Murri, MD aRésumé |
Background |
A bloodstream infection (BSI) prognostic score applicable at the time of blood culture collection is missing.
Methods |
In total, 4,327 patients with BSIs were included, divided into a derivation (80%) and a validation dataset (20%). Forty-two variables among host-related, demographic, epidemiological, clinical, and laboratory extracted from the electronic health records were analyzed. Logistic regression was chosen for predictive scoring.
Results |
The 14-day mortality model included age, body temperature, blood urea nitrogen, respiratory insufficiency, platelet count, high-sensitive C-reactive protein, and consciousness status: a score of ≥ 6 was correlated to a 14-day mortality rate of 15% with a sensitivity of 0.742, a specificity of 0.727, and an area under the curve of 0.783. The 30-day mortality model further included cardiovascular diseases: a score of ≥ 6 predicting 30-day mortality rate of 15% with a sensitivity of 0.691, a specificity of 0.699, and an area under the curve of 0.697.
Conclusions |
A quick mortality score could represent a valid support for prognosis assessment and resources prioritizing for patients with BSIs not admitted in the intensive care unit.
Le texte complet de cet article est disponible en PDF.Highlights |
• | A BSI prognostic score applicable at the time of blood culture collection is missing. |
• | BLISCO is a multidimensional prognostic score for non-ICU patients with BSI. |
• | BLISCO was derived from a machine learning model, which ensures strong performance. |
• | Prognostic scores are essential instruments for optimizing resource allocation. |
Key Words : Non-ICU ward, Antimicrobial stewardship tool, Early mortality score, Prognostic stratification tool
Plan
| Ethics approval: Ethics approval was given by the Ethics Commission of the Fondazione Policlinico Universitario A. Gemelli IRCCS, of Rome (ID 4801). The study was performed in accordance with the Declaration of Helsinki. |
|
| Conflicts of interest: None of the authors have potential conflict of interests. Marta Camici received speakers’ honoraria by Gilead, Rita Murri received speakers’ honoraria by Lilly and participates on a Data Safety Monitoring Board or Advisory Board sponsored by Merck Sharp and Dome. |
Vol 52 - N° 12
P. 1377-1383 - décembre 2024 Retour au numéro
Article précédent
- Drastic hourly changes in hand hygiene workload and performance rates: A multicenter time series analysis
- Lori D. Moore, James W. Arbogast, Greg Robbins, Megan DiGiorgio, Albert E. Parker
- A multicentric outbreak of Candida auris in Mexico: 2020 to 2023
- Patricia Rodríguez-de la Garza, Carlos de la Cruz-de la Cruz, José Iván Castillo Bejarano, Alicia Estela López Romo, Jorge Vera Delgado, Beatriz Aguilar Ramos, Mirna Natalia Martínez Neira, Daniel Siller Rodríguez, Héctor Mauricio Sánchez Rodríguez, Omar Alejandro Rangel Selvera
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?