Assessment of the risk of bacteremia in patients with hematologic malignancies in the emergency department: A comparative study between logistic regression and machine learning algorithms
Antonio Gallardo-Pizarro1,2, Olivier Peyrony1-3, Christian Teijón-Lumbreras1,2 Ainhoa Castiella-Aranzasti1,2, Ana Martínez-Urrea1,2, Cynthia Terrones-Campos1,2, Tommaso Francesco Aiello1,2, Emmanuelle Gras1,2,4, Pedro Castro2,5, Cristina Pitart6, François Camelena7, Juan González del Castillo8, Alejandro Avendaño9, Òscar Miró2,10, Josep Mensa1,2, Josep M Nicolás2,5, Álex Soriano1,2,11, Carolina García-Vidal1,2, Grupo de Estudio BOSS
Affiliation of the authors
1Servicio de Enfermedades Infecciosas, Hospital Clínic de Barcelona – IDIBAPS, Barcelona, Spain. 2Universidad de Barcelona, Barcelona, Spain. 3Hospital Saint-Louis, Assistance Publique-Hôpitaux de Paris, París, France. 4Sorbonne Université, INSERM, Institut Pierre Louis d’Épidémiologie et de Santé Publique, París, France. 5Unidad de Cuidados Intensivos Médicos, Hospital Clínic de Barcelona – IDIBAPS, Barcelona, Spain. 6Servicio de Microbiología, Hospital Clínic de Barcelona, Barcelona, Spain. 7Servicio de Microbiología, Hospital Saint-Louis, Assistance Publique–Hôpitaux de Paris, Université Paris Cité, París, France. 8Servicio de Urgencias, Hospital Clínico San Carlos, Madrid, Spain. 9Servicio de Hematología, Hospital Universitario de Salamanca, Salamanca, Spain. 10Servicio de Urgencias, Hospital Clínic de Barcelona – IDIBAPS, Barcelona, Spain. 11CIBERINF, Centro de Investigación Biomédica en Red de Enfermedades Infecciosas, Spain.
Gallardo-Pizarro A, Peyrony O, Teijón-Lumbreras C, Castiella-Aranzasti A, Martínez-Urrea A, Terrones-Campos C, et al. Assessment of the risk of bacteremia in patients with hematologic malignancies in the emergency department: A comparative study between logistic regression and machine learning algorithms. Emergencias. 2026;38:089-97
Summary
Objectives.
To stratify the risk of bacteremia at the time of emergency department (ED) admission in patients with hematologic malignancies. To this end, we compared the performance of unsupervised and supervised machine learning algorithms with the classical multivariable logistic regression model.
Methods.
We conducted a multicenter, international, retrospective cohort study including consecutive ED visits of adult patients with hematologic malignancies for whom blood cultures were obtained. The primary outcome was the prediction of bacteremia. The Bacteremia Objective Score System (BOSS)-1 used multivariable logistic regression, BOSS-2 applied K-means clustering, and BOSS-3 employed a support vector machine algorithm. Discriminative performance was assessed using sensitivity and specificity. External validation of the results was performed.
Results.
The derivation cohort included 679 ED visits. Blood cultures tested positive in 88 cases (13%). BOSS-1 identified low-risk patients (3.1% bacteremia) with high sensitivity (94%; 95% CI, 87–97) but limited specificity (30%; 95% CI, 26–34). BOSS-2 better identified high-risk patients (29% bacteremia; sensitivity 93% [95% CI, 84–97], specificity 30% [95% CI, 26–34]). BOSS-3 classified all patients into low-risk (66.8%) or high-risk (33.2%) categories, without an intermediate group, unlike the other models, showing the best balance between sensitivity (61%; 95% CI, 59–64) and specificity (71%;
95% CI, 70–73) and yielding the most reproducible results in the external validation cohort.
Conclusions.
The BOSS algorithms enabled effective bacteremia risk stratification in the ED, with supervised machine learning models demonstrating the greatest potential clinical utility.
