Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit: A retrospective cohort study

Abstract

ObjectivesDiagnosis and management of intensive care unit (ICU)-acquired bloodstream infections are often based on positive blood culture results. This retrospective cohort study aimed to develop a classification model using data-driven characterisation to optimise the management of intensive care patients with blood cultures. Setting, methodology/designAn unsupervised clustering model was developed based on the clinical characteristics of patients with blood cultures in the Medical Information Mart for Intensive Care (MIMIC)-IV database (n = 2451). It was tested using the data from the MIMIC-III database (n = 2047). Main outcome measuresThe prognosis, blood culture outcomes, antimicrobial interventions, and trajectories of infection indicators were compared between clusters. ResultsFour clusters were identified using machine learning-based k-means clustering based on data obtained 48 h before the first blood culture sampling. Cluster γ was associated with the highest 28-day mortality rate, followed by clusters α, δ, and β. Cluster γ had a higher fungal isolation rate than cluster β (P < 0.05). Cluster δ was associated with a higher isolation rate of Gram-negative organisms and fungi (P < 0.05). Patients in clusters γ and δ underwent more femoral site vein catheter placements than those in cluster β (P < 0.001, all). Patients with a duration of antibiotics treatment of 4, 6, and 7 days in clusters α, δ, and γ, respectively, had the lowest 28-day mortality rate. ConclusionsMachine learning identified four clusters of intensive care patients with blood cultures, which yielded different prognoses, blood culture outcomes, and optimal duration of antibiotic treatment. Such data-driven blood culture classifications suggest further investigation should be undertaken to optimise treatment and improve care. Implications for clinical practiceIntensive care unit-acquired bloodstream infections are heterogeneous. Meaningful classifications associated with outcomes should be described. Using machine learning and cluster analysis could help in understanding heterogeneity. Data-driven blood culture classification could identify distinct physiological states and prognoses before deciding on blood culture sampling, optimise treatment, and improve care.