Development of a random forest model for hypotension prediction after anesthesia induction for cardiac surgery.

BACKGROUND: Hypotension after the induction of anesthesia is known to be associated with various adverse events. The involvement of a series of factors makes the prediction of hypotension during anesthesia quite challenging. AIM: To explore the ability and effectiveness of a random forest (RF) model in the prediction of post-induction hypotension (PIH) in patients undergoing cardiac surgery. METHODS: Patient information was obtained from the electronic health records of the Second Affiliated Hospital of Hainan Medical University. The study included patients, ≥ 18 years of age, who underwent cardiac surgery from December 2007 to January 2018. An RF algorithm, which is a supervised machine learning technique, was employed to predict PIH. Model performance was assessed by the area under the curve (AUC) of the receiver operating characteristic. Mean decrease in the Gini index was used to rank various features based on their importance. RESULTS: Of the 3030 patients included in the study, 1578 (52.1%) experienced hypotension after the induction of anesthesia. The RF model performed effectively, with an AUC of 0.843 (0.808-0.877) and identified mean blood pressure as the most important predictor of PIH after anesthesia. Age and body mass index also had a significant impact. CONCLUSION: The generated RF model had high discrimination ability for the identification of individuals at high risk for a hypotensive event during cardiac surgery. The study results highlighted that machine learning tools confer unique advantages for the prediction of adverse post-anesthesia events.

Experimental and theoretical studies on the morphogenesis of bacterial biofilms.

Biofilm morphogenesis not only reflects the physiological state of bacteria but also serves as a strategy to sustain bacterial survival. In this paper, we take the Bacillus subtilis colony as a model system to explore the morphomechanics of growing biofilms confined in a defined geometry. We find that the growth-induced stresses may drive the occurrence of both surface wrinkling and interface delamination in the biofilm, leading to the formation of a labyrinthine network on its surface. The wrinkles are perpendicular to the boundary of the constraint region. The variation in the surface undulations is attributed to the spatial stress field, which is isotropic in the inner regime but anisotropic in the vicinity of the boundary. Our experiments show that the directional surface wrinkles can confer biofilms with anisotropic wetting properties. This study not only highlights the role of mechanics in sculpturing organisms within the morphogenetic context but also suggests a promising route toward desired surfaces at the interface between synthetic biology and materials sciences.