Real-time machine learning-assisted sepsis alert enhances the timeliness of antibiotic administration and diagnostic accuracy in emergency department patients with sepsis: a cluster-randomized trial.

Machine learning (ML) has been applied in sepsis recognition across different healthcare settings with outstanding diagnostic accuracy. However, the advantage of ML-assisted sepsis alert in expediting clinical decisions leading to enhanced quality for emergency department (ED) patients remains unclear. A cluster-randomized trial was conducted in a tertiary-care hospital. Adult patient data were subjected to an ML model for sepsis alert. Patient visits were assigned into one of two groups. In the intervention cluster, staff received alerts on a display screen if patients met the ML threshold for sepsis diagnosis, while patients in the control cluster followed the regular alert process. The study compared triage-to-antibiotic (TTA) time, length of stay, and mortality rate between the two groups. Additionally, the diagnostic performance of the ML model was assessed. A total of 256 (intervention) and 318 (control) sepsis patients were analyzed. The proportions of patients who received antibiotics within 1 and 3 h were higher in the intervention group than in the control group (in 1 h; 68.4 vs. 60.1%, respectively; P = 0.04, in 3 h; 94.5 vs. 89.0%, respectively; P = 0.02). The median TTA times were marginally shorter in the intervention group (46 vs. 50 min). The area under the receiver operating characteristic curve (AUROC) of ML in early sepsis identification was significantly higher than qSOFA, SIRS, and MEWS. The ML-assisted sepsis alert system may help sepsis ED patients receive antibiotics more rapidly than with the conventional, human-dedicated alert process. The diagnostic performance of ML in prompt sepsis detection was superior to that of the rule-based system.Trial registration Thai Clinical Trials Registry TCTR20230120001. Registered 16 January 2023-Retrospectively registered, https://www.thaiclinicaltrials.org/show/TCTR20230120001 .

Machine learning algorithms for early sepsis detection in the emergency department: A retrospective study.

BACKGROUND: Early recognition and treatment of sepsis are crucial for improving patient outcomes. However, the diagnosis of sepsis remains challenging because of vague clinical presentations. OBJECTIVES: We aim to developed novel sepsis screening tools with machine learning models and compared their performance with traditional methods. METHODS: We used machine learning algorithms to develop models for early risk prediction of sepsis based on retrospective single-center electronic health record data from adult patients who presented to the emergency department (ED) from June 2018 through May 2020. Available triage data including vital signs, baseline characteristics, and chief complaints served as predictors. In our study, 80% and 20% of the data were randomly split into training and testing sets, respectively. Derived from the training set, we built the models based on four machine learning algorithms: logistic regression, gradient boosting, random forest, and neural network. Our primary outcome was the model performance that predicted the final diagnosis of sepsis determined by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and predictive performance compared with those of the reference models (quick sequential organ failure assessment [qSOFA], modified early warning score [MEWS], and systemic inflammatory response syndrome [SIRS]) using the testing dataset. RESULTS: In total, 133,707 ED visits were analyzed. All machine learning models outperformed the reference models by achieving a higher AUROC (e.g., AUROC 0.931 [95% CI 0.921-0.944] in our best model (random forest algorithm) vs 0.635 [95% CI 0.613-0.660] in qSOFA, 0.688 [95% CI 0.662-0.715] in MEWS, and 0.814 [95% CI 0.794-0.833] in SIRS). CONCLUSION: The machine learning models demonstrated superior performance in prediction of sepsis diagnosis among emergency patients compared with that using the traditional screening tools. Further studies are needed to determine whether the models will enhance physicians' judgments and improve patient outcomes.

Difficult airway predictors were associated with decreased use of neuromuscular blocking agents in emergency airway management: a retrospective cohort study in Thailand.

BACKGROUND: It is recommended that difficult airway predictors be evaluated before emergency airway management. However, little is known about how patients with difficult airway predictors are managed in emergency departments. We aimed to explore the incidence, management and outcomes of patients with difficult airway predictors in an emergency department. METHODS: We conducted a retrospective study using intubation data collected by a prospective registry in an academic emergency department from November 2017 to October 2018. Records with complete assessment of difficult airway predictors were included. Two categories of predictors were analyzed: predicted difficult intubation by direct laryngoscopy and predicted difficult bag-mask ventilation. The former was evaluated based on difficult external appearance, mouth opening and thyromental distance, Mallampati score, obstruction, and limited neck mobility as in the mnemonic "LEMON". The latter was evaluated based on difficult mask sealing, obstruction or obesity, absence of teeth, advanced age and reduced pulmonary compliance as in the mnemonic "MOANS". The incidence, management and outcomes of patients with these difficult airway predictors were explored. RESULTS: During the study period, 220 records met the inclusion criteria. At least 1 difficult airway predictor was present in 183 (83.2%) patients; 57 (25.9%) patients had at least one LEMON feature, and 178 (80.9%) had at least one MOANS feature. Among patients with at least one difficult airway predictor, both sedation and neuromuscular blocking agents were used in 105 (57.4%) encounters, only sedation was used in 65 (35.5%) encounters, and no medication was administered in 13 (7.1%) encounters. First-pass success was accomplished in 136 (74.3%) of the patients. Compared with patients without predictors, patients with positive LEMON criteria were less likely to receive neuromuscular blocking agents (OR 0.46 (95% CI 0.24-0.87), p = 0.02) after adjusting for operator experience and device used. There were no significant differences between the two groups regarding glottic view, first-pass success, or complications. The LEMON criteria poorly predicted unsuccessful first pass and glottic view. CONCLUSIONS: In emergency airway management, difficult airway predictors were associated with decreased use of neuromuscular blocking agents but were not associated with glottic view, first-pass success, or complications.