Background: This study aimed to evaluate whether the effect of tachycardia varies according to the degree of tissue perfusion in septic shock. Methods: Patients with septic shock admitted to the intensive care units were categorized into the tachycardia (heart rate > 100 beats/min) and non-tachycardia (≤ 100 beats/min) groups. The association of tachycardia with hospital mortality was evaluated in each subgroup with low and high lactate levels, which were identified through a subpopulation treatment effect pattern plot analysis. Results: In overall patients, hospital mortality did not differ between the two groups (44.6% vs. 41.8%, P = 0.441), however, tachycardia was associated with reduced hospital mortality rates in patients with a lactate level ≥ 5.3 mmol/L (48.7% vs. 60.3%, P = 0.030; adjusted odds ratio [OR], 0.59, 95% confidence interval [CI], 0.35–0.99, P = 0.045), not in patients with a lactate level < 5.3 mmol/L (36.5% vs. 29.7%, P = 0.156; adjusted OR, 1.39, 95% CI, 0.82–2.35, P = 0.227). Conclusion In septic shock patients, the effect of tachycardia on hospital mortality differed by serum lactate level. Tachycardia was associated with better survival in patients with significantly elevated lactate levels.

Background: Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. Methods: This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO 2 /FIO 2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine).The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). Results: Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. Conclusion Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.