A 58-year-old woman with hypertension and type 2 diabetes mellitus presented to the emergency department after five days of fever, malaise, cough and epigastric pain. On examination, the patient's temperature was 40.8°C, pulse rate 133 beats/min and blood pressure 159/73 mm Hg. Laboratory investigations showed no leukocytosis (white blood cell count 6.2 [normal range 3.2-9.2] × 10 9 /L), but an excess of immature white blood cells of 21% (0%-3%), random serum glucose level of 22.2 (normal range 3.9-5.6) mmol/L, glycosylated hemoglobin (HbA 1c) of 11.2% (< 5.7%), alanine transaminase of 144 (normal range 2-40) U/L and serum creatinine level of 75.1 (normal range 50.4-98.1) μmol/L. A chest radiograph showed an air-fluid level lesion over the right subphrenic region (Appendix 1, available at www.cmaj.ca/lookup/suppl/

Background Hyperglycemic crises are associated with high morbidity and mortality. Previous studies proposed methods for predicting adverse outcome in hyperglycemic crises, artificial intelligence (AI) has however never been tried. We implemented an AI prediction model integrated with hospital information system (HIS) to clarify this issue. Methods We included 3,715 patients with hyperglycemic crises from emergency departments (ED) between 2009 and 2018. Patients were randomized into a 70%/30% split for AI model training and testing. Twenty-two feature variables from their electronic medical records were collected, and multilayer perceptron (MLP) was used to construct an AI prediction model to predict sepsis or septic shock, intensive care unit (ICU) admission, and all-cause mortality within 1 month. Comparisons of the performance among random forest, logistic regression, support vector machine (SVM), K-nearest neighbor (KNN), Light Gradient Boosting Machine (LightGBM), and MLP algorithms were also done. Results Using the MLP model, the areas under the curves (AUCs) were 0.808 for sepsis or septic shock, 0.688 for ICU admission, and 0.770 for all-cause mortality. MLP had the best performance in predicting sepsis or septic shock and all-cause mortality, compared with logistic regression, SVM, KNN, and LightGBM. Furthermore, we integrated the AI prediction model with the HIS to assist physicians for decision making in real-time. Conclusions A real-time AI prediction model is a promising method to assist physicians in predicting adverse outcomes in ED patients with hyperglycemic crises. Further studies on the impact on clinical practice and patient outcome are warranted.

No abstract