Using artificial intelligence to predict adverse outcomes in emergency department patients with hyperglycemic crises in real time.

BACKGROUND: Hyperglycemic crises are associated with high morbidity and mortality. Previous studies have proposed methods to predict adverse outcomes of patients in hyperglycemic crises; however, artificial intelligence (AI) has never been used to predict adverse outcomes. We implemented an AI model integrated with the hospital information system (HIS) to clarify whether AI could predict adverse outcomes. METHODS: We included 2,666 patients with hyperglycemic crises from emergency departments (ED) between 2009 and 2018. The patients were randomized into a 70%/30% split for AI model training and testing. Twenty-two feature variables from the electronic medical records were collected. The performance of the multilayer perceptron (MLP), logistic regression, random forest, Light Gradient Boosting Machine (LightGBM), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms was compared. We selected the best algorithm to construct an AI model to predict sepsis or septic shock, intensive care unit (ICU) admission, and all-cause mortality within 1 month. The outcomes between the non-AI and AI groups were compared after implementing the HIS and predicting the hyperglycemic crisis death (PHD) score. RESULTS: The MLP had the best performance in predicting the three adverse outcomes, compared with the random forest, logistic regression, SVM, KNN, and LightGBM models. The areas under the curves (AUCs) using the MLP model were 0.852 for sepsis or septic shock, 0.743 for ICU admission, and 0.796 for all-cause mortality. Furthermore, we integrated the AI predictive model with the HIS to assist decision making in real time. No significant differences in ICU admission or all-cause mortality were detected between the non-AI and AI groups. The AI model performed better than the PHD score for predicting all-cause mortality (AUC 0.796 vs. 0.693). CONCLUSIONS: A real-time AI predictive model is a promising method for predicting adverse outcomes in ED patients with hyperglycemic crises. Further studies recruiting more patients are warranted.

Thigh emphysema as the initial presentation of colon ischemia.

The incidence of colon ischemia has increased in recent years, and is associated with high morbidity and mortality. The typical presentations of colon ischemia include abdominal pain, bloody diarrhea, and in severe case, ileus, fever and peritonitis. Here, we document a rare case of colon ischemia presenting with subcutaneous and intramuscular emphysema of the thigh. A 76-year-old woman presented to the emergency department for left thigh pain for three days. Physical examination revealed tenderness without obvious crepitus, erythema or swelling over the left groin area and a soft abdomen without tenderness. Plain abdominal film showed abnormal gas formation at the left thigh and chest film demonstrated subphrenic free air. Abdominal computer tomography found sigmoid perforation causing left retroperitoneal abscess, and subcutaneous and intramuscular emphysema over the left pelvic and thigh region. During operation, irreversible ischemia from the terminal ileum through the cecum to the sigmoid colon with gangrene and retroperitoneal abscess were found. Total colectomy with end ileostomy and peritoneal toilet were performed. However, massive bloody ascites from abdominal drainage developed on the 13th day of admission. She later passed away due to hemorrhagic shock. In conclusion, emphysema of the thigh may rarely be caused by an intestinal lesion, such as colon ischemia. Clinicians should be alert of these unusual presentations to find the hidden underlying etiologies.