Background: COVID-19, which is accompanied by acute respiratory distress, multiple organ failure, and death, has spread worldwide much faster than previously thought. However, at present, it has limited treatments. Objective: To overcome this issue, we developed an artificial intelligence (AI) model of COVID-19, named EDRnet (ensemble learning model based on deep neural network and random forest models), to predict in-hospital mortality using a routine blood sample at the time of hospital admission. Methods: We selected 28 blood biomarkers and used the age and gender information of patients as model inputs. To improve the mortality prediction, we adopted an ensemble approach combining deep neural network and random forest models. We trained our model with a database of blood samples from 361 COVID-19 patients in Wuhan, China, and applied it to 106 COVID-19 patients in three Korean medical institutions. Results: In the testing data sets, EDRnet provided high sensitivity (100%), specificity (91%), and accuracy (92%). To extend the number of patient data points, we developed a web application (BeatCOVID19) where anyone can access the model to predict mortality and can register his or her own blood laboratory results. Conclusions: Our new AI model, EDRnet, accurately predicts the mortality rate for COVID-19. It is publicly available and aims to help health care providers fight COVID-19 and improve patients’ outcomes.

Ko RE, et al. J Korean Med Sci. 2018 Jan;33(8):e65. https://doi.org/10.3346/jkms.2018.33.e65

The optimal timing of enteral nutrition (EN) in sepsis patients is controversial among societal guidelines. We aimed to evaluate the evidence of early EN’s impact on critically ill sepsis patients’ clinical outcomes. We searched the MEDLINE, Embase, CINAHL, Cochrane Library, ClinicalTrials.gov, and ICTRP databases on 10 March 2023. We included studies published after 2004 that compared early EN versus delayed EN in sepsis patients. We included randomized controlled trials (RCTs), non-RCTs, cohort studies, and case–control studies. Forest plots were used to summarize risk ratios (RRs), including mortality and mean difference (MD) of continuous variables such as intensive care unit (ICU) length of stay and ventilator-free days. We identified 11 eligible studies with sample sizes ranging from 31 to 2410. The RR of short-term mortality from three RCTs was insignificant, and the MD of ICU length of stay from two RCTs was −2.91 and −1.00 days (95% confidence interval [CI], −5.53 to −0.29 and −1.68 to −0.32). Although the RR of intestinal-related complications from one RCT was 3.82 (95% CI, 1.43 to 10.19), indicating a significantly higher risk for the early EN group than the control group, intestinal-related complications of EN reported in five studies were inconclusive. This systematic review did not find significant benefits of early EN on mortality in sepsis patients. Evidence, however, is weak due to inconsistent definitions, heterogeneity, risk of bias, and poor methodology in the existing studies.

Background: Delirium frequently occurs among patients admitted to the intensive care unit (ICU). There is limited evidence to support interventions to treat or resolve delirium in patients who have already developed delirium. Therefore, the early recognition and prevention of delirium are important in the management of critically ill patients. Objective: This study aims to develop and validate a delirium prediction model within 24 hours of admission to the ICU using electronic health record data. The algorithm was named the Prediction of ICU Delirium (PRIDE). Methods: This is a retrospective cohort study performed at a tertiary referral hospital with 120 ICU beds. We only included patients who were 18 years or older at the time of admission and who stayed in the medical or surgical ICU. Patients were excluded if they lacked a Confusion Assessment Method for the ICU record from the day of ICU admission or if they had a positive Confusion Assessment Method for the ICU record at the time of ICU admission. The algorithm to predict delirium was developed using patient data from the first 2 years of the study period and validated using patient data from the last 6 months. Random forest (RF), Extreme Gradient Boosting (XGBoost), deep neural network (DNN), and logistic regression (LR) were used. The algorithms were externally validated using MIMIC-III data, and the algorithm with the largest area under the receiver operating characteristics (AUROC) curve in the external data set was named the PRIDE algorithm. Results: A total of 37,543 cases were collected. After patient exclusion, 12,409 remained as our study population, of which 3816 (30.8%) patients experienced delirium incidents during the study period. Based on the exclusion criteria, out of the 96,016 ICU admission cases in the MIMIC-III data set, 2061 cases were included, and 272 (13.2%) delirium incidents occurred. The average AUROCs and 95% CIs for internal validation were 0.916 (95% CI 0.916-0.916) for RF, 0.919 (95% CI 0.919-0.919) for XGBoost, 0.881 (95% CI 0.878-0.884) for DNN, and 0.875 (95% CI 0.875-0.875) for LR. Regarding the external validation, the best AUROC were 0.721 (95% CI 0.72-0.721) for RF, 0.697 (95% CI 0.695-0.699) for XGBoost, 0.655 (95% CI 0.654-0.657) for DNN, and 0.631 (95% CI 0.631-0.631) for LR. The Brier score of the RF model is 0.168, indicating that it is well-calibrated. Conclusions: A machine learning approach based on electronic health record data can be used to predict delirium within 24 hours of ICU admission. RF, XGBoost, DNN, and LR models were used, and they effectively predicted delirium. However, with the potential to advise ICU physicians and prevent ICU delirium, prospective studies are required to verify the algorithm’s performance.

Background: Hospital-acquired pneumonia (HAP) and ventilator-associated pneumonia (VAP) are significant public health issues in the world, but the epidemiological data pertaining to HAP/VAP is limited in Korea. The objective of this study was to investigate the characteristics, management, and clinical outcomes of HAP/VAP in Korea.Methods: This study is a multicenter retrospective cohort study. In total, 206,372 adult patients, who were hospitalized at one of the 13 participating tertiary hospitals in Korea, were screened for eligibility during the six-month study period. Among them, we included patients who were diagnosed with HAP/VAP based on the Infectious Diseases Society of America (IDSA)/American Thoracic Society (ATS) definition for HAP/VAP.Results: Using the IDSA/ATS diagnostic criteria, 526 patients were identified as HAP/VAP patients. Among them, 27.9% were diagnosed at the intensive care unit (ICU). The cohort of patients had a median age of 71.0 (range from 62.0 to 79.0) years. Most of the patients had a high risk of aspiration (63.3%). The pathogen involved was identified in 211 patients (40.1%). Furthermore, multidrug resistant (MDR) pathogens were isolated in 138 patients; the most common MDR pathogen was Acinetobacter baumannii. During hospitalization, 107 patients with HAP (28.2%) had to be admitted to the ICU for additional care. The hospital mortality rate was 28.1% in the cohort of this study. Among the 378 patients who survived, 54.2% were discharged and sent back home, while 45.8% were transferred to other hospitals or facilities.Conclusion: This study found that the prevalence of HAP/VAP in adult hospitalized patients in Korea was 2.54/1,000 patients. In tertiary hospitals in Korea, patients with HAP/VAP were elderly and had a risk of aspiration, so they were often referred to step-down centers.

Background: Although cancer patients are increasingly admitted to the intensive care unit (ICU) for cancer- or treatment-related complications, improved mortality prediction remains a big challenge. This study describes a new ML-based mortality prediction model for critically ill cancer patients admitted to ICU. Patients and Methods: We developed CanICU, a machine learning-based 28-day mortality prediction model for adult cancer patients admitted to ICU from Medical Information Mart for Intensive Care (MIMIC) database in the USA (n = 766), Yonsei Cancer Center (YCC, n = 3571), and Samsung Medical Center in Korea (SMC, n = 2563) from 2 January 2008 to 31 December 2017. The accuracy of CanICU was measured using sensitivity, specificity, and area under the receiver operating curve (AUROC). Results: A total of 6900 patients were included, with a 28-day mortality of 10.2%/12.7%/36.6% and a 1-year mortality of 30.0%/36.6%/58.5% in the YCC, SMC, and MIMIC-III cohort. Nine clinical and laboratory factors were used to construct the classifier using a random forest machine-learning algorithm. CanICU had 96% sensitivity/73% specificity with the area under the receiver operating characteristic (AUROC) of 0.94 for 28-day, showing better performance than current prognostic models, including the Acute Physiology and Chronic Health Evaluation (APACHE) or Sequential Organ Failure Assessment (SOFA) score. Application of CanICU in two external data sets across the countries yielded 79–89% sensitivity, 58–59% specificity, and 0.75–0.78 AUROC for 28-day mortality. The CanICU score was also correlated with one-year mortality with 88–93% specificity. Conclusion: CanICU offers improved performance for predicting mortality in critically ill cancer patients admitted to ICU. A user-friendly online implementation is available and should be valuable for better mortality risk stratification to allocate ICU care for cancer patients.