Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model.

INTRODUCTION: This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong. METHODS: This retrospective analysis included all patients admitted to the intensive care unit of Pamela Youde Nethersole Eastern Hospital from January 2010 to December 2019. The ANN model was constructed using parameters identical to the APACHE IV model. Discrimination performance was assessed using area under the receiver operating characteristic curve (AUROC); calibration performance was evaluated using the Brier score and Hosmer-Lemeshow statistic. RESULTS: In total, 14 503 patients were included, with 10% in the validation set and 90% in the ANN model development set. The ANN model (AUROC=0.88, 95% confidence interval [CI]=0.86-0.90, Brier score=0.10; P in Hosmer-Lemeshow test=0.37) outperformed the APACHE II model (AUROC=0.85, 95% CI=0.80-0.85, Brier score=0.14; P<0.001 for both comparisons of AUROCs and Brier scores) but showed performance similar to the APACHE IV model (AUROC=0.87, 95% CI=0.85-0.89, Brier score=0.11; P=0.34 for comparison of AUROCs, and P=0.05 for comparison of Brier scores). The ANN model demonstrated better calibration than the APACHE II and APACHE IV models. CONCLUSION: Our ANN model outperformed the APACHE II model but was similar to the APACHE IV model in terms of predicting hospital mortality in Hong Kong. Artificial neural networks are valuable tools that can enhance real-time prognostic prediction.

Alcohol Consumption and Depression Among University Students and Their Perception of Alcohol Use.

OBJECTIVES: To investigate the association between alcohol use and depression among university students in Hong Kong, their stress-coping methods, and their knowledge and perception of the effects of alcohol on health. METHODS: 345 full-time undergraduate students from The University of Hong Kong were invited to complete a questionnaire to assess their alcohol consumption (Alcohol Use Disorders Identification Test, CAGE questionnaire), depressive symptoms (Patient Health Questionnaire-9), and stress-coping methods (Coping Orientation to Problems Experienced Inventory), as well as knowledge and perception of alcohol consumption on health. Multiple linear regression was used to determine significant variables associated with depressive symptoms. Multinominal logistic regression was used to determine the effect of such variables on depressive symptom caseness and AUDIT drinking risk groups. RESULTS: 43.2% of respondents were moderate- to high-risk drinkers, but only 23.2% were self-reported as moderate- to high-level drinkers. 57.9% of respondents had mild to severe depressive symptoms. Probable depression was more likely to occur in female students, those with higher general stress, those who do not use social support for stress-coping, and those who smoke. High-risk drinkers were more likely to occur in older students, smokers, those with higher household income, and those with higher general stress levels. Students with higher levels of depressive symptoms and higher risk of alcohol consumption were more likely to use avoidance for stress-coping. 89.5% of students considered alcohol consumption moderately to very harmful to health, but students demonstrated only moderate knowledge levels of alcohol consumption on health. CONCLUSION: Alcohol consumption and depressive symptoms are prevalent among university students in Hong Kong. The use of avoidance for stress-coping is common in those with higher levels of depressive symptoms and higher-risk drinkers. Students tend to avoid seeking help for depressive symptoms and potentially take up drinking as a coping strategy. Context-specific approaches should be used when providing counselling services for student wellbeing in university settings. Further education of university students on knowledge and perception of alcohol consumption on health should be provided.