The Effect of Indoor Daylight Levels on Hospital Costs and Length of Stay of Patients Admitted to General Surgery.

BACKGROUND: Indoor daylight levels can directly affect the physical and psychological state of people. However, the effect of indoor daylight levels on the clinical recovery process of the patient remains controversial. This study was to evaluate the effect of indoor daylight levels on hospital costs and the average length of stay (LOS) of a large patient population in general surgery wards. METHODS: Data were collected retrospectively and analyzed of patients in the Second Affiliated Hospital of Zhejiang University, School of Medicine between January 2015 and August 2020. We measured daylight levels in the patient rooms of general surgery and assessed their association with the total hospital costs and LOS of the patients. RESULTS: A total of 2,998 patients were included in this study with 1,478 each assigned to two daylight level groups after matching. Overall comparison of hospital total costs and LOS among patients according to daylight levels did not show a significant difference. Subgroup analysis showed when exposed to higher intensity of indoor daylight, illiterate patients had lower total hospital costs (CNY ¥13070.0 vs. ¥15210.3, p = 0.018) and shorter LOS (7 vs. 10 days, p = 0.011) as compared to those exposed to a lower intensity. CONCLUSIONS: Indoor daylight levels were not associated with the hospital costs and LOS of patients in the wards of general surgery, except for those who were illiterate. It might be essential to design guidelines for medical staff and healthcare facilities to enhance the indoor environmental benefits of daylight for some specific populations.

Prediction of Disease Progression of COVID-19 Based upon Machine Learning.

BACKGROUND: Since December 2019, COVID-19 has spread throughout the world. Clinical outcomes of COVID-19 patients vary among infected individuals. Therefore, it is vital to identify patients at high risk of disease progression. METHODS: In this retrospective, multicenter cohort study, COVID-19 patients from Huoshenshan Hospital and Taikang Tongji Hospital (Wuhan, China) were included. Clinical features showing significant differences between the severe and nonsevere groups were screened out by univariate analysis. Then, these features were used to generate classifier models to predict whether a COVID-19 case would be severe or nonsevere based on machine learning. Two test sets of data from the two hospitals were gathered to evaluate the predictive performance of the models. RESULTS: A total of 455 patients were included, and 21 features showing significant differences between the severe and nonsevere groups were selected for the training and validation set. The optimal subset, with eleven features in the k-nearest neighbor model, obtained the highest area under the curve (AUC) value among the four models in the validation set. D-dimer, CRP, and age were the three most important features in the optimal-feature subsets. The highest AUC value was obtained using a support vector-machine model for a test set from Huoshenshan Hospital. Software for predicting disease progression based on machine learning was developed. CONCLUSION: The predictive models were successfully established based on machine learning, and achieved satisfactory predictive performance of disease progression with optimal-feature subsets.