Search

Background: Acute kidney injury (AKI) after coronary artery bypass grafting (CABG) surgery is associated with poor outcomes. The objective of this study was to apply a new machine learning (ML) method to establish prediction models of AKI after CABG. Methods: A total of 2,780 patients from two medical centers in East China who underwent primary isolated CABG were enrolled. The dataset was randomly divided for model training (80%) and model testing (20%). Four ML models based on LightGBM, Support vector machine (SVM), Softmax and random forest (RF) algorithms respectively were established in Python. A total of 2,051 patients from two other medical centers were assigned to an external validation group to verify the performances of the ML prediction models. The models were evaluated using the area under the receiver operating characteristics curve (AUC), Hosmer-Lemeshow goodness-of-fit statistic, Bland-Altman plots, and decision curve analysis. The outcome of the LightGBM model was interpreted using SHapley Additive exPlanations (SHAP). Results: The incidence of postoperative AKI in the modeling group was 13.4%. Similarly, the incidence of postoperative AKI of the two medical centers in the external validation group was 8.2% and 13.6% respectively. LightGBM performed the best in predicting, with an AUC of 0.8027 in internal validation group and 0.8798 and 0.7801 in the external validation group. The SHAP revealed the top 20 predictors of postoperative AKI ranked according to the importance, and the top three features on prediction were the serum creatinine in the first 24 h after operation, the last preoperative Scr level, and body surface area. Conclusion: This study provides a LightGBM predictive model that can make accurate predictions for AKI after CABG surgery. The LightGBM model shows good predictive ability in both internal and external validation. It can help cardiac surgeons identify high-risk patients who may experience AKI after CABG surgery. [ABSTRACT FROM AUTHOR]

Background: Crohn's disease (CD) is a chronic disease that may have an adverse impact on health-related quality of life (HRQoL). This study aimed to describe the HRQoL of CD patients and assess correlating factors using the EQ-5D-5L in China.Methods: We recruited CD patients at Shanghai Renji Hospital from October 2018 to May 2019. The data collected included demographic and clinical information, medical expenditures, and EQ-5D-5L questionnaire responses. The chi-square test or Fisher's exact test was applied to analyse the proportion of patients in subgroups at each level. After the selection of correlating variables by univariate analysis, multivariate regression analyses were used to explore the correlating factors of HRQoL in CD patients.Results: A total of 202 CD inpatients with a mean disease duration of 3.3 years were enrolled in the study. A total of 71.8% of patients were males, and 49.5% of patients were aged between 30 and 49 years. The average EQ-5D-5L utility score was 0.85, with a standard deviation (SD) of 0.12. Males, ileum lesions, remission status, and lower expenditure predicted higher EQ-5D-5L scores. In each EQ-5D-5L dimension, the proportion of patients differed significantly by gender, disease activity and location subgroup. In the multivariate regression models, being in an active CD state and using antibiotics had significantly adverse impacts on HRQoL (p < 0.05).Conclusions: CD may have a significant negative impact on HRQoL in Chinese CD patients. Being in an active phase of the disease and using antibiotics were identified as affecting HRQoL. [ABSTRACT FROM AUTHOR]

Background: China launched the National Malaria Elimination Programme (NMEP) in 2010 and set the goal that all health facilities should be able to diagnose malaria. Additionally, hospitals at all levels could treat malaria by 2015. To provide a reference for the control of imported malaria, a study was conducted on the distribution of malaria patients seeking care in different types of health facilities. Methods: There were two data sources. One was obtained through the Infectious Diseases Information Reporting Management System (IDIRMS), which only contained the name of health facilities and the number of cases. The other was obtained through multistage stratified cluster sampling. Descriptive statistical analysis was used to investigate the distribution of malaria patients attending different types of health facilities (hospitals, township hospitals, and Centers for Disease Control and Prevention), hospital tiers (county-level, prefecture-level, and provincial-level), and hospital levels (primary, secondary, and tertiary). Chi-square test was also used to compare the proportions of patients seeking care outside their current residence region between different types of hospitals. Point maps were drawn to visualize the spatial distribution of hospitals reporting malaria cases, and flow maps were created to show the spatial flow of malaria patients by using the ArcGIS software. Results: The proportions of malaria patients who sought care in hospitals, township hospitals, and Centers for Disease Control and Prevention were 81.7%, 14.7%, and 3.6%, respectively. For those who sought care in hospitals, the percentages of patients who sought care in provincial-level, prefecture-level and county-level hospitals were 17.4%, 60.5% and 22.1%, correspondingly; the proportions of patients who sought care in tertiary hospitals, secondary hospitals, and primary hospitals were 59.8%, 39.9%, and 0.3%, respectively. Moreover, the proportions of patients seeking care in hospitals within county and prefectural administrative areas were 18.2%, 63.4%, respectively. Conclusion: During the implementation of NMEP, malaria patients tended to seek care in tertiary hospitals and prefecture-level hospitals, and more than half of patients could be treated in hospitals in prefecture-level areas. In the current phase, it is necessary to establish referral system from county-level hospitals to higher-level hospitals for malaria treatment. [ABSTRACT FROM AUTHOR]

Background: Insufficient nutrition intake has negatively influenced the health of the elderly in rural China where the problem of population aging is serious. The present study aims to explore whether the medical system, called the New Rural Cooperative Medical System (NRCMS), can improve the rural elderly's nutrition intake and the mechanism behind it.Methods: The difference in differences (DID) model and the propensity score matching-difference in differences (PSM-DID) model are both performed to investigate the impact of the medical system on nutrition improvement for the rural elderly. Two thousand seven hundred eighty rural elderly samples tracked in 2000 and 2006 from the China Health and Nutrition Survey are analyzed. Indices for the elderly's nutrition intake includes daily average intake of energy, fat, protein, and carbohydrate.Results: The results show that participation in the NRCMS can significantly increase the rural elderly's total energy intake, carbohydrate intake, and protein intake by 206.688 kcal, 36.379 g, and 6.979 g, respectively. A more significant impact of the NRCMS on nutrition intake is observed in the central and near-western where economic development is lagging behind. Also, compared to people of 18-60 age group, such impact is statistically more significant in the elderly for the carbohydrate intake.Conclusions: The NRCMS can improve the rural elderly's nutrition intake in China. As the population ages rapidly in rural China, the present study provides recommendations on how to improve nutrition and health status of the elderly from the aspect of the medical system. [ABSTRACT FROM AUTHOR]

Background: Crohn's disease (CD) is a chronic disease that may have an adverse impact on health-related quality of life (HRQoL). This study aimed to describe the HRQoL of CD patients and assess correlating factors using the EQ-5D-5L in China., Methods: We recruited CD patients at Shanghai Renji Hospital from October 2018 to May 2019. The data collected included demographic and clinical information, medical expenditures, and EQ-5D-5L questionnaire responses. The chi-square test or Fisher's exact test was applied to analyse the proportion of patients in subgroups at each level. After the selection of correlating variables by univariate analysis, multivariate regression analyses were used to explore the correlating factors of HRQoL in CD patients., Results: A total of 202 CD inpatients with a mean disease duration of 3.3 years were enrolled in the study. A total of 71.8% of patients were males, and 49.5% of patients were aged between 30 and 49 years. The average EQ-5D-5L utility score was 0.85, with a standard deviation (SD) of 0.12. Males, ileum lesions, remission status, and lower expenditure predicted higher EQ-5D-5L scores. In each EQ-5D-5L dimension, the proportion of patients differed significantly by gender, disease activity and location subgroup. In the multivariate regression models, being in an active CD state and using antibiotics had significantly adverse impacts on HRQoL (p < 0.05)., Conclusions: CD may have a significant negative impact on HRQoL in Chinese CD patients. Being in an active phase of the disease and using antibiotics were identified as affecting HRQoL., (© 2022. The Author(s).)