Health data science最新文献

Background: Although loneliness and social isolation are proposed as important risk factors for metabolic diseases, their associations with the risk of non-alcoholic fatty liver disease (NAFLD) have not been elucidated. The aims of this study were to determine whether loneliness and social isolation are independently associated with the risk of NAFLD and to explore potential mediators for the observed associations. Methods: In this large prospective cohort analysis with 405,073 participants of the UK Biobank, the status of loneliness and social isolation was assessed through self-administrated questionnaires at study recruitment. The primary endpoint of interest was incident NAFLD. Multivariable-adjusted Cox proportional hazard regression models were used to calculate hazard ratios (HRs) and 95% confidence intervals for the associations between loneliness, social isolation, and risk of NAFLD. Results: During a median follow-up of 13.6 years, there were 5,570 cases of NAFLD identified. In the multivariable-adjusted model, loneliness and social isolation were both statistically significantly associated with an increased risk of NAFLD (HR = 1.22 and 1.13, respectively). No significant multiplicative or additive interaction was found between loneliness and social isolation on the risk of NAFLD. The mediation analysis estimated that 30.4%, 16.2%, 5.3%, 4.1%, 10.5%, and 33.2% of the loneliness-NAFLD association was mediated by unhealthy lifestyle score, obesity, current smoking, irregular physical activity, suboptimal sleep duration, and depression, respectively. On the other hand, 25.6%, 10.1%, 15.5%, 10.1%, 8.1%, 11.6%, 9.6%, 4.8%, and 3.0% of the social isolation-NAFLD association was mediated by unhealthy lifestyle score, obesity, current smoking, irregular physical activity, suboptimal sleep duration, depression, C-reactive protein, count of white blood cells, and count of neutrophils, respectively. Conclusions: Our study demonstrated that loneliness and social isolation were associated with an elevated risk of NAFLD, independent of other important risk factors. These associations were partially mediated by lifestyle, depression, and inflammatory factors. Our findings substantiate the importance of loneliness and social isolation in the development of NAFLD.

[This corrects the article DOI: 10.34133/hds.0099.].

Background: Machine learning models are not in routine use for predicting HIV status. Our objective is to describe the development of a machine learning model to predict HIV viral load (VL) hotspots as an early warning system in Kenya, based on routinely collected data by affiliate entities of the Ministry of Health. Based on World Health Organization's recommendations, hotspots are health facilities with ≥20% people living with HIV whose VL is not suppressed. Prediction of VL hotspots provides an early warning system to health administrators to optimize treatment and resources distribution.

Methods: A random forest model was built to predict the hotspot status of a health facility in the upcoming month, starting from 2016. Prior to model building, the datasets were cleaned and checked for outliers and multicollinearity at the patient level. The patient-level data were aggregated up to the facility level before model building. We analyzed data from 4 million tests and 4,265 facilities. The dataset at the health facility level was divided into train (75%) and test (25%) datasets.

Results: The model discriminates hotspots from non-hotspots with an accuracy of 78%. The F1 score of the model is 69% and the Brier score is 0.139. In December 2019, our model correctly predicted 434 VL hotspots in addition to the observed 446 VL hotspots.

Conclusion: The hotspot mapping model can be essential to antiretroviral therapy programs. This model can provide support to decision-makers to identify VL hotspots ahead in time using cost-efficient routinely collected data.