Disruption of hospital care during the first year of the COVID-19 pandemic impacted socioeconomic groups differently: population based study using routine registration data.

BACKGROUND: During the COVID-19 pandemic, provision of non-COVID healthcare was recurrently severely disrupted. The objective was to determine whether disruption of non-COVID hospital use, either due to cancelled, postponed, or forgone care, during the first pandemic year of COVID-19 impacted socioeconomic groups differently compared with pre-pandemic use. METHODS: National population registry data, individually linked with data of non-COVID hospital use in the Netherlands (2017-2020). in non-institutionalised population of 25-79 years, in standardised household income deciles (1 = low, 10 = high) as proxy for socioeconomic status. Generic outcome measures included patients who received hospital care (dichotomous): outpatient contact, day treatment, inpatient clinic, and surgery. Specific procedures were included as examples of frequently performed elective and acute procedures, e.g.: elective knee/hip replacement and cataract surgery, and acute percutaneous coronary interventions (PCI). Relative risks (RR) for hospital use were reported as outcomes from generalised linear regression models (binomial) with log-link. An interaction term was included to assess whether income differences in hospital use during the pandemic deviated from pre-pandemic use. RESULTS: Hospital use rates declined in 2020 across all income groups. With baseline (2019) higher hospital use rates among lower than higher income groups, relatively stronger declines were found for lower income groups. The lowest income groups experienced a 10% larger decline in surgery received than the highest income group (RR 0.90, 95% CI 0.87 - 0.93). Patterns were similar for inpatient clinic, elective knee/hip replacement and cataract surgery. We found small or no significant income differences for outpatient clinic, day treatment, and acute PCI. CONCLUSIONS: Disruption of non-COVID hospital use in 2020 was substantial across all income groups during the acute phases of the pandemic, but relatively stronger for lower income groups than could be expected compared with pre-pandemic hospital use. Although the pandemic's impact on the health system was unprecedented, healthcare service shortages are here to stay. It is therefore pivotal to realise that lower income groups may be at risk for underuse in times of scarcity.

A machine learning approach to small area estimation: predicting the health, housing and well-being of the population of Netherlands.

BACKGROUND: Local policymakers require information about public health, housing and well-being at small geographical areas. A municipality can for example use this information to organize targeted activities with the aim of improving the well-being of their residents. Surveys are often used to gather data, but many neighborhoods can have only few or even zero respondents. In that case, estimating the status of the local population directly from survey responses is prone to be unreliable. METHODS: Small Area Estimation (SAE) is a technique to provide estimates at small geographical levels with only few or even zero respondents. In classical individual-level SAE, a complex statistical regression model is fitted to the survey responses by using auxiliary administrative data for the population as predictors, the missing responses are then predicted and aggregated to the desired geographical level. In this paper we compare gradient boosted trees (XGBoost), a well-known machine learning technique, to a structured additive regression model (STAR) designed for the specific problem of estimating public health and well-being in the whole population of the Netherlands. RESULTS: We compare the accuracy and performance of these models using out-of-sample predictions with five-fold Cross Validation (5CV). We do this for three data sets of different sample sizes and outcome types. Compared to the STAR model, gradient boosted trees are able to improve both the accuracy of the predictions and the total time taken to get these predictions. Even though the models appear quite similar in overall accuracy, the small area predictions at neighborhood level sometimes differ significantly. It may therefore make sense to pursue slightly more accurate models for better predictions into small areas. However, one of the biggest benefits is that XGBoost does not require prior knowledge or model specification. Data preparation and modelling is much easier, since the method automatically handles missing data, non-linear responses, interactions and accounts for spatial correlation structures. CONCLUSIONS: In this paper we provide new nationwide estimates of health, housing and well-being indicators at neighborhood level in the Netherlands, see 'Online materials'. We demonstrate that machine learning provides a good alternative to complex statistical regression modelling for small area estimation in terms of accuracy, robustness, speed and data preparation. These results can be used to make appropriate policy decisions at a local level and make recommendations about which estimation methods are beneficial in terms of accuracy, time and budget constraints.

Using machine learning to predict blood culture outcomes in the emergency department: a single-centre, retrospective, observational study.

OBJECTIVES: To develop predictive models for blood culture (BC) outcomes in an emergency department (ED) setting. DESIGN: Retrospective observational study. SETTING: ED of a large teaching hospital in the Netherlands between 1 September 2018 and 24 June 2020. PARTICIPANTS: Adult patients from whom BCs were collected in the ED. Data of demographic information, vital signs, administered medications in the ED and laboratory and radiology results were extracted from the electronic health record, if available at the end of the ED visits. MAIN OUTCOME MEASURES: The primary outcome was the performance of two models (logistic regression and gradient boosted trees) to predict bacteraemia in ED patients, defined as at least one true positive BC collected at the ED. RESULTS: In 4885 out of 51 399 ED visits (9.5%), BCs were collected. In 598/4885 (12.2%) visits, at least one of the BCs was true positive. Both a gradient boosted tree model and a logistic regression model showed good performance in predicting BC results with area under curve of the receiver operating characteristics of 0.77 (95% CI 0.73 to 0.82) and 0.78 (95% CI 0.73 to 0.82) in the test sets, respectively. In the gradient boosted tree model, the optimal threshold would predict 69% of BCs in the test set to be negative, with a negative predictive value of over 94%. CONCLUSIONS: Both models can accurately identify patients with low risk of bacteraemia at the ED in this single-centre setting and may be useful to reduce unnecessary BCs and associated healthcare costs. Further studies are necessary for validation and to investigate the potential clinical benefits and possible risks after implementation.