Abstract-We study a novel solution to executing aggregation (and specifically COUNT) queries over large-scale data. The proposed solution is generally applicable, in the sense that it can be deployed in environments in which data owners may or may not restrict access to their data and allow only 'aggregation operators' to be executed over their data. For this, it is based on predictive analytics, driven by queries and their results. We propose a machine learning (ML) framework for the task (which can be adapted for different aggregates as well). We focus on the widely used set-cardinality (i.e., COUNT) aggregation operator, as it is a fundamental operator for both internal data system optimisations and for aggregation-query analytics. We contribute a novel, query-driven ML model whose goals are to: (i) learn the query space (access patterns), (ii) associate (complex) aggregation queries with the cardinality of their results, (iii) define query similarity and use it to predict the cardinality of the answer set of an ad-hoc incoming query. Our ML model incorporates incremental learning algorithms for ensuring high prediction accuracy even when both the querying patterns and the underlying data change. The significance of contribution lies in that it (i) is the only query-driven solution applicable over general environments which include restrictedaccess data, (ii) offers incremental learning adjusted for arriving ad-hoc queries, which is well suited for big data analytics, and (iii) offers a performance (in terms of prediction accuracy and time, and memory requirements) that is superior to datacentric approaches. We provide a comprehensive performance evaluation of our model, evaluating its sensitivity and comparative advantages versus acclaimed data-centric methods (self-tuning histograms, sampling, and multidimensional histograms).

Aim To compare weight change in a lifestyle-based weight management programme between participants taking weight-gaining, weight-neutral/loss and mixed diabetes medications.Methods Electronic health records for individuals (≥ 18 years) with Type 2 diabetes who had been referred to a nonsurgical weight management programme between February 2008 and May 2014 were studied. Diabetes medications were classified into three categories based on their effect on body weight. In this intervention cohort study, weight change was calculated for participants attending two or more sessions.Results All 998 individuals who took oral diabetes medications and attended two or more sessions of weight management were included. Some 59.5% of participants were women, and participants had a mean BMI of 41.1 kg/m 2 (women) and 40.2 kg/m 2 (men). Of the diabetes medication combinations prescribed, 46.0% were weight-neutral/loss, 41.3% mixed and 12.7% weight-gaining. The mean weight change for participants on weight-gaining and weightneutral/loss diabetes medications respectively was À2.5 kg [95% confidence interval (CI) À3.2 to À1.8) and À3.3 kg (95% CI À3.8 to À2.9) (P = 0.05) for those attending two or more sessions (n = 998). Compared with those prescribed weight-neutral medications, participants prescribed weight-gaining medication lost 0.86 kg less (95% CI 0.02 to 1.7; P = 0.045) in a model adjusted for age, sex, BMI and socio-economic status.Conclusions Participants on weight-neutral/loss diabetes medications had a greater absolute weight loss within a weight management intervention compared with those on weight-gaining medications. Diabetes medications should be reviewed ahead of planned weight-loss interventions to help ensure maximal effectiveness of the intervention.