This paper develops a multiple state model to project the number of people with disabilities in the United Kingdom over the next 35 years, thereby identifying implications for demand for long-term care for the elderly in the future.The model requires three types of data: prevalence rate data, transition rate data and trends data. Recent trends in healthy life expectancy data are used to frame the assumptions made regarding changes in the disability rates of the U.K. population in the future.Although there will be a large increase in the number of elderly people in the U.K. over the next 35 years, the projections suggest that the implications for the number of elderly people requiring long-term care could be ameliorated by a reduction in the proportion of older people who are severely disabled.

No abstract

We also thank the communities and health departments that invited the EpiPOD development team to observe seasonal vaccination clinics in action. These observations gave the team a great appreciation for the variability in the ways clinics can be managed successfully.

No abstract

INTRODUCTION AND OBJECTIVE: To enable earlier preventative interventions or guide empiric therapy for kidney stone disease, our objective was to demonstrate feasibility of predicting 24-hour urine abnormalities using several machine learning methods.METHODS: We trained machine learning models (XGBoost [XG] and Ensemble [EN]) to predict 24-hour urine abnormalities from electronic health record-derived demographic, laboratory, stone composition, and comorbidity data, including age, BMI, comorbidities (n[1,296). The machine learning models were compared to a logistic regression model [LR]. Models predicted binary (normal vs high) 24hour urine values for sodium, oxalate, calcium, and uric acid; and (normal vs low) for citrate; as well as a multiclass prediction of pH (low, normal, high). We evaluated performance using area under the receiver operating curve (ROC-AUC) and accuracy and identified predictors for each task.RESULTS: Both XG and EN were able to discriminate 24-hour urine abnormalities with fair performance, with comparable performance to LR (see Figure ). EN most accurately predicted abnormalities of oxalate (accuracy[65%, ROC-AUC[0.70) and citrate (65%, 0.69), while XG most accurately predicted abnormalities of uric acid (69%, 0.73) and sodium (71%, 0.70). Both models had similar accuracy for the prediction of pH (45%, 0.57) and calcium (55%, 0.59) abnormalities. Body mass index, age, and gender were the three most important features for training the models for all outcomes.CONCLUSIONS: Urine chemistry prediction for kidney stone disease appears to be feasible with machine learning methods with acceptable discrimination for several urinary parameters modifiable with diet. Further optimization of the performance could facilitate earlier pharmacologic preventative therapy.