Developing a short-term prediction model for asthma exacerbations from Swedish primary care patients' data using machine learning - Based on the ARCTIC study.

OBJECTIVE: The ability to predict impending asthma exacerbations may allow better utilization of healthcare resources, prevention of hospitalization and improve patient outcomes. We aimed to develop models using machine learning to predict risk of exacerbations. METHODS: Data from 29,396 asthma patients was collected from electronic medical records and national registers covering clinical and epidemiological factors (e.g. comorbidities, health care contacts), between 2000 and 2013. Machine-learning classifiers were used to create models to predict exacerbations within the next 15 days. Model selection was done using the mean cross validation score of area under precision-recall curve (AUPRC). RESULTS: The most important predictors of exacerbation were comorbidity burden and previous exacerbations. Model validation on test data yielded an AUPRC = 0.007 (95% CI: ± 0.0002), indicating that historic clinical information alone may not be sufficient to predict a near future risk of asthma exacerbation. CONCLUSIONS: Supplementation with additional data on environmental triggers, (e.g. weather, pollen count, air quality) and from wearables, might be necessary to improve performance of the short-term predictive model to develop a more clinically useful tool.

Early discontinuation of attention-deficit/hyperactivity disorder drug treatment: a Danish nationwide drug utilization study.

Knowledge of patterns of treatment discontinuation in attention-deficit/hyperactivity disorder (ADHD) drug treatment is of importance, for both the clinical practice and the study of long-term treatment outcomes. The purpose of this study was to describe early discontinuation of ADHD drug treatment. Using the Danish National Prescription Registry, all first-time users of the ADHD drugs methylphenidate and atomoxetine were identified between 2000 and 2012. Early discontinuation was defined as failing to fill a second prescription for any ADHD drug within 6 months. Analyses were conducted stratified by calendar year, drug formulation, patient sex, age and region of residence. 59,116 first-time users of methylphenidate and atomoxetine with at least 6 months of eligible follow-up were identified. Overall, 12.6% (n = 7441) failed to fill a second prescription within 6 months. This proportion changed over time, dropping from 20.8% in 2000 to 12.5% in 2012. The proportion of early discontinuation was considerably lower among children than among adults. Proportions were comparable when stratifying by index drug. Proportions of early discontinuation were similar between regions of Denmark, except in the capital region, where it remained at around 20% among 18- to 49-year-olds throughout the study period (22.6% in 2012). In conclusion, we found that the proportion of early discontinuation among ADHD drug users in Denmark dropped markedly during the past decade for both sexes, all age groups and all regions, except for adults in the capital region. Overall, early discontinuation was somewhat lower than expected, considering rates of side effects or non-response to ADHD drug treatment.

Use of exenatide and liraglutide in Denmark: a drug utilization study.

PURPOSE: The purpose of this study was to characterise the utilization of the glucagon-like peptide-1 (GLP-1) analogues exenatide and liraglutide in Denmark. METHODS: From the Danish National Prescription Registry, we extracted all prescriptions for either liraglutide or exenatide twice-daily in the period 1 April 2007 to 31 December 2012. Using descriptive statistics, we calculated incidence rates, prevalence proportions, daily consumption, and concomitant drug use. For a subset of users we included data from other registries and characterised the baseline characteristics of incident users of GLP-1 analogues. RESULTS: We identified 21,561 and 2,354 users of liraglutide and exenatide respectively. From market entry in 2009 liraglutide showed an increasing prevalence reaching 2.4 per thousand inhabitants in 2012. Exenatide ranged between 0.01 and 0.25 per thousand inhabitants from 2007 to 2012. Treatment intensity showed geographical variation ranging from 1.84per thousand inhabitants to 3.22 per thousand inhabitants for liraglutide. Average doses were 1.34 mg/day (liraglutide) and 16.4 µg/day (exenatide). Treatment initiation was most often performed by a hospital physician and was not associated with any changes in concomitant treatment with antihypertensives, cholesterol-lowering drugs or anticoagulants. Of liraglutide and exenatide users, 38 % and 43 % also used insulin. Low kidney function (eGFR < 30 ml/min) was found in 10.1 % and 9.0 % of users of liraglutide and exenatide respectively. CONCLUSIONS: The preferred GLP-1 analogue in Denmark is liraglutide. Certain aspects of the utilization of GLP-1 analogues, such as large regional differences and concomitant use of GLP-1 analogues and insulin, warrant further investigation.

The use of medication against attention deficit/hyperactivity disorder in Denmark: a drug use study from a patient perspective.

AIM: Our aim was to characterize utilization patterns for drugs used to treat attention deficit/hyperactivity disorder (ADHD) on the level of the individual patient among Danish users, focusing on treatment duration, doses used, and concurrent use of ADHD and non-ADHD drugs. METHODS: Using the Danish Registry of Medicinal Product Statistics, we extracted data on 1,085,099 prescriptions for ADHD drugs issued to a total of 54,024 persons in the study period 1 January 1995 to 30 September 2011. For users in the final year of the study period, we further extracted 315,365 prescriptions for non-ADHD drugs. Drug utilization was characterized using descriptive statistics. RESULTS: The mean duration of ADHD treatment was highest (3.6-4.2 years) for patients initiating therapy at a young age (age<13). Dropout rate after receiving only one prescription was highest among off-label users (age<6 and age >17). All age categories showed an increase in the average daily dosage of methylphenidate used from 2003 to 2010. Concomitant treatment with methylphenidate and atomoxetine was rare, as only 2 % of methylphenidate treatment overlapped with atomoxetine treatment. Nineteen percent of methylphenidate instant-release treatment overlapped with methylphenidate controlled-release treatment. Users of ADHD drugs across all age categories had an increased use of drugs related to the nervous system, especially antipsychotics [standardized morbidity rate (SMR), 6.4-19.5] and antiepileptics (SMR, 4.0-5.5). CONCLUSION: We found certain traits that warrant further investigation: the apparent increase in average daily doses, the low adherence to treatment among off-label users, and the increased use of other psychotropic medication.

The use of medication against attention deficit hyperactivity disorder in Denmark: a drug use study from a national perspective.

PURPOSE: The purpose of the study was to characterize the utilization of medication against attention deficit hyperactivity disorder (ADHD) in Denmark between 1995 and 2011 from a national perspective, by using population-based prescription data. METHODS: National data on drug use in Denmark between 1 January 1995 and 30 September 2011 were extracted from the Registry of Medicinal Product Statistics (RMPS). Drug utilization was characterized using descriptive statistics. RESULTS: A total of 1,085,090 prescriptions issued to 54,020 persons were identified. The incidence rate was stable in the last 3 years of the study period, and a slightly decreasing incidence rate and a stabilizing prevalence were observed towards the end of this period. The therapeutic intensity was 6.7 defined daily dose/person/day, with large regional differences that ranged from 64 to 145 % of the national average. Methylphenidate accounted for 92.6 % of DDDs used. The general practitioner (GP) rarely initiated treatment, although treatment initiation based on the GP's advice increased with older age of the patient. Maintenance treatment was found to be distributed roughly equally between prescriber types. For methylphenidate, 1 % of users accounted for 6.1 % of the drug volume and 50 % of users accounted for 84.4 %. The data therefore do not suggest a high proportion of heavy users. CONCLUSION: The findings of this analysis are mostly reassuring, with the data indicating a seemingly stagnant incidence and prevalence rate and lacking evidence of heavy users. However, the prescriber profile for incident users and the large regional variances raise concerns. It is therefore vital that the use of ADHD drugs is closely monitored.

The effect of occasional smoking on smoking-related cancers: in the European Prospective Investigation into Cancer and Nutrition (EPIC).

OBJECTIVE: Most studies on tobacco smoking have focused on daily-smokers. Occasional smokers, who have never smoked daily, have often been included in the reference group of never-smokers. We have investigated the association between occasional smoking and cancer of the bladder, kidney, pancreas, upper aero-digestive tract and lung. METHODS: The study population consisted of 158,488 persons, who provided information on occasional smoking, within the European Prospective Investigation into Cancer and Nutrition (EPIC), 780 of whom developed a smoking-related cancer. We used Cox proportional hazard model, stratified by gender and country to estimate incidence rate ratios (IRR) for smoking-related cancers. RESULTS: The results suggest that occasional smokers have a higher risk of bladder cancer (IRR: 1.92, 95% confidence interval (CI) 0.93-3.98) and of the major smoking-related cancers combined (IRR: 1.24, 95% CI 0.80-1.94) than true never-smokers. Including occasional smokers in the reference group resulted in a lower risk estimate for former and current smokers. CONCLUSIONS: Occasional smoking should be discouraged.

Tobacco smoke and bladder cancer--in the European Prospective Investigation into Cancer and Nutrition.

The purpose of the present study was to investigate the association between smoking and the development of bladder cancer. The study population consisted of 429,906 persons participating in the European Prospective Investigation into Cancer and Nutrition (EPIC), 633 of whom developed bladder cancer during the follow-up period. An increased risk of bladder cancer was found for both current- (incidence rate ratio 3.96, 95% confidence interval: 3.07-5.09) and ex- (2.25, 1.74-2.91) smokers, compared to never-smokers. A positive association with intensity (per 5 cigarettes) was found among current-smokers (1.18, 1.09-1.28). Associations (per 5 years) were observed for duration (1.14, 1.08-1.21), later age at start (0.75, 0.66-0.85) and longer time since quitting (0.92, 0.86-0.98). Exposure to environmental tobacco smoke (ETS) during childhood increased the risk of bladder cancer (1.38, 1.00-1.90), whereas for ETS exposure as adult no effect was detected. The present study confirms the strong association between smoking and bladder cancer. The indication of a higher risk of bladder cancer for those who start smoking at a young age and for those exposed to ETS during childhood adds to the body of evidence suggesting that children are more sensitive to carcinogens than adults.