Dataset Information

Evaluation of Bayesian classifiers in asthma exacerbation prediction after medication discontinuation.

ABSTRACT: The achievement of the optimal control of the disease is of cardinal importance in asthma treatment. As the control of the disease is sustained the medication should be gradually reduced and then stopped. Nevertheless, the discontinuation of asthma medication may lead to loss of disease control and eventually to an exacerbation of the disease. The goal of this paper is to examine the performance of Bayesian network classifiers in predicting asthma exacerbation based on several patient's parameters such as objective measurements and medical history data.In this study several Bayesian network classifiers are presented and evaluated. It is shown that the proposed semi-naive network classifier with the use of Backward Sequential Elimination and Joining algorithm is able to predict if a patient will have an exacerbation of the disease after his last assessment with 93.84% accuracy and 90.9% sensitivity. In addition, the resulting structure and the conditional probability tables give a clear view of the probabilistic relationships between the used factors. This network may help the clinicians to identify the patients who are at high risk of having an exacerbation after stopping the medication and to confirm which factors are the most important.

SUBMITTER: Spyroglou II

PROVIDER: S-EPMC6069881 | biostudies-other | 2018 Jul

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Evaluation of Bayesian classifiers in asthma exacerbation prediction after medication discontinuation.

Spyroglou Ioannis I II Spöck Gunter G Rigas Alexandros G AG Paraskakis E N EN

BMC research notes 20180731 1

<h4>Objective</h4>The achievement of the optimal control of the disease is of cardinal importance in asthma treatment. As the control of the disease is sustained the medication should be gradually reduced and then stopped. Nevertheless, the discontinuation of asthma medication may lead to loss of disease control and eventually to an exacerbation of the disease. The goal of this paper is to examine the performance of Bayesian network classifiers in predicting asthma exacerbation based on several ...[more]

PMID: 30064478

Similar Datasets

Project description:BackgroundImproving accurate risk assessment of asthma exacerbations, and reduction via relevant behaviour change among people with asthma could save lives and reduce health care costs. We developed a simple personalised risk prediction model for asthma exacerbations using factors collected in routine healthcare data for use in a risk modelling feature for automated conversational systems.MethodsWe used pseudonymised primary care electronic healthcare records from the Clinical Practice Research Datalink (CPRD) Aurum database in England. We combined variables for prediction of asthma exacerbations using logistic regression including age, gender, ethnicity, Index of Multiple Deprivation, geographical region and clinical variables related to asthma events.ResultsWe included 1,203,741 patients divided into three cohorts to implement temporal validation: 898,763 (74.7%) in the training sample, 226,754 (18.8%) in the testing sample and 78,224 (6.5%) in the validation sample. The Area under the ROC curve (AUC) for the full model was 0.72 and for the restricted model was 0.71. Using a cut-off point of 0.1, approximately 27 asthma reviews by clinicians per 100 patients would be prevented compared with a strategy that all patients are regarded as high risk. Compared with patients without an exacerbation, patients who exacerbated were older, more likely to be female, prescribed more SABA and ICS in the preceding 12 months, have history of GORD, COPD, anxiety, depression, live in very deprived areas and have more severe disease.ConclusionUsing information available from routinely collected electronic healthcare record data, we developed a model that has moderate ability to separate patients who had an asthma exacerbation within 3 months from their index date from patients who did not. When comparing this model with a simplified model with variables that can easily be self-reported through a WhatsApp chatbot, we have shown that the predictive performance of the model is not substantially different.

Project description:BackgroundAlthough cholesterol-lowering medications can reduce the risk of recurrent cardiovascular events, premature discontinuation limits effectiveness. Discontinuation rates have not been systematically reported for lipid-lowering trials.Methods and resultsWe evaluated medication discontinuation in IMPROVE-IT (Improved Reduction of Outcomes: Vytorin Efficacy International Trial), which evaluated placebo+simvastatin versus ezetimibe+simvastatin in patients hospitalized with the acute coronary syndrome and followed longitudinally postdischarge. Reasons for discontinuation were evaluated from randomization through study end (median 71.9 [interquartile range 51.8-85.8] months). Kaplan-Meier (KM) discontinuation rates were evaluated at 30 days, 1 year, and through year 7, and compared by treatment arm and region, with Cox proportional hazards modeling used to evaluate predictors of discontinuation. Overall, 46.7% of subjects discontinued study medication (KM rate by study end 50.9% [95% CI, 50.1%-51.7%]). The risk of discontinuation was highest early in the trial but decreased with increasing time, with a terminal KM rate per 100 person-years of 8.4 (8.2-8.6) from years 1 to 7. Discontinuation was higher in the placebo+simvastatin versus ezetimibe+simvastatin arm (KM rate 52.0% versus 49.8%, P=0.049) and was highest in the United States (7-year KM rate 57.4%). In multivariable modeling, smoking, prior revascularization, hypertension, unstable angina, female sex, nonwhite race, and US location were associated with higher discontinuation rates.ConclusionsAlthough discontinuation was highest early and stabilized to 8% per year, because of prolonged follow-up, most discontinuation occurred after year 1. Adding ezetimibe to statin therapy did not increase discontinuation risk. Geographic differences and patient-level factors should be considered in trial design and analysis.Clinical trial registrationURL: https://www.clinicaltrials.gov . Unique identifier: NCT00202878.

Dataset Information

Evaluation of Bayesian classifiers in asthma exacerbation prediction after medication discontinuation.

Publications

Evaluation of Bayesian classifiers in asthma exacerbation prediction after medication discontinuation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets