Predictors of sinus rhythm after electrical cardioversion of atrial fibrillation: results from a data mining project on the Flec-SL trial data set

Aims

Data mining is the computational process to obtain information from a data set and transform it for further use. Herein, through data mining with supportive statistical analyses, we identified and consolidated variables of the Flecainide Short-Long (Flec-SL-AFNET 3) trial dataset that are associated with the primary outcome of the trial, recurrence of persistent atrial fibrillation (AF) or death.

Methods and results

The 'Ranking Instances by Maximizing the Area under the ROC Curve' (RIMARC) algorithm was applied to build a classifier that can predict the primary outcome by using variables in the Flec-SL dataset. The primary outcome was time to persistent AF or death. The RIMARC algorithm calculated the predictive weights of each variable in the Flec-SL dataset for the primary outcome. Among the initial 21 parameters, 6 variables were identified by the RIMARC algorithm. In univariate Cox regression analysis of these variables, increased heart rate during AF and successful pharmacological conversion (PC) to sinus rhythm (SR) were found to be significant predictors. Multivariate Cox regression analysis revealed successful PC as the single relevant predictor of SR maintenance. The primary outcome risk was 3.14 times (95% CI:1.7-5.81) lower in those who had successful PC to SR than those who needed electrical cardioversion.

Conclusions

Pharmacological conversion of persistent AF with flecainide without the need for electrical cardioversion is a powerful and independent predictor of maintenance of SR. A strategy of flecainide pretreatment for 48 h prior to planned electrical cardioversion may be a useful planning of a strategy of long-term rhythm control.

A prescription fraud detection model

Prescription fraud is a main problem that causes substantial monetary loss in health care systems. We aimed to develop a model for detecting cases of prescription fraud and test it on real world data from a large multi-center medical prescription database. Conventionally, prescription fraud detection is conducted on random samples by human experts. However, the samples might be misleading and manual detection is costly. We propose a novel distance based on data-mining approach for assessing the fraudulent risk of prescriptions regarding cross-features. Final tests have been conducted on adult cardiac surgery database. The results obtained from experiments reveal that the proposed model works considerably well with a true positive rate of 77.4% and a false positive rate of 6% for the fraudulent medical prescriptions. The proposed model has the potential advantages including on-line risk prediction for prescription fraud, off-line analysis of high-risk prescriptions by human experts, and self-learning ability by regular updates of the integrative data sets. We conclude that incorporating such a system in health authorities, social security agencies and insurance companies would improve efficiency of internal review to ensure compliance with the law, and radically decrease human-expert auditing costs.

Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals

A new classification algorithm, called VFI5 (for Voting Feature Intervals), is developed and applied to problem of differential diagnosis of erythemato-squamous diseases. The domain contains records of patients with known diagnosis. Given a training set of such records, the VFI5 classifier learns how to differentiate a new case in the domain. VFI5 represents a concept in the form of feature intervals on each feature dimension separately. classification in the VFI5 algorithm is based on a real-valued voting. Each feature equally participates in the voting process and the class that receives the maximum amount of votes is declared to be the predicted class. The performance of the VFI5 classifier is evaluated empirically in terms of classification accuracy and running time.