METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.
RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.
CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.
METHODS: This study used the MIT-BIH Normal Sinus Rhythm (nsrdb) and MIT-BIH Atrial Fibrillation (afdb) databases for healthy human (NSR) and atrial fibrillation patient (N and AF) ECG signals, respectively. The extraction of features was based on the dynamic system concept to determine the ω of the ECG signals. There were 35,031 samples used for classification.
RESULTS: There were significant differences between the N & NSR, N & AF, and NSR & AF groups as determined by the statistical t-test (p<0.0001). There was a linear separation at 0.4s(-1) for ω of both databases upon using the thresholding method. The feature ω for afdb and nsrdb falls within the high frequency (HF) and above the HF band, respectively. The feature classification between the nsrdb and afdb ECG signals was 96.53% accurate.
CONCLUSIONS: This study found that features of the ω of atrial fibrillation patients and healthy humans were associated with the frequency analysis of the ANS during parasympathetic activity. The feature ω is significant for different databases, and the classification between afdb and nsrdb was determined.
METHODS: Data on allopurinol ADR reports (2000-2018) were extracted from the Malaysian ADR database. We identified RMMs implemented between 2000 and 2018 from the minutes of relevant meetings and the national pharmacovigilance newsletter. We obtained allopurinol utilization data (2004-2018) from the Pharmaceutical Services Programme. To determine the impact of RMMs on ADR reporting, we considered ADR reports received within 1 year of RMM implementation. We used the Pearson χ2 test to examine the relation between the implementation of RMMs and allopurinol ADR reports.
RESULTS: The 16 RMMs for allopurinol-related SCARs implemented in Malaysia involved nine risk communications, four prescriber or patient educational material, and three health system innovations. Allopurinol utilization decreased by 21.5% from 2004 to 2018. ADR reporting rates for all drugs (n = 144 507) and allopurinol (n = 1747) increased. ADR reports involving off-label use decreased by 6% from 2011. SCARs cases remained between 20% and 50%. RMMs implemented showed statistically significant reduction in ADR reports involving off-label use for August 2014 [χ2(1, N = 258) = 5.32, P = .021] and October 2016 [χ2(1, N = 349) = 3.85, P = .0499].
CONCLUSIONS: RMMs to promote the appropriate use of allopurinol and prescriber education have a positive impact. We need further measures to reduce the incidence and severity of allopurinol-induced SCARs, such as patient education and more research into pharmacogenetic screening.