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: To answer this demand, the Health Equity Assessment Toolkit (HEAT), was developed between 2014 and 2016. The software, which contains the World Health Organization's Health Equity Monitor database, allows the assessment of inequalities within a country using over 30 reproductive, maternal, newborn and child health indicators and five dimensions of inequality (economic status, education, place of residence, subnational region and child's sex, where applicable).
RESULTS/CONCLUSION: HEAT was beta-tested in 2015 as part of ongoing capacity building workshops on health inequality monitoring. This is the first and only application of its kind; further developments are proposed to introduce an upload data feature, translate it into different languages and increase interactivity of the software. This article will present the main features and functionalities of HEAT and discuss its relevance and use for health inequality monitoring.
RESEARCH DESIGN AND METHODS: All suspected ADEs associated with tocilizumab between April to August 2020 were analyzed based on COVID-19 patients' demographic and clinical variables, and severity of involvement of organ system.
RESULTS: A total of 1005 ADEs were reported among 513 recipients. The majority of the ADEs (46.26%) were reported from 18-64 years, were males and reported spontaneously. Around 80%, 20%, and 64% were serious, fatal, and administered intravenously, respectively. 'Injury, Poisoning, and Procedural Complications' remain as highest (35%) among categorized ADEs. Neutropenia, hypofibrinogenemia were common hematological ADEs. The above 64 years was found to have significantly lower odds than of below 45 years. In comparison, those in the European Region have substantially higher odds compared to the Region of Americas.
CONCLUSION: Neutropenia, superinfections, reactivation of latent infections, hepatitis, and cardiac abnormalities were common ADEs observed that necessitate proper monitoring and reporting.