RESUMO
BACKGROUND: Drug safety relies on advanced methods for timely and accurate prediction of side effects. To tackle this requirement, this scoping review examines machine-learning approaches for predicting drug-related side effects with a particular focus on chemical, biological, and phenotypical features. METHODS: This was a scoping review in which a comprehensive search was conducted in various databases from 1 January 2013 to 31 December 2023. RESULTS: The results showed the widespread use of Random Forest, k-nearest neighbor, and support vector machine algorithms. Ensemble methods, particularly random forest, emphasized the significance of integrating chemical and biological features in predicting drug-related side effects. CONCLUSIONS: This review article emphasized the significance of considering a variety of features, datasets, and machine learning algorithms for predicting drug-related side effects. Ensemble methods and Random Forest showed the best performance and combining chemical and biological features improved prediction. The results suggested that machine learning techniques have some potential to improve drug development and trials. Future work should focus on specific feature types, selection techniques, and graph-based methods for even better prediction.
RESUMO
BACKGROUND: Congenital heart disease (CHD) is one of the leading causes of death. Safe and timely medical interventions, especially in children, can prolong their survival. The drugs prescribed for children with CHD are mainly based on the outcomes of drug therapy in adults with cardiovascular diseases, and their adverse drug reactions (ADRs) might be different. Therefore, the aim of this study was to investigate ADRs in children with CHD. METHODS: This was a scoping review conducted in 2023. PubMed, Web of Science, Scopus, the Cochrane Library, Ovid, ProQuest, and Google Scholar databases were searched. All studies that reported ADRs for children with CHD and were published in English by 1 November 2023 were included in this study. Finally, the results were reported using a content analysis method. RESULTS: A total of 87 articles were included in the study. The results showed that symptoms/signs/clinical findings, and cardiovascular disorders were the most common ADRs reported in children with CHD. The results also showed that most of the ADRs were reported for prostaglandin E1, amiodarone, prostaglandin E2, dexmedetomidine, and captopril, respectively. CONCLUSION: The review underscores the wide array of ADRs in children with CHD, particularly in antiarrhythmics, diuretics, beta-blockers, anticoagulants, and vasodilators, which affected cardiovascular, respiratory, endocrine, metabolic, genitourinary, gastrointestinal, and musculoskeletal systems. Tailored treatment is imperative, considering individual patient characteristics, especially in the vulnerable groups. Further research is essential for optimizing dosing, pharmacogenetics, and alternative therapies to enhance patient outcomes in CHD management.