EXPLAINABILITY OF NEURAL NETWORK CLUSTERING IN INTERPRETING THE COVID-19 EMERGENCY DATA

Among other hospitalization causes and cases, the clinical emergency is a critical case data of reporting patients are biased as well poorly managed due to chaotic situation. The world has faced chaos over past year frequent waves COVID-19 resulting emergencies. banks, linked with emergencies require serious quantitative qualitative analysis drive interpretable conclusions for necessary future measures develop explainable artificial intelligence tools. This important procedure involves clear understanding patterns topologies, which great challenge multidimensional sets. Mathematically, topological mapping can resolve this problem by higher-dimensional two-dimensional representation, based on overall association. Proper mining pattern recognition help in improving rapid admission, providing medical resources timely proper patient administration. In paper, importance self-organizing maps, interpret hospital data, particularly epidemic discussed detail. Important variables identified aid networks mappings.