| dc.description.abstract | Artificial intelligence (AI), which is already being used in healthcare, has brought a paradigm shift to the field. Owing to the growing availability of healthcare data, there has been rapid advancement in the use of analytical tools in the sector. To improve emergency response in healthcare, the study developed an optimized AI model. Healthcare emergency management is sometimes believed to mean solely the tasks involved in responding to an emergency. However, in a broader sense, it refers to the actual planning of emergencies and includes a wide range of activities. Notably these entail business continuity management and planning, up-front training and preparedness, as well as the response to, and recovery from, any likely disaster that arises from issues arising in emergency situations. Despite well-implemented prevention efforts, many acute health issues continue to occur. The lack of adequate resources in healthcare emergency management; the chaotic administration of resources used in handling emergency situations; getting to the nearest health facility as a critical point of concern; and not having enough ambulances to serve the large population, making it difficult to transport patients in need of emergency management care are some of the challenges encountered. Many people in the society are left to their fate and the whims of public opinion when it comes to their unique demands during emergency situations. Clearly, having a thorough understanding of the facilities in close proximity is a major difficulty. Since there is a lack of awareness of the health facility mapping, it is difficult to get to them in a timely manner. Models used in emergency case response for healthcare haven't been able to achieve statistically meaningful reductions in mortality rates due to inadequate medical emergency case management. The objective of this study, therefore, was to improve the efficiency of medical emergency case response in developing countries using an artificial intelligence-based model. Specifically, the study identified challenges with existing disaster response models and narrowed on areas of significant intervention, developed a model addressing those significant areas and finally validated the model. R programming with R studio platform was used for model development and simulation. Key findings of the study included that the developed model is able to select the most appropriate health facility (precision) and an optimal route to the facility (time optimization). It is recommended that this model be adopted to optimize the selection of an appropriate facility for timely response. This reduces mortality rates during emergency responses. | en_US |