APPLICATION OF MACHINE LEARNING IN DATA ANALYSIS IN HOSPITALS FOR DECISION MAKING: A SYSTEMATIC LITERATURE REVIEW
APPLICATION OF MACHINE LEARNING IN DATA ANALYSIS IN HOSPITALS FOR DECISION MAKING: A SYSTEMATIC LITERATURE REVIEW
Bundi D - School of Science and Technology, Department of Computing, United States International University Africa, Kenya
ABSTRACT
There are several ways to learn from data using machine learning, which is a wide word. Using these technologies, big real-world datasets might be quickly converted into apps that help patients and healthcare providers make better decisions. Patient-provider-level decision-making was intended to be informed by published observational studies on the use of machine learning. Two reviewers independently assessed papers that met the qualifying criteria after implementing the search technique. Different statistical programs and procedures were employed in the selected investigations. A decision tree and a random forest were the two most frequent techniques. Less than 1% of the research used external validation, while the majority used internal validation. Only eight research used more than one machine learning method to analyze the data. In the application of machine learning techniques to patient-provider decision making, a broad range of methodologies, algorithms, statistical software, and validation procedures were used. Multiple machine learning methodologies must be employed, the model selection process must be clearly specified, and both internal and external validation is required to guarantee that choices for patient care are based on the most accurate evidence possible.
