A NOVEL SOFTWARE ENGINEERING APPROACH TOWARD USING MACHINE LEARNING FOR IMPROVING THE EFFICIENCY OF HEALTH SYSTEMS

Abstract

This study examines how software engineering and machine learning interact in the context of health systems. We proposed the software framework and methodology as a fresh framework for health informatics. Health informatics engineering for machine learning (SEMLHI). The SEMLHI framework consists of four modules (software, machine learning, machine learning algorithms, and health informatics data), which group the tasks in the framework according to the SEMLHI methodology. This enables researchers and developers to examine health informatics software from an engineering standpoint and gives developers a new road map for creating health applications with system functions and software implementations. In order to comprehend both the function of objects linked with the system and the machine learning techniques that must be used on the dataset, users can study and analyze user demands with the help of our new technique, which sheds light on its qualities. Real data from a hospital run by the Palestinian Authority during the last three years make up our dataset for this study. The SEMLHI technique is broken down into seven phases: creating, managing, defining, and implementing procedures; gathering data; ensuring security and privacy; testing and evaluating performance; and delivering software applications.