WEB BASED MEDICAL CONSULTING INFORMATION FLOW FOR HOSPITAL OUT-PATIENTS USING MACHINE LEARNING TECHNIQUES

Abstract

Medical consulting today is characterized by numerous demanding tasks that are prone to illness and need to be efficiently managed by medical practitioners using emerging techniques and solutions. Although there are concerted efforts by both the doctors and other medical stakeholders aimed at improving the condition, human errors abound. Sequel to this, the level of management bottlenecks recorded in the hospitals on a daily basis abound, such as the unordered information flow in the outpatients department (OPD); thus, effective health service delivery is being stifled. In this regard, the application of natural language-based medical consulting information flow cannot be undermined. This work seeks to develop a natural language-based medical consulting information flow for hospital outpatients using machine learning techniques. The architecture of the system was modeled using universal modeling language (UML) tools. The medical information flow is processed using machine learning techniques (MLT), which are named Word Rank. The word rank positions and sorts all sentences accordingly in an input corpus of a patient case report and is presented in a summarized version of the word. So, the word-rank algorithm generates a summary of the patient’s record based on the input corpus. The implemented system can be deployed in the Nigerian Electronic Health Records (NEHR) used in hospitals to ensure efficient information flow for patients in the outpatient department of every hospital. The system would therefore reduce the effort expended by the medical practitioners in comprehending a case report and offering various medical services since it would be very easy to view the salient parts promptly, resulting in a reasonably smooth information flow, an easier consultation process, and a reduction in patient waiting time. Cosine similarity Identify the applicable funding agency here. If none, delete this. is used as the metric to evaluate the accuracy of the output from the algorithm when weighted against the traditional information flow in the outpatient department.