IMPLEMENTASI METODE PEMBOBOTAN BERBASIS ATURAN DAN METODE PROFILE MATCHING PADA SISTEM PAKAR MEDIS UNTUK PREDIKSI RISIKO HIPERTENSI

Cardiovascular is a disease that often causes death. One of the cardiovascular diseases that often cause death is the risk of Hipertensi. The highest risk factors for premature death and disability in the world are caused by smoking habits, high systolic blood pressure, and increased blood sugar levels. This death factor is because people with Hipertensi generally do not experience any symptoms until their blood pressure is too high which can cause death. Efforts that can be made are by utilizing information technology in the form of a medical expert system to Kelasify the risk of Hipertensi. This study aims to develop a medical expert system in a different way using rule-based weighting methods and profile matching. The weighting method is used to determine the risk weight based on patient variables, while the profile matching method is used to calculate the risk Kelasification based on the core factor and secondary factor variables on the risk of Hipertensi. System evaluation is carried out by comparing asset data taken from the Pima Indian Hipertensi Data (NHANES) with results from the system. The results of the comparison show that the accuracy of the proposed system is 96.67%. The proposed system is also compared with other Kelasification methods such as decision tree, Random Tree, Decision Stump, KNN, Naïve BaYa, Deep Learning, and Rule Induction. Based on the comparison results, the proposed system has a better level of accuracy, therefore the system developed can be used to Kelasify risks for other types of diseases.

Design and implementation of a medical expert system for diagnosis and prescription

This project work focuses on computerization of medical diagnosis and prescription system to increase medical services and enhancement of logistic efficiency. The aim is to produce approach which through computer programs and files carefully created, written, designed and integrated from an application package that accepts both physical states of patients. Disease symptoms (input data) and as such one which is able to store, access, manipulates as much information as possible. The ease and speed of processing, storage and versatility of the computer make it possible for easy diagnosis and prescription interestingly; the end results is the ability analysis of the disease by producing the input data and provide summaries of the total treatment bill, lab result and other disease investigation and confirmation for a particular patient.

The Development of Integrated Medical Expert System for Diabetes Mellitus Patient

Diabetes Mellitus (DM) is a degenerative disease that has many causative factors. DM patients cannot recover completely but they can maintain the stability of their glucose level by following a healthy lifestyle. The goal of this research is to make an integrated system for people to promote a healthy lifestyle. This system also allows people to monitor the changes in their daily health conditions regularly. Main features in this system diagnose, treatment, guidelines for a healthy lifestyle, including a feature for counting and saving daily calorie consumption and physical activity. The system using the backward inference method to get the conclusion from a set of rules in the knowledge base. The verification using a query, validation with using recall and precision, and usability testing using a questionnaire, was conducted to test the performance of the system. The result of the testing shows that the system gives a good response to all queries given and the user also satisfied with the system. The recall value is 1 with the precision is 0.658. This precision value also promotes the inference process used in the system, which every user will suspect has DM when they start to use the diagnose feature.

Data aggregation and indexing support from multiple sources using graph model in medical expert system databases

One of the key problems in developing and integrating expert systems for medical research is the problem of data aggregation. Most of the times, general information about the patient and data about undergone research procedures exist as part of several disconnected information systems, each using its own schema for presenting and storing information. The paper proposes a solution to aggregate research and patient data in medical establishments using formal projections mechanism, which allows to unify data extraction from separate data sources. Graph-based patient and research record representation is introduced, which allows to support and optimize complex queries for single patient and for a set of historical data from single research. Proposed representation mechanism is also shown to be effective for centralized processing using various data mining and intelligent analysis techniques.