(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 14, No. 7, 2023 783 | Page www.ijacsa.thesai.org GDM-PREP: A Rule-Based Technique to Enhance Early Detection of Gestational Diabetes Mellitus Ayunnie Azmi 1 , Nurulhuda Zainuddin 2 , Azmi Aminordin 3 , Masurah Mohamad 4 College of Computing, Informatics & Mathematics, Universiti Teknologi MARA (UiTM), Melaka Branch, Jasin Campus, 77300 Merlimau, Melaka, Malaysia 1, 2, 3 College of Computing, Informatics & Mathematics, Universiti Teknologi MARA (UiTM) Perak Branch, Tapah Campus, 3500 Tapah Road, Perak, Malaysia 4 Abstract—Gestational diabetes mellitus (GDM), a condition occurring solely during pregnancy, poses risks to both expectant mothers and their infants, particularly among individuals with pre-existing risk factors. However, early diagnosis and effective management of GDM can help mitigate potential complications. As part of the Ministry of Health's efforts to enhance screening and management strategies for GDM in Malaysia, this study aims utilizing a rule-based technique, acting as an Expert System for Initial Screening of Gestational Diabetes Mellitus Detection. This application will facilitate early diagnosis by assessing risk factors and symptoms to calculate the probability of GDM occurrence and classify it as low, medium, or high. Functionality and usability tests are conducted to ensure error-free performance and gather user feedback. The study's findings indicate that the self-check GDM system effectively utilizes the algorithm, while the mobile application showcases good usability, achieving an above-average System Usability Scale (SUS) score. Keywords—Gestational diabetes mellitus (GDM); rule based; expert systems; risk factor I. INTRODUCTION Gestational diabetes mellitus (GDM), which only manifests during pregnancy, is the term used to describe diabetes during pregnancy. This is a severe condition that causes pregnant women who were previously normal but discovered to have higher levels of blood glucose during pregnancy [1]. GDM is increasing in prevalence, with 21 million cases (or 7% of the global population) being reported globally [2]. The number of pregnant women with GDM is increasing due to changes in eating habits, increased purchasing power, and climate change [3]. In the early stages of pregnancy, the mother‟s body undergoes several changes that turn her into a different individual with unique physical and mental features leading to changes in health habits and lifestyle. Hence, those habits and lifestyle choices during pregnancy seem to have permanent and long-term effects on the mother's and child's health [4]. GDM raises the risk of short-term and long-term risks in pregnant women, including pre-eclampsia, caesarean section rates, miscarriage, and subsequent lifelong diabetes. Children of mothers with GDM are more probably to have neonatal respiratory distress syndrome and hypoglycemia and develop diabetes, obesity, and metabolic disorders later in life. Women at risk to develop GDM is when they are having the presence of any risk factors such as a body mass index of more than 27 kg/m2, previous history of GDM, first-degree relative with diabetes, history of macrosomia, bad obstetric history, developed glycosuria ≥2+ on two occasions, and any current obstetric problems. These recommendations from the Clinical Practice Guidelines (CPG) are intended to be clinical practice manuals in Malaysia based on the best information available at the time of development [1]. In support of the Ministry of Health‟s objectives of continuing to develop improved screening and management strategies for GDM in Malaysia and of preventing the development of type 2 diabetes mellitus in pregnant women [5][6], this study aims utilizing a rule-based technique, acting as an Expert System for Initial Screening of Gestational Diabetes Mellitus Detection based on the risk factors and symptoms. Early diagnosis of GDM is important to minimize the risk, but in the first trimester of gestation, the Oral Glucose Tolerance Test (OGTT) is ineffective as pregnancy-induced hyperglycemia is not always clearly apparent in the first months of gestation [3]. Therefore, screening for a disease is advised when the disease is common and clinically significant, and when there is a clear screening test that will classify most diseased persons without high rates of false-positive or false- negative outcomes. The early screening of diseases is very important for society as it contributes to improvements in the quality of life and economic growth in the countries. This screening allows the early initiation of proper treatment of the disease to prevent death [3]. In addition, the screening and subsequent detection of GDM before pregnancy enable effective management to reduce maternal and fetal morbidity and mortality associated with pregnancy hyperglycemia [6]. In the research conducted by [7], Malaysia is in the fifth rank in Asia with an 18.5% prevalence rate of GDM. To reduce the prevalence rate in Malaysia and to have good primary care for the mother and patients at risk at a minimal cost, needs a pre-screening test procedure that is easy and gives new knowledge to know better about themselves [8][9]. Several biochemical tests for diabetes diagnosis in early pregnancy were proposed, which as the Oral Glucose Tolerance Test (OGTT). However, it is an expensive and manual test, and its poor tolerability may affect enforcement, especially in the context of nausea during the early stages of pregnancy [6]. Therefore, in this research, the initial screening of the GDM expert system is proposed based on risk factors