Kasim, Sazzli Shahlan
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Review of NLP in EMR: abbreviation, diagnosis, and ICD classification Iqbal Basheer, Nurul Anis Balqis; Nordin, Sharifalillah; Kasim, Sazzli Shahlan; Ali, Azliza Mohd; Abdul Hamid, Nurzeatul Hamimah
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 14, No 3: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v14i3.pp881-891

Abstract

This review explores state-of-the-art natural language processing (NLP) methods applied to electronic medical records (EMRs) for key tasks such as expanding medical abbreviations, automated diagnosis generation, international classification of diseases (ICD) classification, and explaining model outcomes. With the growing digitization of healthcare data, the complexity of EMR analysis presents a significant challenge for accurate and interpretable results. This paper evaluates various methodologies, highlighting their strengths, limitations, and potential for improving clinical decision-making. Special attention is given to abbreviation expansion as a crucial step for disambiguating terms in the clinical text, followed by an exploration of auto-diagnosis models and ICD code assignment techniques. Finally, interpretability methods like integrated gradients and attention-based approaches are reviewed to understand model predictions and their applicability in healthcare. This review aims to provide a comprehensive guide for researchers and practitioners interested in leveraging NLP for clinical text analysis.
Effects of Time-Restricted Eating on Cardiometabolic and Cardiovascular Health: Study Protocol (TRES) Zaman, Mazuin Kamarul; Mohd Fahmi Teng, Nur Islami; Kasim, Sazzli Shahlan; Juliana, Norsham
Jurnal Gizi dan Pangan Vol. 19 No. Supp.1 (2024)
Publisher : The Food and Nutrition Society of Indonesia in collaboration with the Department of Community Nutrition, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25182/jgp.2024.19.Supp.1.35-44

Abstract

This study aims to assess the safety, feasibility, and effectiveness of 10-hr Time-Restricted Eating (TRE) compared to ad libitum eating on anthropometric measurements, cardiometabolic and cardiovascular health in patients with Acute Coronary Syndrome (ACS). The Time-Restricted Eating Study (TRES) is a single-centre, pragmatic, prospective, randomised controlled trial that will include 48 patients with ACS. Participants will be randomised in a 1:1 ratio to the intervention group where eating duration is restricted to 10 hours per day or control group with no limitation of eating duration imposed. Testing is scheduled at baseline and after four weeks of intervention. The primary outcome is change in body weight after four weeks of intervention. Secondary outcomes include changes in body composition, glycaemic and lipid profiles, inflammatory markers, oxidative stress, endothelial function, arterial stiffness, blood pressure, heart rate, safety, and feasibility of TRE on patients with ACS. The study was approved by the UiTM Research Ethics Committee. Findings will be disseminated through manuscripts, reports, and presentations. Findings on the feasibility and effectiveness of TRE in patients with ACS may broaden the body of evidence for implementing TRE as a dietary intervention to prevent secondary cardiovascular diseases.
Factors Associated with Ischemic Heart Disease (IHD) among Type 2 Diabetes Mellitus Patients: Evidence from the National DiabetesRegistry of Johor, Malaysia Salleh, Muhammad Muzzammil Mohamad; Kasim, Sazzli Shahlan; Razak, Tajul Rosli; Azahar, Nazar Mohd; Ismail, Norzaher; Yusoff, Mohamad Zuhair Mohamed; Khebir, Muhammad Hariz ‘Ammar; Teruna, Muhammad Muaz Shahriman; Rameli, Nur Adilla Che; Moh, Muhammad Irfan
Mulawarman International Conference on Tropical Public Health Vol. 2 No. 2 (2025): The 4th MICTOPH
Publisher : Faculty of Public Health Mulawarman University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Background : IHD remains a leading cause of mortality among individuals with type 2 diabetes mellitus (T2DM). Despite the availability of extensive registry data, limited local evidence exists regarding factors associated with IHD among Malaysian diabetic populations. Objective : This study aimed to identify demographic, clinical, and pharmacological associated factors of IHD using data from the National Diabetes Registry (NDR) of Johor, Malaysia. Research Methods/ Implementation Methods : A cross-sectional analysis was conducted using NDR data from 11,082 adults with T2DM registered between 2019 and 2021. Sociodemographic, clinical, biochemical, and medication variables were analyzed. Univariable and multivariable logistic regression identified independent associated factors of IHD, expressed as adjusted odds ratios (aORs) with 95% confidence intervals (CIs). Results : The prevalence of IHD among T2DM patients was 10.4% (95% CI=9.8, 11.0). Independent predictors of IHD included age ≥60 years (aOR = 1.57, 95% CI: 1.33–1.86), male sex (aOR = 1.46, 95% CI: 1.25–1.71), Chinese ethnicity (aOR = 1.60, 95% CI: 1.28–1.98), hypertension (aOR = 1.86, 95% CI: 1.38–2.51), dyslipidaemia (aOR = 1.47, 95% CI: 1.16–1.86), diabetes duration > 10 years (aOR = 1.35, 95% CI: 1.10–1.65), and diabetic retinopathy (aOR = 1.52, 95% CI: 1.28–1.79). Non- use of calcium channel blockers (aOR = 1.52, 95% CI: 1.32–1.76) increased IHD risk, while paradoxical inverse associations were noted for non-use of aspirin, ticlopidine, and beta-blockers, likely reflecting confounding by indication. Glitazone use showed a strong association with IHD (aOR = 10.46, 95% CI: 1.423, 76.960), possibly due to small sample bias. Conclusion/Lesson Learned : IHD prevalence among Malaysian diabetics is substantial and driven by multiple modifiable and demographic factors. Integrating artificial intelligence (AI) predictive models within the NDR using these variables could enhance early risk stratification and targeted cardiovascular prevention.