cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dwiza Riana
Contact Email
dwizariana22@gmail.com
Phone
+6281771998
Journal Mail Official
jmedinftech@gmail.com
Editorial Address
Jl. Raya Jatiwaringin No.2, Jakarta-13620, Indonesia
Location
Kota padang,
Sumatera barat
INDONESIA
Journal Medical Informatics Technology
Published by Asia Pacific Network for Sustainable Agriculture, Food and Energy
ISSN : 29887003     EISSN : 29887003     DOI : https://doi.org/10.37034/medinftech
Core Subject : Health, Science, Engineering,
Computer Science & IT Dentistry Engineering Medicine & Pharmacology Public Health
Journal Medical Informatics Technology publishes papers on innovative applications, development of new technologies and efficient solutions in Health Professions, Medicine, Neuroscience, Nursing, Dentistry, Immunology, Pharmacology, Toxicology, Psychology, Pharmaceutics, Medical Records, Disease Informatics, Medical Imaging and scientific research to improve knowledge and practice in the field of Medical.
Arjuna Subject : Teknik (semua kategori) - Teknik Biomedis
Articles 72 Documents
 4   5   6   7   8 
Enhancing Thorax Images Using Fuzzy Logic Based Techniques Duwi Lufita Marfiana
Journal Medical Informatics Technology Volume 4 No. 1, March 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i1.46

Abstract

Enhancing the quality of thoracic X-ray images is crucial for accurate medical diagnosis; however, conventional enhancement methods often struggle to reduce noise while preserving important edge structures and anatomical details. This study proposes a hybrid image enhancement framework that integrates median neighborhood filtering, convolution processing, fuzzy logic-based edge detection, and morphological operations to improve image clarity and structural definition. The proposed pipeline begins with median neighborhood filtering to reduce noise while preserving essential image structures. The filtered image is then processed using convolution to enhance feature representation and prepare the data for edge detection. Subsequently, fuzzy logic-based edge detection is applied to handle intensity variations and uncertainty, enabling adaptive detection of faint and overlapping edges. Finally, morphological operations are used to refine edge continuity and remove small artifacts, resulting in clearer anatomical boundaries. Experimental results demonstrate that the proposed method effectively reduces noise while maintaining structural integrity, as indicated by stable pixel value transformations after filtering and improved edge clarity in visual comparisons. The method shows better performance in preserving continuous edge structures and detecting subtle thoracic features compared to conventional approaches. In conclusion, the integration of median filtering, convolution processing, fuzzy logic-based edge detection, and morphological refinement provides an effective framework for enhancing thoracic medical images and supports more reliable interpretation in medical imaging applications.
Early Diabetes Detection Using Machine Learning Models: A Case Study from Indonesian Clinical Data Yasrizal Chairul; Muhammad Haris
Journal Medical Informatics Technology Volume 4 No. 1, March 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i1.80

Abstract

Diabetes is a major health problem that can significantly reduce life expectancy and increase the risk of serious complications such as kidney failure, stroke, and cardiovascular disease. Therefore, early detection is essential to prevent the progression of the disease. This study proposes a machine learning-based approach for early diabetes detection using a private dataset obtained from RSUP Persahabatan General Hospital in Jakarta, Indonesia. The dataset consists of 501 patient records with clinical and laboratory features extracted from the hospital’s electronic medical record system. Several machine learning algorithms were implemented and compared, including Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, Naïve Bayes, Extreme Gradient Boosting, Ensemble methods, and Artificial Neural Networks. Feature selection was performed using ANOVA, and hyperparameter optimization was applied using GridSearchCV to improve model performance. The experimental results show that the Artificial Neural Network model achieved the best performance with an accuracy of 0.86 (86%). Statistical analysis using logistic regression identified systolic blood pressure, diastolic blood pressure, age, HDL cholesterol, and leukocyte levels as the most significant risk factors associated with diabetes. These findings demonstrate the potential of machine learning techniques to support early diabetes detection using clinical data from Indonesian healthcare settings.
Evaluation of Pap Smear Nucleus Cell Image Segmentation: The Impact of Enhancement Processes on Segmentation Result Esron Nainggolan; Nita Merlina; Farisya Setiadi
Journal Medical Informatics Technology Volume 4 No. 1, March 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i1.93

Abstract

Accurate nucleus segmentation is vital for automated cervical cancer diagnosis, yet it remains challenging due to overlapping cells and uneven lighting. This study evaluates Polynomial Contrast Enhancement (PCE) using a second-degree polynomial function to improve segmentation on 100 images from the RepomedUNM dataset. The pipeline integrates grayscale conversion, Gaussian blur, and PCE prior to Canny edge detection. Results demonstrate near-perfect Precision (0.9999–1.0000) across all categories (Normal, H-SIL, L-SIL, and Koilocyt), effectively eliminating false positives. However, Recall and Accuracy remained low (max 0.0634 in H-SIL), a technical consequence of Canny’s limitation in capturing thin boundaries versus solid nuclear areas. The study’s novelty lies in the application of second-degree PCE to stabilize intensity variations across multiple diagnostic categories. While PCE ensures exceptional localization precision, future systems should integrate deep learning to enhance recall in complex overlapping structures.
Validation of the pSUAPP Questionnaire and User Experience Evaluation of the Satu Sehat Health Application in Indonesia Vina Eriyandi; Riki Daniel Tanebeth; Dwiza Riana; Sri Hadianti
Journal Medical Informatics Technology Volume 4 No. 1, March 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i1.110

Abstract

The increasing use of digital health applications in Indonesia requires valid and reliable instruments to evaluate usability and user experience. This study aims to adapt and validate the pSUAPP questionnaire in the Indonesian context and to assess the usability of the Satu Sehat application. A cross-sectional validation study was conducted from May to June 2025 involving 102 active users of the Satu Sehat application, with 90 respondents included in the final psychometric analysis. The adapted pSUAPP questionnaire consists of 27 items covering four domains: first contact, registration, features, and overall user experience. Reliability and validity were assessed using Cronbach’s alpha, correlation analysis with SUS, and exploratory factor analysis (EFA). The results showed that the mean pSUAPP score was 67.76 (SD = 18.39), indicating moderate usability. The registration domain obtained the highest score (mean = 87.50; SD = 12.50), while the feature (mean = 70.36) and experience (mean = 69.62) domains showed relatively lower scores. The questionnaire demonstrated high internal consistency, with strong correlations across domains and with SUS. EFA identified four factors explaining 76.7% of the total variance. No significant differences were observed across sociodemographic characteristics. In conclusion, the Indonesian version of the pSUAPP questionnaire is a valid and reliable instrument for evaluating digital health applications. While the Satu Sehat application performs well in registration, improvements are needed in monitoring features and user experience to support long-term engagement.
Differences in Contrast Quality of Digital Panoramic Radiographs Before and After Contrast Stretching Moh Yusuf; Rina Kartika S; Dinanti Irwina Putri
Journal Medical Informatics Technology Volume 4 No. 1, March 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i1.115

Abstract

Digital panoramic radiography is widely used for diagnosis and treatment planning because it provides comprehensive information on dental and maxillofacial anatomical structures in digital form that can be directly visualized on a computer screen. However, the quality of panoramic radiographs may decrease due to noise, inadequate density, and low contrast, which can affect diagnostic interpretation. The contrast stretching method can be applied to address this problem by increasing image contrast and reducing noise, thereby improving the visibility of objects and anatomical boundaries in radiographic images. This study aimed to determine the effect of the contrast stretching method on the quality of digital panoramic radiographs. A quantitative experimental analysis was conducted using retrospective digital panoramic radiograph data from patients at RSIGMP UNISSULA. A total of 155 digital panoramic radiograph images from July 2021 to July 2022 were selected using the Slovin method. Image quality enhancement was quantitatively evaluated using the Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) parameters. The obtained data were analyzed using a paired t-test after fulfilling the normality assumption. The results showed significant differences in both SNR and CNR values before and after processing, with a significance value of 0.000 (p < 0.05). Both parameters increased after contrast stretching, indicating improved image contrast and reduced noise in digital panoramic radiographs. These findings demonstrate that contrast stretching is an effective and practical method for improving radiographic quality, which may support radiographers in achieving clearer diagnostic images and provide useful insight for medical imaging system developers in designing image enhancement modules.
Classification of Corn Leaf Disease Detection Using ResNet50 and Inception V3 I Indarti; Dewi Laraswati; F Frieyadie
Journal Medical Informatics Technology Volume 4 No. 2, June 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i2.90

Abstract

Corn is an important food crop in Indonesia, requiring accurate classification methods to support agricultural productivity. To evaluate and compare ResNet50 and Inception V3 models with augmentation techniques for corn image classification. Deep learning classification using CNN architectures with rotation, shifting, and flipping augmentation. 3,560 corn images (2,500 training, 700 validation, and 360 testing). ResNet50 achieved 93.05% accuracy, while Inception V3 achieved the highest performance with 94.02% accuracy, 93.04% precision, 93.00% recall, and 93.02% F1-score. Image augmentation significantly improved classification performance, and Inception V3 was identified as the most effective model for corn image classification.
Computational Pharmacology Approach to Identify Antidiarrheal Candidates from Eleusine indica L.: Molecular Docking Simulation and Drug-likeness Prediction Targeting 5ZHP Receptor Faisal Akhmal Muslikh; Rizki Rahmadi Pratama; Syahputra Wibowo; Yanu Andhiarto; Burhan Ma’arif; Maximus M. Taek
Journal Medical Informatics Technology Volume 4 No. 2, June 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i2.142

Abstract

Diarrhea remains a significant global health concern with high morbidity and mortality rates, particularly in developing countries. The use of synthetic antidiarrheal drugs is associated with various adverse effects, necessitating the exploration of safer therapeutic alternatives derived from natural sources. This study aimed to evaluate the potential of secondary metabolite compounds from Eleusine indica as antidiarrheal candidates through an in silico approach, employing drug-likeness analysis and molecular docking simulation against the muscarinic acetylcholine M3 receptor (PDB ID: 5ZHP). Drug-likeness analysis was performed using the SwissADME web tool based on Lipinski's Rule of Five. Molecular docking simulation was conducted using Molegro Virtual Docker, with the root mean square deviation (RMSD) value employed as a validation parameter. The results revealed that the majority of the compounds satisfied Lipinski's criteria, indicating their potential as oral drug candidates. Docking method validation yielded an RMSD value of 0.777437 Å, confirming the validity and reliability of the docking procedure. Docking results suggested that compound M15 (andrographolide) and compound M13 [4-(1-hydroxyethyl)-2,6-bis(3-methylbut-2-en-1-yl)phenol] exhibited the lowest Rerank Scores of −116.686 and −114.300, respectively, which were notably lower than that of the positive control loperamide (−41.9287), suggesting potentially stronger binding affinity and more favorable interaction with the target receptor. However, these findings are predictive in nature and require further validation through experimental biological studies and molecular dynamics simulations to confirm actual binding stability and pharmacological effectiveness.
Accuracy of Clinical Coding in Cesarean Section Cases Using ICD-10 and ICD-9-CM Gama Bagus Kuntoadi; Indah Kristina; Hudiyati Agustini; Rumondang Christin
Journal Medical Informatics Technology Volume 4 No. 2, June 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i2.146

Abstract

Accurate clinical coding in cesarean section cases is essential for morbidity reporting, clinical data quality, and the validity of INA-CBG reimbursement claims under the national health insurance system. Obstetric cases are inherently complex, involving multiple diagnosis and procedure codes that must conform to ICD-10 and ICD-9-CM standards. Objective: This study aimed to analyze the accuracy of ICD-10 diagnosis coding and ICD-9-CM procedure coding across multiple obstetric coding components in cesarean section cases at a hospital in Jakarta, Indonesia. A descriptive quantitative study with a retrospective design was conducted on 95 medical records of obstetric and gynecological patients who underwent cesarean section in 2025, selected through total sampling. Coding accuracy was determined by comparing hospital-assigned codes against standard codes re-verified by researchers based on WHO ICD-10 Volume 2 and ICD-9-CM guidelines. Data were analyzed using frequency, percentage, mean, median, and standard deviation, following a Shapiro-Wilk normality test. The overall accuracy rate for ICD-10 diagnosis codes was 83.9% (266/317 codes) and for ICD-9-CM procedure codes was 91.5% (86/94 codes). Accuracy varied substantially across coding components: secondary diagnosis codes for cesarean delivery and delivery outcome codes each reached 90.5%, while codes for concomitant diagnoses reached only 34.7%. For procedures, cesarean section codes (74.x) achieved 85.3% accuracy, whereas non-cesarean section procedure codes showed accuracy of only 5.3%, predominantly due to undercoding of additional operative procedures documented in surgical reports. Coding accuracy for obstetric cesarean section cases was generally good to very good in aggregate; however, substantial gaps remain in the coding of concomitant diagnoses and additional procedures. This study contributes a component-level evaluation across diagnosis, delivery outcome, and procedure coding, offering a more granular assessment of coding accuracy than prior single-metric studies.
The Sociodemographic Factors and Accessibility in Utilizing the Maternal and Child Health Handbook for Monitoring Under-Five Children in North Sumatera Syafrina Ulfah; Fithri Handayani Lubis; Kiki Rismadi; Diza Fathamira Hamzah
Journal Medical Informatics Technology Volume 4 No. 2, June 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i2.149

Abstract

Utilization of the Maternal and Child Health (MCH) Handbook plays a crucial role in monitoring the health and development of children under five years of age; however, its uptake remains suboptimal. According to the 2023 Indonesian Health Survey (SKI), MCH Handbook utilization for under-five growth monitoring in North Sumatra Province was only 67.9%, below the national average of 74.4%. This study aimed to analyze the influence of sociodemographic factors and healthcare accessibility on MCH Handbook utilization for under-five child monitoring in North Sumatra Province. A cross-sectional design was employed using secondary data from the 2023 SKI. The study sample comprised 4,164 under-five children who owned or had previously owned an MCH Handbook in North Sumatra. Data were analyzed through univariate frequency distribution, bivariate chi-square testing, and multivariate multiple logistic regression using the backward stepwise (likelihood ratio) method. The multivariate analysis demonstrated that health insurance ownership (AOR = 1.389; 95% CI = 1.215–1.587), maternal education (AOR = 1.326; 95% CI = 1.107–1.588), maternal age (AOR = 1.163; 95% CI = 1.009–1.339), and maternal employment (AOR = 1.161; 95% CI = 1.007–1.338) were significant positive predictors of MCH Handbook utilization, while longer travel time to health facilities (AOR = 0.690; 95% CI = 0.503–0.946) was inversely associated. Area classification was not statistically significant. These findings underscore the need for sustained health education targeting mothers, maintenance of universal health insurance coverage, and strengthening of community-based health services particularly posyandu to optimize MCH Handbook utilization in North Sumatra.
Determinants of Hospital Length of Stay Among Pulmonary Tuberculosis Inpatients at A Secondary General Hospital in Indonesia: A Comparative Analysis Balqis Nurmauli Damanik; Hely Hely
Journal Medical Informatics Technology Volume 4 No. 2, June 2026
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v4i2.150

Abstract

Tuberculosis (TB) remains a major public health challenge in Indonesia, which has the second-highest TB burden globally. Hospital length of stay (LOS) is an important indicator of inpatient care efficiency and influences reimbursement under the Indonesia Case-Based Groups (INA-CBGs) payment system. However, evidence regarding determinants of LOS in Indonesian secondary hospitals is still limited. This retrospective comparative study analyzed secondary medical-record data from a secondary general hospital in Medan, North Sumatra, collected between January and August 2025. Among 238 identified records, 215 patients with a primary diagnosis of pulmonary TB (ICD-10: A15.0–A16.9) met the inclusion criteria. LOS was calculated from admission and discharge dates. As LOS was not normally distributed (Shapiro–Wilk, p < 0.001), the Kruskal–Wallis and Mann–Whitney U tests with Dunn post-hoc correction were applied (α = 0.05). The median LOS was 3 days (IQR 2–4; range 0–13). Most patients were younger than 65 years (75.3%), while 51.2% had no documented comorbidity. Comorbidity burden was the only factor significantly associated with LOS (H = 18.74, p < 0.001; η² = 0.082). Patients with two or more comorbidities had significantly longer hospitalization than those without comorbidities (mean 4.18 vs. 2.82 days; p < 0.001) and those with one comorbidity (p = 0.013). No significant differences were found according to age group or insurance status. These findings indicate that comorbidity burden contributes to prolonged hospitalization among pulmonary TB inpatients and support integrating multimorbidity management into TB care. Larger multicenter prospective studies are needed to validate these findings.

Page 7 of 8 | Total Record : 72

 4   5   6   7   8 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Volume 4 No. 2, June 2026 Volume 4 No. 1, March 2026 Volume 3 No. 4, December 2025 Volume 3 No. 3, September 2025 Volume 3 No. 2, June 2025 Volume 3 No. 1, March 2025 Volume 2 No. 4, December 2024 Volume 2 No. 3, September 2024 Volume 2 No. 2, June 2024 Volume 2 No. 1, March 2024 Volume 1 No. 4, December 2023 Volume 1 No. 3, September 2023 Volume 1 No. 2, June 2023 Volume 1 No. 1, March 2023 More Issue