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 16 Documents
 1   2 
Segmentation in Identifying the Development of Ground Glass Opacity on CT-Scan Images of the Lungs Jufriadif Na`am
Journal Medical Informatics Technology Volume 1 No. 1, March 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i1.1

Abstract

Ground Glass Opacity (GGO) in the image of the lungs is an object that is white in color. The image was recorded using a Computerized Tomography Scan (CT-Scan). This object has very similar color features to other objects in the lung image, making it very difficult to identify precisely. Likewise by observing the development of this object every time from recording continuously. This study aims to segment the GGO on CT-Scan images that are examined repeatedly due to an increase in complaints against patients. The processed image is an image of the lungs from the CT-Scan equipment. Patients were recorded twice at different time intervals. The processed image is an axial slice of the data cavity as a whole, totaling 12 images for each patient in each recording. The tool used for recording is a CT-Scan with the General Electric (GE) brand model D3162T. The method used is parallel processing with a combination of Image Enhancement techniques, Convert to Binary Image, Morphology Operation, Image Inverted, Active Contour Model, Image Addition, Convert Matrix to Grayscale, Image Filtering, Convert to Binary Image, Image Subtraction and Region Properties. The results of this study can identify the development of the GGO pixel size well, where the increasing number of patient complaints, the larger the GGO area. The extent of development of GGO is irregular with respect to time and examination. Each patient experienced an expansion of GGO by an average of 0.54% to 1.89%. This study is very good and can correctly identify ARF, so it can be used to measure the level of development of ARF in patients with accuracy.
Performance Comparison of Three Classification Algorithms for Non-alcoholic Fatty Liver Disease Patients Using Data Mining Tool Adi Octaviantara; Moch Anwar Abbas; Ahmad Azhari; Dwiza Riana; Alya Shafira Hewiz
Journal Medical Informatics Technology Volume 1 No. 1, March 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i1.2

Abstract

This study aims to carry out a comparative analysis of the three classification algorithms used in research on Nonalcoholic Fatty Liver Disease (NAFLD) Patients. NAFLD is a liver condition associated with the accumulation of fat in the liver in individuals who do not consume excessive alcohol. The algorithms used in the analysis are Decision Tree, Naïve Bayes, and k-Nearest Neighbor (k-NN), with data processing using RapidMiner software. The data used is sourced from Kaggle which comes from the Rochester Epidemiology Project (REP) database with research conducted in Olmsted, Minnesota, United States. The measurement results show that the Decision Tree algorithm has an accuracy of 92.56%, a precision of 93.24%, and a recall of 99.08%. The Naïve Bayes algorithm has an accuracy of 89.93%, a precision of 95.40% and a recall of 93.56%. While the k-Nearest Neighbor algorithm has an accuracy of 91.33%, a precision of 91.94%, and a recall of 99.27%. ROC curve analysis, all algorithms show "Excellent" classification quality. However, only the k-NN algorithm reached 1.0, showing excellent classification results in solving the problem of classifying Nonalcoholic Fatty Liver Disease patients. This study concluded that the k-NN algorithm is a better choice in solving the problem of classifying Non-alcoholic Fatty Liver Disease patients compared to the Decision Tree and Naïve Bayes algorithms. This study provides valuable insights in the development of classification methods for the early diagnosis and management of NAFLD.
Logistic Regression with Hyper Parameter Tuning Optimization for Heart Failure Prediction Teguh Herwanto; Wan Ahmad Gazali Kodri; Faruq Aziz; Alya Shafira Hewiz; Dwiza Riana
Journal Medical Informatics Technology Volume 1 No. 1, March 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i1.3

Abstract

Heart failure is a major public health concern that causes a substantial number of deaths worldwide. Risk factor analysis is required to diagnose and treat patients with heart failure. The logistic regression with hyper parameter tuning optimization is presented in this research, with ejection fraction, high blood pressure, age, and  serum creatinine as relevant risk factors. This study indicates that better data preparation utilizing Deep Learning with hyper parameter adjustment be used to determine the best parameter that has a substantial influence as a risk factor for heart failure. The experiments employed data from the Faisalabad Institute of Cardiology and Allied  Hospital in Faisalabad (Punjab, Pakistan), which included 299 samples. The experimental findings reveal that the proposed approach obtains a recall of 63.16% greater than related works.
Optimizing Lung Cancer Prediction Using Evaluating Classification Methods and Sampling Techniques Dika Putri Metalica; Fahmi B Marasabessy
Journal Medical Informatics Technology Volume 1 No. 1, March 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i1.4

Abstract

Lung cancer is an extremely aggressive type of cancer and one of the leading causes of death globally. The focus of this study is to improve the detection and prediction of lung cancer by evaluating different approaches for classification and sampling. The research utilizes a dataset comprising 1000 patients and 24 Attributes. The primary goal is to compare the effectiveness of classification methods like Logistic Regression, AdaBoost, and GradientBoosting, in conjunction with diverse sampling techniques such as Random Over-Sampling, RandomUnder-Sampling, and SMOTE by Level Considering, for predicting lung cancer. The assessment metrics includeaccuracy, precision, recall, and F1-score. The experimental findings demonstrate that Gradient Boosting (GBoost) attains flawless accuracy, precision, recall, and F1-score results of 100% when identifying lung cancer instances within the dataset. This highlights the effectiveness of GBoost in accurately predicting lung cancer occurrence. The findings of this research aim to contribute significantly to the development of more effective diagnostic and predictive methods for lung cancer. 
Optimization of Breast Cancer Prediction using Optimaze Parameter on Machine Learning Sri Nuarini; Ade Rumintarsih
Journal Medical Informatics Technology Volume 1 No. 1, March 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i1.5

Abstract

At present, a very common cancer disease in women is breast cancer. This cancer develops in the female breast tissue and is the cancer with the highest mortality rate. This needs great attention. Forecasting breast cancer has been studied by a number of researchers and is considered a serious threat to women. Clinical difficulties in creating treatment approaches that will help patients live longer, due to the lack of solid predictive models that can predict outcomes at an early stage by analyzing patient history data. Because it can affect women all over the world. Early detection of breast cancer is crucial in determining the path of action. Cancer types can be distinguished into two types: benign and malignant. this research aims to provide information and science to medical professionals and also cancer patients to know the classification of the two types of cancer. The research project aims to also leverage data mining techniques using several algorithms on Machine Learning (ML) such as Decision Tree(DT), Random Forest (RF), K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machine (SVM), and Gradient Boosting Tress (XGBoost). The results of this algorithm will determine the prediction of the most common types of cancer. The study used 683 samples of breast cancer patients, including 10 characteristics. This test is measured through mammography and biopsy tests. Using K-Fold Validation operators, then the sresults of the study showed that the K-Nearest Neighbor (KNN) algorithm produced the highest accuracy of 96.87% compared to the other five algorithms. Then, as a comparison again, the researchers also optimized the accuracy value using the parameter optimize operator. Where the number produced becomes more overwhelming. The highest accuracy result after calculated with the parameter optimize is the Random Forest (RF) algorithm. Where the result is 100% accurate compared to other ML algorithms. 
Image Segmentation of Normal Pap Smear Thinprep using U-Net with Mobilenetv2 Encoder Deviana Sely Wita
Journal Medical Informatics Technology Volume 1 No. 2, June 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i2.6

Abstract

Pap smear is a technique to detect changes in the cells in the uterine wall. With a Pap smear, a woman can be known to have cervical cancer or not. However, the problem of cancer screening on pap smear images is largely hindered by improper cell staining and overlapping cell images. For accurate Pap smear image segmentation, this study uses the U-Net method which is better for Pap smear image segmentation. This method integrates the MobilenetV2 network and converts ordinary convolution into deep split convolution to improve transmission and feature utilization by the network, and at the same time increase the speed of feature extraction. Then the segmentation results from MobilenetV2 produce accuracy in distinguishing the nucleus, cytoplasm, and background on the pap smear image. The dataset used in this study is a normal analogue image of the Pap smear image obtained from the RepoMedUNM Database. Initial data processing is done by digitizing the image, where analog data from the Pap smear is transformed into a digital image. Based on the results of research that has been carried out, namely segmentation of Pap smear images using U-Net with MobilenetV2 encoder, the accuracy value on differences in nucleus, cytoplasm, and background cells is 98%.
Glaucoma Detection in Fundus Eye Images using Convolutional Neural Network Method with Visual Geometric Group 16 and Residual Network 50 Architecture Chandra Nugraha; Sri Hadianti
Journal Medical Informatics Technology Volume 1 No. 2, June 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i2.7

Abstract

Glaucoma is an eye disease usually caused by abnormal eye pressure. One of the causes of abnormal eye pressure is blockage of fluid flow, which if detected too late can lead to blindness. Glaucoma can be identified by examining specific areas on the retina fundus image. The aim of this study is to detect positive and negative glaucoma in fundus images. The image data was obtained from the glaucoma_detection dataset, consisting of 520 images, including 134 glaucoma-infected images and 386 normal images. This study uses the Convolutional Neural Network (CNN) method with Visual Geometric Group-16 (VGG-16) and Residual Network-50 (ResNet-50) architectures. The research and testing results using the VGG-16 architecture obtained an accuracy rate of 78%, while using the ResNet-50 architecture obtained an accuracy rate of 80%.
Classification of Myopia Levels using Deep Learning Methods on Fundus Image Waeisul Bismi; Jufriadif Na`am
Journal Medical Informatics Technology Volume 1 No. 2, June 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i2.8

Abstract

Disorders of the eye or also known as eye disease is a condition that can affect vision for some people in their lifetime. There are 40 types of eye disorders or eye diseases, one of which is Myopia. Myopia is a visual disturbance that causes objects that are far away to appear blurry, but there is no problem seeing objects that are near. Myopia or nearsightedness is also known as minus eye. From this description, it is very important to conduct research in detecting eye diseases before the increase in eye minus and blindness. This study aims to classify myopic eye disease using the Deep Learning method with several different architectures, namely the VGG16, VGG19 and InceptionV3V3 models. Where the first is to distinguish normal and abnormal while the other is to classify with Augmented myopia image dataset and non augmented myopia image dataset obtained from the Retinal Fundus Multi-Disease Image Dataset (RFMID). In the implementation of the Deep Learning method using 20 Epochs. The results of the accuracy of the classification of eye diseases using the non augmented myopia image dataset are 66.0% for the VGG16 architectural model, then 95.99% for the VGG19 architectural model and 93.99% for the InceptionV3 architectural model and the accuracy results using the Augmented myopia image dataset are 97.53% for the VGG16 architectural model, 97.53% for the VGG19 architectural model and 99.50% for the InceptionV3 architecture model.
Systematic Review: Risk Factors and Prevalence of Urinary Incontinence in Elderly Women, a Case Study in Japan and Taiwan Alya Shafira Hewiz; Novira Widajanti; Lukman Hakim; Rwahita Satyawati
Journal Medical Informatics Technology Volume 1 No. 2, June 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i2.9

Abstract

Knowledge of the conditions of elderly women in Japanese and Taiwanese communities, particularly in relation to risk factors and their association with urinary incontinence, is of interest. This study aimed to identify risk factors and prevalence of urinary incontinence in elderly women in the community of the Japanese and Taiwanese case study areas. The research method used was a systematic review based on PRISMA guidelines. Data sources were obtained from PubMed and Science Direct for the period 2000-2020 using specific inclusion and exclusion criteria. Evaluation was conducted for quality and bias risk using a standardized assessment system. Results showed that the prevalence of urinary incontinence in elderly women in Japanese and Taiwanese communities ranged from 29.8% to 31.3%. Many factors influenced urinary incontinence, such as age, body mass index (BMI), and smoking habits. From the two selected articles in Japan and Taiwan, it was concluded that urinary incontinence was commonly experienced by elderly women in the community, and awareness of this condition could help improve management.
Optimization of Melanoma Skin Cancer Detection with the Convolutional Neural Network Harming Puja Kekal; Daniati Uki Eka Saputri
Journal Medical Informatics Technology Volume 1 No. 2, June 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i2.10

Abstract

Currently, skin cancer is a very dangerous disease for humans. Skin cancer is classified into many types such as Melanoma, Basal and Squamous cell carcinoma. In all types of cancer, melanoma is the most dangerous and unpredictable disease. Detection of melanoma cancer at an early stage is useful for effective treatment and can be used to classify types of melanoma cancer. New innovations in the classification and detection of skin cancer using artificial neural networks continue to develop to assist the medical and medical world in analyzing images precisely and accurately. The method used in this research is Convolutional Neural Network (CNN) with MobileNet model architecture. Skin cancer detection consists of five important stages, namely image database collection, preprocessing methods, augmentation data, model training and model evaluation. This evaluation was carried out using the MobileNet method with an accuracy of 88%.

Page 1 of 2 | Total Record : 16

 1   2 

Filter by Year

2023 2023


Reset
Filter By Issues
All Issue Volume 1 No. 4, December 2023 (Accepted) Volume 1 No. 3, September 2023 Volume 1 No. 2, June 2023 Volume 1 No. 1, March 2023