Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Journal Medical Informatics Technology

Logistic Regression with Hyper Parameter Tuning Optimization for Heart Failure Prediction Herwanto, Teguh; Kodri, Wan Ahmad Gazali; Aziz, Faruq; Hewiz, Alya Shafira; Riana, Dwiza
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.
Enhancing Skin Cancer Classification Using Optimized InceptionV3 Model Daniati Uki Eka Saputri; Nurul Khasanah; Aziz, Faruq; Taopik Hidayat
Journal Medical Informatics Technology Volume 1 No. 3, September 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i3.14

Abstract

Skin cancer is a disease that starts in skin cells characterized by uncontrolled growth that can attack skin tissue. Although it has a high cure rate if treated in a timely manner, a delay in diagnosis can have serious consequences. The use of computer technology, especially Artificial Intelligence (AI), has played an important role in improving health services, including in the context of skin cancer. New innovations in the classification and detection of skin cancer using artificial neural networks have led to significant improvements in diagnosis and treatment. One promising approach is using the InceptionV3 algorithm, which has high accuracy and is capable of processing high-resolution images. This study aims to implement InceptionV3 to classify two types of skin cancer, namely malignant and benign, with an emphasis on improving accuracy performance. With the pre-processing process, namely augmentation and the addition of several features, this study aims to provide accurate and efficient results in skin cancer classification. The results of this study can have a positive impact in increasing the accuracy of early detection of skin cancer, especially by future researchers.
Relevance of e-Health Needs and Usage in Indonesia Chairul, Yasrizal; Aziz, Faruq; Hadianti, Sri
Journal Medical Informatics Technology Volume 1 No. 4, December 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i4.20

Abstract

The eHealth application can be used for healthcare, supervision, literature, education, and research. It is a cost-efficient and secure application based on information and communication technology for the health and medical fields. The use of Information and Communication Technology (ICT) as an infrastructure or medium that connects hospitals and health centers using the eHealth electronic health application is the key problem facing the implementation of eHealth on a worldwide scale. eHealth is an ICT-based application for the healthcare industry and one of the Action Plans of the World Summit on the Information Society (WSIS) Geneva 2003. The goal of using the eHealth app is to increase patient access, medical process efficiency, effectiveness, and process quality. This covers the administration of medical services provided by hospitals, clinics, health centers, medical professionals (including therapists and doctors), laboratories, pharmacies, and insurance
Tubercolusis Segmentation Based on X-ray Images Priyono, Eko; Fatah, Teddy Al; Ma’mun, Sukrul; Aziz, Faruq
Journal Medical Informatics Technology Volume 1 No. 4, December 2023
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v1i4.22

Abstract

Tuberculosis or TB is an infectious disease caused by the bacteria Mycobacterium tubercolusis. This disease usually attacks the lungs, but can also affect other organs such as the kidneys, bones and brain. TB is highly contagious, and can spread through the air when someone who is infected coughs or sneezes. Risk factors that can increase a person's chances of developing TB include a weak immune system, such as people with AIDS, diabetes, or people taking immunosuppressant drugs. And people who live or work in environments with high rates of TB transmission are also at risk of infection. Symptoms of TB are usually a cough that lasts more than three weeks, unexplained weight loss, fever, night sweats and persistent fatigue. In more severe cases, TB can cause coughing up blood, chest pain and difficulty breathing. One of the examination tools that can be used to detect TB disease is x-rays. Which produces X-Rays to help and confirm the diagnosis of TB disease, to see the chest part of the body which is used as medical record documentation. In X-ray photos, random dark and light spots of noise are often found which are caused by several factors. Based on the facts above, image segmentation is an important task for doctors in diagnosing disease. Automatic detection or segmentation of lung images from chest x-ray images is the initial stage of the diagnosis process. This research aims to implement a segmentation method to determine edge detection in clearer images using several segmentation methods, namely the Canny Edge Detection method, Sobel reading chest x-ray results for tuberculosis. And canny edge detection with segmented RGB image (otsu's thresholding) produces the highest value, namely 230,466.0 pixels and a lesion volume of 14,818.625 mm3.
Optimising Cataract Detection in Fundus Images through EfficientNet-Based Classification Ibrahim, Andi; Sabara, Edi; Dirsam, Winarlin; Aziz, Faruq
Journal Medical Informatics Technology Volume 2 No. 1, March 2024
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v2i1.25

Abstract

Turbidity of the lens of the eyeball that causes blindness or loss of vision is known as a cataract. By diagnosing the causes and symptoms of cataracts, early detection helps patients in prevention and treatment. The purpose of the research was to classify the image of the fundus into two classes: normal and cataract. The study also looked at how the optimizers for stochastic gradient descent, adaptive moment estimation, root mean square propagation, adaptive gradient algorithm, adaptive delta, and Nesterov-accelerated adaptive moment estimation stacked up against each other. We used the EfficientNet architecture in CNN and preprocessed the normal fundus and cataract fundus images by dividing each into training data (N = 80) and validation data (N = 20) from the Kaggle repository. We added test data from the normal fondus image (N =20) to see the accuracy of the results. We get 100% accuracy of training data, 87% and 77% validation data, and 100% and 95% test data.
Identification of Potato Plant Pests Using the Convolutional Neural Network VGG16 Method Hadianti, Sri; Aziz, Faruq; Nur Sulistyowati, Daning; Riana, Dwiza; Saputra, Ridwan; Kurniawantoro
Journal Medical Informatics Technology Volume 2 No. 2, June 2024
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v2i2.37

Abstract

Pests are one of the main challenges in potato cultivation that can significantly reduce crop yields. Therefore, quick and accurate pest identification is crucial for effective pest control. This research aims to develop a pest identification system for potato plants using the Convolutional Neural Network (CNN) method with the VGG16 architecture. The dataset used consists of images of pests commonly found on potato plants. After the labeling process, these images were used to train the CNN VGG16 model. The research results show that the CNN VGG16 method can identify types of pests with an accuracy rate of 73%. The results serve as a reference to help farmers and agricultural practitioners detect the presence of pests earlier and take the necessary actions to reduce crop losses.