Frequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
IJCATR Volume 13 Issue 12
DOCTOR’S COMPANION: A Support Vector Machine Image Classifier to Enhance Decision Making
Daniel Ugoh, Ike Mgbeafulike
10.7753/IJCATR1312.1003
keywords : ailing, SVM, RESNET50, companion
An ailing child depends on the parents to detect that the child is not feeling well through observations and a doctor (pediatrician) to know exactly what the problem is and administer medication for such child to get well in the shortest possible time. It has been observed, that the number of doctors in hospitals are not enough to manage the number of patients that need medical attention. These doctors can at some point be overwhelmed by the number of cases they handle on daily basis and therefore require some assistance. The assistance would reduce the work load on the doctor and help the doctor to make accurate diagnosis as the wrong diagnosis could be very disastrous. This work used support vector machine, a machine learning technique to classify X-ray images to enable the doctor make better decisions in administering medications to the patient as wrong diagnosis leads to wrong medications which might lead to death eventually. This work employed object oriented and analysis design methodology in order to model software objects after real world objects. The dataset used for model training was chest X-ray dataset from Kaggle. 70% of the data was used for training while 30% of the data was used for testing. RESNET 50 was used for feature extraction while tensorflow were used as framework for model learning development and computer vision library respectively. The performance metrics used for this work are accuracy, precision, recall and F1. The result is a doctor’s companion that that has a high accuracy of 97% which will help doctor to make better decisions in image analysis.
@artical{d13122024ijcatr13121003,
Title = "DOCTOR’S COMPANION: A Support Vector Machine Image Classifier to Enhance Decision Making",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "13",
Issue ="12",
Pages ="14 - 18",
Year = "2024",
Authors ="Daniel Ugoh, Ike Mgbeafulike"}
This paper highlights the importance of using machine learning in the healthcare industry.
This paper understands the efficiency of using the RESNET family for feature extraction.
The efficiency of using support vector machine for image classification was also confirmed.
Data needs to be pre-processed to avoid biasedness.