Anemia Detection Using Machine Learning and Deep Learning - A Systematic Literature Review

Computer Science & Engineering

Anemia is a crucial global public health issue with women and children have high risk of contraction. Anemia is caused due to scarceness of Red Blood Cells also known as RBCs in the body. Diagnosis of Anemia has traditionally been through invasive means by means of drawing blood from the body. Invasive measures cause pain to the body and also not easily accessible to the masses. This study aims to review various Machine learning and deep learning techniques that can be employed for the detection of anemia in a non-invasive manner. Studies of various literature and research papers published on the subject detection of anemia using machine and deep learning were carried out. Non-invasive techniques based on Machine Learning and Deep Learning play a pivotal role in the early detection and treatment of anemia in an efficient and cost-effective way.Using convolutional neural networks (CNN), the proposed model effectively eliminates relevant features from different blood samples. Preprocessed datasets, including blood smears and microscopy images, enable training and validation. The model is highly effective in identifying abnormal blood signatures associated with anemia, helping to make early and accurate diagnosis. Our findings demonstrate the potential of deep learning as an important tool in diagnosing type 2 diabetes, providing better results and saving time compared to other diagnostic methods. The research helps advance clinical image analysis and highlights the importance of artificial intelligence in improving diagnosis.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.