article · Medicine in Novel Technology and Devices
Anaemia is a widespread public health issue that primarily affects children and pregnant women. Standard clinical diagnosis requires invasive blood extraction to measure haemoglobin levels, which can be costly and slow. Non-invasive alternatives offer a rapid, cost-effective screening method. A machine learning system was developed to detect anaemia through pallor analysis of conjunctiva photographs. Using a public dataset of 710 eye conjunctiva images taken under controlled lighting conditions, the system integrates Convolutional Neural Networks, Logistic Regression, and Gaussian Blur algorithms. The resulting software features a FastAPI backend server linked to a React Native mobile application interface. The integrated smartphone application analyses conjunctiva images to detect anaemia in roughly 50 seconds. On average, the diagnostic model achieves 90 percent sensitivity, 95 percent specificity, and an overall accuracy of 92.50 percent.
Anaemia is a major global health condition that conventionally demands invasive blood draws and expensive laboratory equipment. A non-invasive smartphone tool capable of delivering accurate evaluations in under a minute could provide an accessible, pain-free alternative for screening vulnerable groups such as children and pregnant women, reducing both diagnostic costs and waiting times.
The system represents an applied and tested prototype embedded into a functioning smartphone application via a React Native frontend and FastAPI server. It is aimed at clinical or field screening of patients, particularly pregnant women and children. Practical deployment would rely on capturing suitable conjunctiva images, which currently requires lighting control methods, indicating that further field validation may be necessary before full market entry.
AI-generated from the published abstract. Always read the original work before citing.
Anemia is one of the public health issues that affect children and pregnant women globally. Anemia occurs when the level of red blood cells within the body is reduced. Detecting anemia requires expert blood draw for clinical analysis of hemoglobin quantity. Although this standard method is accurate, it is costive and consumes enough time, unlike the non-invasive approach which is cost-effective and takes less time. This study focused on pallor analysis and used images of the conjunctiva of the eyes to detect anemia using machine learning techniques. This study used a publicly available dataset of 710 images of the conjunctiva of the eyes acquired with a unique tool that eliminates any interference from ambient light. We combined Convolutional Neural Networks, Logistic Regression, and Gaussian Blur algorithm to develop a conjunctiva detection model and an anemia detection model which runs on a Fast API server connected to a frontend mobile app built with React Native. The developed model was embedded into a smartphone application that can detect anemia by capturing and processing a patient's conjunctiva with a sensitivity of 90%, a specificity of 95%, and an accuracy of 92.50% on average performance in about 50 s.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.medntd.2023.100237
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
