Ridge regression algorithm based non-invasive anaemia screening using conjunctiva images
- PDF / 1,364,047 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 90 Downloads / 220 Views
ORIGINAL RESEARCH
Ridge regression algorithm based non‑invasive anaemia screening using conjunctiva images Sivachandar Kasiviswanathan1 · Thulasi Bai Vijayan1 · Sheila John2 Received: 20 June 2020 / Accepted: 10 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Anaemia is one of the most prevalent nutritional deficiency disorders in the world that affects 1.62 billion people of all age groups. Its effects are more significant in the preschool-age children and pregnant women. The objective of this work is to develop a noninvasive method for identifying the anaemic status of a person by estimating their haemoglobin (Hb) level. Data collected from 135 participants is used for developing this model in which 80% of them (108 participants) were classified as a training group and the rest (27 participants) were grouped into a test group and their data is used for testing the model that’s based on the Ridge Regression algorithm. Haemoglobin level of a person is predicted from their digital image of the lower palpebral conjunctiva and basic details like age, sex, height, weight and BMI. These predicted values are closer to the values measured by the standard invasive methods and the Pearson correlation coefficients between the measured haemoglobin value and the predicted haemoglobin value are 0.722 and 0.705 for training and testing respectively. This model is trained to perform well with any smartphone in almost any non-ideal lighting condition without the usage of any external hardware. A web application and mobile application both called ’Chromanalysis’ were developed and made available to anyone for screening their anaemic condition with their conjunctiva image and other basic details. This application will help users to assess their haemoglobin levels frequently without undergoing invasive procedures. Keywords Artificial intelligence · Computer-aided analysis · Feature extraction · Image processing · Machine learning · Medical diagnostic imaging
1 Introduction Anaemia is a blood disorder developed by a reduction in the number of circulating erythrocytes or an insufficient quantity of haemoglobin in the blood (WHO 2014). A person with hemoglobin level less than the prescribed threshold level is considered anemic (WHO 2011). Anaemia prevalence among common people is not given the attention it deserves (WHO 2008, 2017). National Family Health Survey * Sivachandar Kasiviswanathan [email protected] Thulasi Bai Vijayan [email protected] Sheila John [email protected] 1
Department of Electronics and Communication Engineering, KCG College of Technology, Chennai 600097, India
Tele-Ophthalmology Department, Sankara Nethralaya, Chennai 600006, India
2
statistics reveal that every second Indian woman is anemic and one in every five maternal deaths is due to anaemia (IIPS and ICF 2017). People with any anaemia related symptoms are predominantly recommended a Standard Invasive Hemoglobin measurement test to determine the amount of hemoglobin in their blood. Since the symptom
Data Loading...
