Performance Analysis of the Ensemble Model in Anaemia Detection from Unmodified Smartphone-Captured Conjunctiva Images

Abstract

Anaemia is a blood-related disorder that is sometimes a harbinger of a much more severe condition like cancer. WHO recommends context-specific diagnosing methods for anaemia in the case of in-feasibility of traditional diagnosing methods, including a haemoglobin colour scale method that is based on the colour of the blood. In this manifesto, we take it one step further and diagnose anaemia using images of lower palpebral conjunctiva captured in consumer-grade cameras. Data that include lower palpebral conjunctiva images, basic details, and haemoglobin values are collected from participants. Pixel parameters of collected conjunctiva images are extracted in various colour spaces and used as input features. An ensemble learning model was developed with K-Nearest Neighbour (KNN), Random Forest and Decision Tree algorithms which showed better classification performance in classifying anaemic and non-anaemic samples. This Ensemble Model-Based Anaemia Classifier (EMBAC) performed well with both training and test sets and produced 90.91% sensitivity, 89.06% specificity, 89.69% accuracy, and area under the Receiver Operating Characteristics(ROC) curve of 0.90 for the unseen test data. EMBAC also outperformed the conventional ensemble algorithms in terms of sensitivity and accuracy. EMBAC will classify the samples more correctly irrespective of the image acquisition device under any lighting conditions without any additional hardware. This research work attempts to lay the foundation for a smartphone application to detect anaemia in real-life conditions which will enable access to a mobile healthcare instrument to diagnose anaemia for the proletariat.

KEYWORDS:

• Artificial intelligence
• computer-aided analysis
• feature extraction
• image processing
• machine learning
• medical diagnostic imaging

Disclosure statement

No potential conflict of interest was reported by the author(s).

DATA AVAILABILITY STATEMENT

The data will be made available to the researchers upon their request and subject to the author’s approval.

Additional information

Notes on contributors

Sivachandar Kasiviswanathan

K Sivachandar holds a bachelor of engineering degree in electronics and communication engineering and a master of engineering degree in embedded systems technologies. He has been in the field of teaching and research for the past 11 years in various engineering colleges. His area of interest includes artificial intelligence, machine learning, digital image processing, signal processing, and embedded systems, and co-authored more than 17 papers in International Journals and Conference Proceedings.

Thulasi Bai Vijayan

V Thulasi Bai has been in the field of teaching and research for the past 8 years. She is an alumna of BITS, Pilani, India and has a doctorate from Sathayabama University, Chennai. She was awarded the DST-Young Scientist Award by the department of science and technology, Govt of India in 2008. In September 2016, she was awarded the IETE-Technomedia Award for Young Women in Engineering by IETE, New Delhi for her significant contribution to engineering and related fields for more than 15 years. She was awarded the IEEE Award for Professional Achievement (2016) from the IEEE Chennai Chapter. Her professional interests include telemedicine, broadband networks, mobile communication, and ITS. She is a member of many professional societies, such as IEEE, ISTE, IsfTeH, TSI, and BES. She has published more than 75 papers in reputed journals and conference proceedings in her career so far. Email: [email protected]

Sheila John

Sheila John has been a consultant ophthalmologist since 1991 at Sankara Nethralaya, Chennai, India. She has worked in collaboration with IIT Madras for original research work on Tissue Characterization of Malignant Melanoma using wave spectral analysis, which was accepted as a poster in the American Academy of Ophthalmology in Atlanta 1995 and Chicago, Illinois 1996 and later published. She has worked in collaboration with the genetic department for research on retinal degeneration and has published peer-reviewed original publications in international Journals. She has been associated with the community ophthalmology services of Sankara Nethralaya since 1992. She is currently the head of the department of teleophthalmology and e-learning and a member of the Indian and American Telemedicine Associations. Her current research interests include the organization and incorporation of electronic medical records with rural eye camps in two states of India. She has been one of the pioneers in the development of the community ophthalmology programme using telemedicine. Email: [email protected]