Iron deficiency anemia detection using machine learning models: A comparative study of fingernails, palm and conjunctiva of the eye images

Abstract

Anemia is one of the global public health challenges that particularly affect children and pregnant women. A study by WHO indicates that 42% of children below the age of 6 and 40% of pregnant women worldwide are anemic. This affects the world's total population by 33%, due to the cause of iron deficiency. The non‐invasive technique, such as the use of machine learning algorithms is one of the methods used in the diagnosis or detection of clinical diseases, which anemia detection cannot be overlooked in recent days. In this study, a machine learning approach was used to detect iron‐deficiency anemia with the application of Naïve Bayes, CNN, SVM, k‐NN, and decision tree algorithms. This enabled us to compare the conjunctiva of the eyes, the palpable palm, and the color of the fingernail images to justify which of them has a higher accuracy for detecting anemia in children. The method utilized was categorized into three different stages: dataset collection, dataset preprocessing, and model development for anemia detection. The CNN achieved a higher accuracy of 99.12%, while the SVM had the least accuracy of 95.4%. The performance of the models justifies that the non‐invasive approach is an effective mechanism for anemia detection.

Classification and Explanation of Iron Deficiency Anemia from Complete Blood Count Data Using Machine Learning

“…The published ML models for anemia classification all use different data than used here or perform a task other than discriminating IDA. For example, they rely on image data, or they use CBC variables to identify genetic disorders related to hemoglobin [10][11][12][13][14][15][16][17][18][19][20][27][28][29][30]. Since the cause of anemia is multifactorial [4], identifying concurrent iron deficiency is required to guide iron therapy.…”

“…Machine learning (ML) algorithms are increasingly being used in medicine for the classification of diseases, predicting the clinical outcome [10,11]. Indeed, many studies have attempted to diagnose or classify anemia based on blood cell variables [12,13], demographic variables [14,15], images of palm [16], conjunctiva, or fingertips [17][18][19], and sickle cell anemia from images of blood smears [20], but all these studies were to diagnose anemia, rather than IDA specifically. Some studies also reported differential diagnosis of IDA and ß-thalassemia with high accuracy [12,21,22].…”

Artificial Intelligence (AI)-Based Detection of Anaemia Using the Clinical Appearance of the Gingiva

“…Anaemia happens either when the body's red blood cell production declines or the cells' structural integrity is compromised [3]. Anaemia can also appear when the haemoglobin level in the red blood cells drops below the typical threshold as a result of increases in red blood cell oxidation, blood loss, defective cells, or a reduction in the quantity of red blood cells [1].…”

Revolutionizing anemia detection: integrative machine learning models and advanced attention mechanisms

“…The complexities inherent to accurately identifying the diverse causes and variations of anemia are further compounded by challenges in resource-constrained settings [ 8 ]. Although, machine learning (ML) techniques represent a promising avenue towards more efficient, accurate, and accessible detection of anemia [ 9 – 12 ], the integration of these technologies faces hurdles related to data quality, model generalization, and ethical considerations, necessitating a nuanced approach to harness their full potential [ 13 , 14 ].…”

“…Furthermore, ref. [ 9 ] employed palpable palm image datasets from Ghana, utilizing a convolutional neural network (CNN) to achieve an impressive accuracy of 99.12% and F1 score of 99.89%. Another method, developed in ref.…”