Medicine in Novel Technology and Devices Application of ensemble models approach in anemia detection using images of the palpable palm

Medicine in Novel Technology and Devices Application of ensemble models approach in anemia detection using images of the palpable palm

ABSTRACT

Anemia is a public health issue with serious ramifications for human health globally. Anemia particularly affects pregnant women and children from six to fifty-nine months old even though every individual is at risk. Anemia occurs when the hemoglobin level is below its normal threshold or when the red blood cells are weakened or destroyed. To discover medical remedies on time, early detection or diagnosis of anemia assist patients to understand their condition.

The invasive approach for anemia detection is costive and time-consuming as compared to the non-invasive approach which is reliable and suitable for developing communities where medical resources and personnel are inadequate. This study uses palpable palm images (dataset) collected from seven hundred ten participants in selected hospitals in Ghana. The images were extracted, segmented and converted into RGB percentile to train, validate and tested the machine learning models. A hybrid model was developed with the application of ensemble learning models using the R programming language on the R Studio platform. Stacking, voting, boosting and bagging ensemble model techniques were used to build the hybrid models, the stacking ensemble model achieved an accuracy of ninety-nine point seven three percent. The study justifies that ensemble models are efficient for medical disease diagnosis or detection such as anemia.

One. Introduction

Technology is influencing the future of healthcare where the use of non-invasive medical techniques aided by technology is preferred in medical diagnostics. Computer-aided disease diagnosis is less expensive, saves time, is more accurate, and reduces the need for additional labor in medical decision-making. Anemia is a worldwide public health issue with serious ramifications for human health. Anemia is one of the most common medical disorders affecting people all over the world, particularly pregnant women and children. Tackling this issue with improved technology would significantly lower the occurrence.

Anemia is a condition in which the hemoglobin level is low. Hemoglobin is an iron-rich protein that gives blood its red colour and is responsible for assisting red blood cells in transporting oxygen from the lungs throughout the body, including vital organs such as the heart, kidneys, and other organs. The World Health Organization discovered that forty-two percent of children below the age of fifty-nine months and forty percent of pregnant females universally are anemic and this affects thirty-three percent of the global population due to iron deficiency.

Anemia is common in people with heart failure, with a frequency ranging from nine percent to sixty-nine point six percent depending on the patient's features. Early detection and diagnosis of anemia would assist persons to understand their condition and discover medical remedies on time. It would also be beneficial to the economy through efficient productivity. A high prevalence of anemia in the community has implications for both mor- talities, and the physical and mental health of people affected.

Other non-invasive methods of identifying anemia include examination of the conjunctiva eyes, the colour of the fingernail, palpable palms, and tongue. The use of images of the palpable palm in the diagnosis of anemia is uncommon, although it is a non-invasive procedure that yields reliable results. The traditional method of detecting anemia with the palm was to examine how pale or yellowish the individual's palm is, and then proceed to the laboratory for a clinical confirmation test to distinguish either one is anemic or not with the use of a blood sample.

The clinical approach for the detection of anemia involves collecting blood samples from patients, either by pricking their fingertips or with a syringe and then performing a laboratory test on these blood samples. The extraction of blood samples is an intravenous procedure that requires sophisticated surgical equipment. Nonetheless, diagnostic procedures are costive, and take enough time and effort, to obtain the findings. This also exposes biomedical scientists and medical laboratory technicians to the danger of blood-borne diseases, and patients may experience pain when blood samples are taken, while frequent blood collection causes discomfort for patients.

The novelty of this study is the combination of several individual or single machine learning algorithms to develop an ensemble model to detect anemia by comparing both ensemble learners and single or individual machine learning models. In addition, most studies used the conjunctiva of the eye images for the detection of anemia, however, this study utilizes medical images of the palpable palm to detect anemia in children for the reason that the human palm is one of the sensitive spots for detecting anemia in children. This is due to the reason that children may be exposed to falling objects or infected with bacteria when the conjunctiva of the eye is exposed for examination during the period of diagnosis.

The main contribution to knowledge by this study is the use of palpable palm images in the detection of anemia since most studies used the conjunctiva of the eye images. Moreover, the size of the dataset (images of the palpable palm from seven hundred ten participants) used for the study is made publicly available on the Mendeley dataset repository which is the highest number of palpable palm medical images used for the detection of anemia.

In this study, we used an ensemble model, that is, stacking, bagging, voting, and boosting to detect anemia in children aged six to fifty-nine months using the palpable palm images. The ensemble model techniques were used to build the hybrid models which are used to diagnose and detect anemia at its preliminary stage since early detection of anemia would help prevent serious complications such as heart problems, pregnancy complications and developmental delays in children.