Stephen Afrifa; Peter Appiahene; Tao Zhang; Vijayakumar Varadarajan

Machine Learning Algorithms for Iron Deficiency Anemia Detection in Children Using Palm Images

Full Text (PDF, 998KB), PP.1-15

Views: 0 Downloads: 0

Author(s)

Stephen Afrifa ^1,2,* Peter Appiahene ² Tao Zhang ¹ Vijayakumar Varadarajan ^3,4

1. Department of Information and Communication Engineering, Tianjin University, Tianjin 300072, China

2. Department of Information Technology and Decision Sciences, University of Energy and Natural Resources, Sunyani 00233, Ghana

3. School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia

4. International Divisions, Ajeenkya D. Y. Patil University, Pune 412105, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijeme.2024.01.01

Received: 29 May 2023 / Revised: 1 Aug. 2023 / Accepted: 28 Aug. 2023 / Published: 8 Feb. 2024

Index Terms

Anemia, machine learning, health, artificial intelligence, sustainable development, deep learning

Abstract

Anemia is a common condition among adults, particularly in children and pregnant women. Anemia is defined as a lack of healthy red blood cells or hemoglobin. Early identification of anemia is critical for excellent health and well-being, which contributes to the sustainable development goals (SDGs), notably SDG 3. The intrusive way to detecting anemia has several hurdles, including anxiety and cost, which impedes health development. With the advent of technology, it is critical to create non-invasive techniques to diagnose anemia that can minimize costs while also improving detection efficacy. A distinct non-invasive technique is developed in this study employing machine learning (ML) models. This study's dataset contains 4260 observations of non-anemic (0) and anemic (1) children. To train the dataset, six (6) different ML models were employed: k-Nearest Neighbor (KNN), decision tree (DT), logistic regression (LR), nave bayes (NB), random forest (RF), and kernel-support vector machine (KSVM). The DT and RF models obtained the highest accuracy of 99.92%, followed by the KNN at 98.98%. The ML models used in this study produced substantial results. The models also received high marks on performance evaluation metrics such as accuracy, recall, F1-score, and Area Under the Curve-Receiver Operating Characteristics (AUC-ROC). When compared to the other ML models, the DT and RF had the best precision (1.000), recall (0.9987), F1-score (0.9994), and AUC-ROC (0.9994) ratings. According to the findings, ML models are crucial in the detection of anemia using a non-invasive technique, which is critical for health facilities to boost efficiency and quality healthcare. Various machine learning models were used in this study to detect anemia in children using palm images. Finally, the findings confirm earlier studies on the effectiveness of ML algorithms as a non-invasive means of detecting iron deficiency anemia.

Cite This Paper

Stephen Afrifa, Peter Appiahene, Tao Zhang, Vijayakumar Varadarajan, "Machine Learning Algorithms for Iron Deficiency Anemia Detection in Children Using Palm Images", International Journal of Education and Management Engineering (IJEME), Vol.14, No.1, pp. 1-15, 2024. DOI:10.5815/ijeme.2024.01.01

Reference

[1]G. Dimauro, M. E. Griseta, M. G. Camporeale, F. Clemente, A. Guarini, and R. Maglietta, “An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset,” Artif. Intell. Med., vol. 136, no. August 2022, p. 102477, 2023, doi: 10.1016/j.artmed.2022.102477.
[2]P. Appiahene, E. J. Arthur, S. Korankye, S. Afrifa, J. W. Asare, and E. T. Donkoh, “Detection of anemia using conjunctiva images: A smartphone application approach,” Med. Nov. Technol. Devices, vol. 18, no. February, p. 100237, 2023, doi: 10.1016/j.medntd.2023.100237.
[3]Q. Chen, Y. Zhang, M. Zhang, Z. Li, and J. Liu, “Application of Machine Learning Algorithms to Predict Acute Kidney Injury in Elderly Orthopedic Postoperative Patients,” Clin. Interv. Aging, vol. 17, no. March, pp. 317–330, 2022, doi: 10.2147/CIA.S349978.
[4]A. Chakraborty, S. Mitra, M. Bhattacharjee, D. De, and A. J. Pal, “Determining human-coronavirus protein-protein interaction using machine intelligence,” Med. Nov. Technol. Devices, vol. 18, no. December 2022, p. 100228, 2023, doi: 10.1016/j.medntd.2023.100228.
[5]WHO.int, “Anaemia.” Accessed: Apr. 30, 2023. [Online]. Available: https://www.who.int/health-topics/anaemia#tab=tab_1
[6]E. I. Abd El-Latif and N. E. Khalifa, “A Model based on Deep Learning for COVID-19 X-rays Classification,” Int. J. Image, Graph. Signal Process., vol. 15, no. 1, pp. 36–46, 2023, doi: 10.5815/ijigsp.2023.01.04.
[7]S. E. Wilson et al., “Comprehensive framework for integrated action on the prevention , diagnosis , and management of anemia : An introduction The WHO Interdepartmental Anaemia Working Group : María Barreix 2,” pp. 1–5, 2023, doi: 10.1111/nyas.14999.
[8]A. Kesarwani et al., “Non-invasive anaemia detection by examining palm pallor: A smartphone-based approach,” Biomed. Signal Process. Control, vol. 79, no. July 2022, 2022, doi: 10.1016/j.bspc.2022.104045.
[9]S. Afrifa, V. Varadarajan, P. Appiahene, T. Zhang, and E. A. Domfeh, “Ensemble Machine Learning Techniques for Accurate and Efficient Detection of Botnet Attacks in Connected Computers,” MDPI Eng, pp. 650–664, 2023, doi: https://doi.org/10.3390/eng4010039.
[10]S. Afrifa and V. Varadarajan, “Cyberbullying Detection on Twitter Using Natural Language Processing and Machine Learning Techniques,” Int. J. Innov. Technol. Interdiscip. Sci., vol. 5, no. 4, pp. 1069–1080, 2022, doi: 10.15157/IJITIS.2022.5.4.1069-1080.
[11]A. Mohammed, P. S. B. Podila, R. L. Davis, K. I. Ataga, J. S. Hankins, and R. Kamaleswaran, “Using machine learning to predict early onset acute organ failure in critically ill intensive care unit patients with sickle cell disease: Retrospective study,” J. Med. Internet Res., vol. 22, no. 5, pp. 1–10, 2020, doi: 10.2196/14693.
[12]W. K. Adu, P. Appiahene, and S. Afrifa, “VAR , ARIMAX and ARIMA models for nowcasting unemployment rate in Ghana using Google trends,” J. Electr. Syst. Inf. Technol., pp. 1–16, 2023, doi: 10.1186/s43067-023-00078-1.
[13]S. Afrifa, T. Zhang, P. Appiahene, and V. Vijayakumar, “Mathematical and Machine Learning Models for Groundwater Level Changes : A Systematic Review and Bibliographic Analysis,” Futur. Internet, 2022, doi: https:// doi.org/10.3390/fi14090259.
[14]P. Appiahene, J. W. Asare, E. T. Donkoh, G. Dimauro, and R. Maglietta, “Detection of iron deficiency anemia by medical images: a comparative study of machine learning algorithms,” BioData Min., vol. 16, no. 1, pp. 1–20, 2023, doi: 10.1186/s13040-023-00319-z.
[15]A. Mitani et al., “Detection of anaemia from retinal fundus images via deep learning,” Nat. Biomed. Eng., vol. 4, no. 1, pp. 18–27, 2020, doi: 10.1038/s41551-019-0487-z.
[16]S. KILICARSLAN, M. CELIK, and Ş. SAHIN, “Hybrid models based on genetic algorithm and deep learning algorithms for nutritional Anemia disease classification,” Biomed. Signal Process. Control, vol. 63, no. September 2020, 2021, doi: 10.1016/j.bspc.2020.102231.
[17]L. Alzubaidi, M. A. Fadhel, O. Al‐shamma, J. Zhang, and Y. Duan, “Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis,” Electron., vol. 9, no. 3, 2020, doi: 10.3390/electronics9030427.
[18]F. Alsayegh, M. A. Alkhamis, F. Ali, S. Attur, N. M. Fountain-Jones, and M. Zubaid, “Anemia or other comorbidities? using machine learning to reveal deeper insights into the drivers of acute coronary syndromes in hospital admitted patients,” PLoS One, vol. 17, no. 1 January, pp. 1–15, 2022, doi: 10.1371/journal.pone.0262997.
[19]E. Waisberg, J. Ong, N. Zaman, S. A. Kamran, A. G. Lee, and A. Tavakkoli, “A non-invasive approach to monitor anemia during long-duration spaceflight with retinal fundus images and deep learning,” Life Sci. Sp. Res., vol. 33, no. April, pp. 69–71, 2022, doi: 10.1016/j.lssr.2022.04.004.
[20]P. Appiahene, V. Varadarajan, T. Zhang, and S. Afrifa, “Experiences of sexual minorities on social media : A study of sentiment analysis and machine learning approaches,” J. Auton. Intell., vol. 6, no. 2, pp. 1–15, 2023, doi: 10.32629/jai.v6i2.623.
[21]P. Appiahene, Y. M. Missah, and U. Najim, “Evaluation of information technology impact on bank’s performance: The Ghanaian experience,” Int. J. Eng. Bus. Manag., vol. 11, no. March, 2019, doi: 10.1177/1847979019835337.
[22]B. Jalili, A. Rezaeian, P. Jalili, D. D. Ganji, and Y. Khan, “Squeezing flow of Casson fluid between two circular plates under the impact of solar radiation,” ZAMM Zeitschrift fur Angew. Math. und Mech., no. October 2022, pp. 1–11, 2023, doi: 10.1002/zamm.202200455.
[23]M. A. Junior, P. Appiahene, and O. Appiah, “Forex market forecasting with two ‑ layer stacked Long Short ‑ Term Memory neural network ( LSTM ) and correlation analysis,” J. Electr. Syst. Inf. Technol., vol. 1, pp. 1–24, 2022, doi: 10.1186/s43067-022-00054-1.
[24]S. Roy, “Island Loss for Improving the Classification of Facial Attributes with Transfer Learning on Deep Convolutional Neural Network,” Int. J. Image, Graph. Signal Process., vol. 12, no. 1, pp. 18–29, 2020, doi: 10.5815/ijigsp.2020.01.03.
[25]S. Afrifa, T. Zhang, X. Zhao, P. Appiahene, and M. S. Yaw, “Climate change impact assessment on groundwater level changes: A study of hybrid model techniques,” IET Signal Process., vol. 17, no. April, p. e12227, 2023, doi: 10.1049/sil2.12227.
[26]S. Shastri, “An Efficient Approach for Text-to-Speech Conversion Using Machine Learning and Image Processing Technique,” Int. J. Educ. Manag. Eng., vol. 13, no. 4, pp. 44–49, 2023, doi: 10.5815/ijem.2023.04.05.
[27]R. Hasan and A. S. M. Shafi, “Feature Selection based Breast Cancer Prediction,” Int. J. Image, Graph. Signal Process., vol. 15, no. 2, pp. 13–23, 2023, doi: 10.5815/ijigsp.2023.02.02.
[28]G. Rossin et al., “Artificial Intelligence in Bladder Cancer Diagnosis: Current Applications and Future Perspectives,” BioMedInformatics, vol. 3, no. 1, pp. 104–114, 2023, doi: 10.3390/biomedinformatics3010008.
[29]J. Lötsch and B. Mayer, “A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery,” BioMedInformatics, vol. 2, no. 4, pp. 544–552, 2022, doi: 10.3390/biomedinformatics2040034.
[30]J. Lötsch and A. Ultsch, “Enhancing Explainable Machine Learning by Reconsidering Initially Unselected Items in Feature Selection for Classification,” BioMedInformatics, vol. 2, no. 4, pp. 701–714, 2022, doi: 10.3390/biomedinformatics2040047.
[31]S. C. Christopoulou, “Machine Learning Tools and Platforms in Clinical Trial Outputs to Support Evidence-Based Health Informatics: A Rapid Review of the Literature,” BioMedInformatics, vol. 2, no. 3, pp. 511–527, 2022, doi: 10.3390/biomedinformatics2030032.
[32]P. Appiahene, Y. M. Missah, and U. Najim, “Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks,” Adv. Fuzzy Syst., vol. 2020, 2020, doi: 10.1155/2020/8581202.
[33]F. Zhang, J. Yang, Y. Wang, M. Cai, J. Ouyang, and J. X. Li, “TT@MHA: A machine learning-based webpage tool for discriminating thalassemia trait from microcytic hypochromic anemia patients,” Clin. Chim. Acta, vol. 545, no. February, p. 117368, 2023, doi: 10.1016/j.cca.2023.117368.
[34]J. W. Asare, P. Appiahene, E. T. Donkoh, and G. Dimauro, “Iron Deficiency Anemia Detection using Machine Learning Models : A Comparative Study of Fingernails , Palm and Conjunctiva of the Eye Images .,” Eng. Reports, no. February, pp. 1–28, 2023, doi: 10.1002/eng2.12667.

International Journal of Education and Management Engineering (IJEME)