Prediction by Sigmoid Multilayer Perceptron Artificial Neural Network Function and Model Selection for the Risk Factors Most Affected Human Immunodeficiency

Nazeera Sedeeq Kareem Barznji

doi:10.21271/zjhs.29.4.13

المؤلفون

Nazeera Sedeeq Kareem Barznji Department of Statistics and Informatics, College of Administrations and Economics, Salahaddin University-Erbil, Kurdistan Region,Iraq

DOI:

https://doi.org/10.21271/zjhs.29.4.13

الملخص

The Multilayer Perceptron (MLP), a widely recognized type of Artificial Neural Network (ANN), was applied in this study to forecast the risk factors associated with human immunodeficiency conditions. A sample of 500 patients with various diseases was collected from hospitals and laboratories in the Kurdistan region. Each patient’s immune level was tested, and the dataset included one dependent variable, immune testing level (classified as either "good immunity" or "poor immunity"), and six independent variables representing potential risk factors (X1 to X6). Statistical analyses, including parameter estimation and variable importance ranking, revealed that X1: Genetic history had the most significant influence on immunity, followed by X5: Cancer treatments such as radiation therapy, X4: AIDS, X2: Diabetes, X3: Human Immunodeficiency Virus (HIV), and lastly, X6: Certain medications. Model selection criteria such as the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), along with the Likelihood Ratio Test and Chi-square test (p-value = 0.011 < 0.05), a that these risk factors significantly affect immune deficiency outcomes. The results validate the effectiveness of the MLP model in identifying the most influential predictors of immunodeficiency.

المراجع

- Amin, M.Z. and Al, A. (2017). ‘Application of Multilayer Perceptron (MLP) for Data Mining in Healthcare Operations’. International Conference on Biotechnology, University of South Asia, Lahore, Pakistan, 8–9 February, pp. 7–8.

- Block, H.D. (1962) ‘The Perceptron: A Model for Brain Functioning. I’, Reviews of Modern Physics, 34(1), pp. 123–135. doi:10.1103/RevModPhys.34.123.

- Castro Gbêmêmali Hounmenou, G., Gneyou, K.E. and Glèlè Kakaï, R. (2021). ‘A Formalism of the General Mathematical Expression of Multilayer Perceptron Neural Networks’. Preprints, doi:10.20944/preprints202105.0412.v1, pp. 3–9.

- Chan, K.Y., Abu-Salih, B., Qaddoura, R. et al. (2023). ‘Deep neural networks in the cloud: Review, applications, challenges and research directions’. Neurocomputing, pp. 3–18.

- Chinn, I.K. and Orange, J.S. (2019). ‘Immunodeficiency Disorders’. Pediatrics in Review, 40(5), pp. 229–242. doi:10.1542/pir.2017-0308. PMID: 31043442.

- Cybenko, G. (1989). ‘Approximation by superpositions of a sigmoidal function’, Mathematics of Control, Signals, and Systems, 2(4), pp. 303–314.

- D'Agostino, A. (2021). Introduction to neural networks: weights, biases and activation. Available at: https://medium.com/mlearning-ai/submission-suggestions-b51e2b130bfb (Accessed: 17 July 2025).

- Ding, J., Tarokh, V. and Yang, Y. (2018). ‘Model Selection Techniques: An Overview’, IEEE Signal Processing Magazine, 35(6), pp. 16–34. arXiv:1810.09583.

- Fernandez, J. (2023). Overview of Immunodeficiency Disorders. MD, PhD, Cleveland Clinic Lerner College of Medicine at Case Western Reserve University, p. 1.

- Goodfellow, I., Bengio, Y. and Courville, A. (2016). ‘Softmax Units for Multinoulli Output Distributions’. In: Deep Learning. Cambridge, MA: MIT Press, pp. 180–184. ISBN 978-0-26203561-3.

- Han, J. and Morag, C. (1995). ‘The influence of the sigmoid function parameters on the speed of backpropagation learning’. In: Mira, J. and Sandoval, F. (eds.) From Natural to Artificial Neural Computation. Lecture Notes in Computer Science, vol. 930. Berlin: Springer, pp. 195–201. doi:10.1007/3-540-59497-3_175.

- Hornik, K., Stinchcombe, M. and White, H. (1989). ‘Multilayer feedforward networks are universal approximators’, Neural Networks, 2(5), pp. 359–366. doi:10.1016/0893-6080(89)90020-8.

- Inoussah, M., Ngoh, S., Molu, R.J.J., Kenfack, B., Onguene, R., Dzonde Naoussi, S., Tamba, J.G., Bajaj, M. & Tuka, M., 2024. A multilayer perceptron neural network approach for optimizing solar irradiance forecasting in Central Africa with meteorological insights. Scientific Reports, 14, Article number: [if available], DOI: 10.1038/s41598-024-54181-y.

- Notarangelo, L.D., Fischer, A., Geha, R.S., Casanova, J.L. and Chapel, H. (2016). Primary immunodeficiencies: 2009 update. pp. 1099–1105.

- Pac, M. and Bernatowska, E. (2016). ‘Comprehensive activities to increase recognition of primary immunodeficiency and access to immunoglobulin replacement therapy in Poland’, Polish Journal of Medicine, 175(8), pp. 101–109.

- Piramuthu, S., Shaw, M.J. and Gentry, J.A. (1990). ‘M Perceptrons’. CMU-RI-TR-90-29Y, Carnegie Mellon University, March, p. 6.

- Roberts, R.L. (2007). Immunodeficiency. University of California at Los Angeles, p. 1.

- Rodrigo, H.S.S. (2017). Bayesian Artificial Neural Networks in Health and Cybersecurity. University of South Florida. Available at: https://digitalcommons.usf.edu/etd (Accessed: 17 July 2025), pp. 120–132.

- Rosenblatt, F. (1961). Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Washington DC: Spartan Books, p. 4.

- Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986). ‘Learning representations by back-propagating errors’, Nature, 323(6088), pp. 533–536.

- Sejnowski, T.J. (2018). The Deep Learning Revolution. Cambridge, MA: MIT Press, p. 47. ISBN 978-0-262-03803-4.

- Stoica, P. and Selen, Y. (2004). ‘Model-order selection: a review of information criterion rules’, IEEE Signal Processing Magazine, (July), pp. 36–47. doi:10.1109/MSP.2004.1311138.

- Sullivan, K. (2024). Primary immunodeficiency. MD, PhD, Children’s Hospital of Philadelphia, p. 201.

- Vaillant, A.A.J. and Qurie, A. (2023). Immunodeficiency, p. 6.

- White, K. and Black, M. (2018). ‘Vaccine efficacy’, Immunology Today, 32(4), pp. 112–120.

- Yang, Z. and Yang, Z. (2014). Comprehensive Biomedical Physics. Stockholm: Elsevier, p. 1. ISBN 978-0-444-53633-4.

- Ziad A.A. Al Qadi (2021). Artificial neural networks (ANN), pp. 1–18.