Prediction of Demand for Red Blood Cells Using Artificial Intelligence Methods

Abstract

Blood is a vital product with limited resources, available only from volunteers. For this reason, the blood components to be sent from the blood bank to the transfusion centers (hospitals) should be accurately predicted. There are many variables that affect the demand prediction. In this study, fifteen different qualitative and quantitative variables were determined. Artificial intelligence (AI) methods are used because the prediction has nonlinear, complex and uncertain relationships and thus it is also difficult to mathematically express on relationship in between input and output variables. AI methods have the feature of predicting the information that is not given or that may occur in the future by learning the past data. In the study, AI methods such as Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Deep Learning (DL) were applied to blood bank providing blood supply to public and private hospitals operating in four provinces. The data obtained from the prediction results of AI methods were compared with performance criteria (MAPE, MSE, MAE RMSE and R2) and values of overprediction, underprediction, minimum and maximum deviation. The weekly average over predictions are calculated as 9.69, 5.29, 8.45, and 15.65 and weekly average underpredictions as 17.57, 3.03, 3.94, and 14.69 for DT, SVM, ANN, and DL methods, respectively. SVM method was determined as giving the best prediction values. Therefore, it is envisaged that the blood component demand prediction can be calculated using the SVM method.

Keywords

• Demand prediction
• decision tree
• support vector machine
• artificial neural network
• deep learning

References

1. J.L. Carson, B.J. Grossman, S. Kleinman, A.T. Tinmouth, M.B. Marques, M.K. Fung, T. Gernsheimer, J.B. Holcomb, L.J. Kaplan, L.M. Katz, N. Peterson, G. Ramsey, S.V. Rao, J.D. Roback, A. Shander, A.A.R. Tobian, “Clinical practice guideline from the AABB: Red blood cell transfusion thresholds and storage,” Ann. Intern. Med., vol. 157, pp. 49-58, 2012.
2. H. F Soares., E.F. Arruda, L. Bahiense, D.Gartner, L.A. Filho, “Optimisation and Control of The Supply of Blood Bags in Hemotherapic Centres via Markov Decision Process with Discounted Arrival Rate, ” Artif. Intell. Med., vol. 104, no. 101791, 2020.
3. S.M. Fortsch, E.A. Khapalova, “Reducing uncertainty in demand for blood,” Oper. Res. Health Care., vol. 9, pp. 16-28, 2016.
4. S. Dharmaraja, S. Narang, V. Jain, “A mathematical model for supply chain management of blood banks in India,” OPSEARCH, vol. 57, pp. 541-552, 2020.
5. S. Moon, “Predicting the Performance of Forecasting Strategies for Naval Spare Parts Demand: A Machine Learning Approach,” Int. J. Manag. Sci. Eng. Manag., vol. 19, no. 1, pp. 1-10, 2013.
6. B.M. Brentan, E. Luvizotto, M. Herrera, J. Izquierdo, R. Pérez-García, “Hybrid regression model for near real-time urban water demand forecasting,” J. Comput. Appl. Math., vol. 309, pp. 532-541, 2017.
7. S. Mouatadid, J. Adamowski, “Using extreme learning machines for short-term urban water demand forecasting,” Urban Water J., vol. 14, no. 6, pp. 630-638, 2017.
8. M.S. Al-Musaylh, R.C. Deo, J.F. Adamowski, Y. Li, “Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia,” Adv. Eng. Inform., vol. 35, pp. 1-16, 2018.

9. W-H. Ho, C-S. Chang, “Genetic-algorithm-based artificial neural network modeling for platelet transfusion requirements on acute myeloblastic leukemia patients,” Expert Syst. Appl., vol. 38, no. 5, pp. 6319-6323, 2011.
10. S. Haghani, M. Sedehi, S. Kheiri, “Artificial Neural Network to Modeling Zero-inflated Count Data: Application to Predicting Number of Return to Blood Donation,” J. Health Sci. Res., vol. 17, no. 3, 2017.
11. F. Firouzi Jahantigh, B. Fanoodi, S. Khosravi, “A demand forcasting model for the blood platelet supply chain with Artificial Neural Network approach and ARIMA models,” Sci J Iran Blood Transfus Organ., vol. 14, no. 4, pp. 335-345, 2018.
12. S. Singaravel, J. Suykens, P. Geyer, “Deep-learning neural-network architectures and methods: Using component based models in building-design energy prediction,” Adv. Eng. Inform., vol. 38, no. 2018, pp. 81-90, 2018.
13. J. Bedi, D. Toshniwal, “Deep learning framework to forecast electricity demand,” Appl. Energy., vol. 238, no. 2019, pp. 1312–1326, 2019.
14. R. Law, G. Li, D.K.C. Fong, H. Xin, “Tourism demand forecasting: A deep learning approach,” Ann. Tour. Res., vol. 75, no. 2019, pp. 410–423, 2019.
15. D. Pi, AW. Shih, L. Sham, D. Zamar, K. Roland, M. Hudoba, “Establishing performance management objectives and measurements of red blood cell inventory planning in a large tertiary care hospital in British Columbia, Canada,” ISBT Sci. Ser., vol. 14, pp. 226–238, 2019.
16. L. Cohen, L. Manion, K. Morrison, Research Methods in Education (6th Edition), London: Routledge. 2000.
17. L. Breiman, J. Friedman, C.J. Stone, R.A. Olshen, Classification and Regression Trees, Chapman& Hall CRC Presss. 1984.
18. A.J. Smola, B. Schölkopf, “A tutorial on support vector regression,” Stat. Comput., vol. 14, no. 3, pp. 199–222, 2004.
19. D. Basak, S. Pal, D.C. Patranabis, “Support vector regression,” Neural Information Processing – Letters and Reviews, vol. 11, no. 10, pp. 203–224, 2007.
20. B.S. Khehra, A.P.S. Pharwaha, “Classification of Clustered Microcalcifications using MLFFBP-ANN and SVM,” Egypt. Inform. J., vol. 17, no. 1, pp. 11-20, 2016.
21. V.Vapnik, S. Golowich, A. Smola, “Support vector method for function approximation, regression estimation, and signal processing,” Adv. Neural Inf. Process Syst., vol. 281–287, 1996.
22. D. Meyer, F. Leisch, K. Hornik, “The support vector machines under test,” Neurocomputing, vol. 55, pp. 169–186, 2003.
23. E.A. Zanaty. “Support Vector Machines (SVMs) versus Multilayer Perception (MLP) in data classification,” Egypt. Inform. J., vol. 13, no. 3, pp. 177-183, 2012.
24. C. Cortes, V. Vapnik, “Support-Vector Networks,” Machine Learning, vol. 20, pp. 273-297, 1995.
25. Y. LeCun, Y. Bengio, G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
26. S.B. Golas, T. Shibahara, S. Agboola, H. Otaki, J. Sato, T. Nakae, T. Hisamitsu, G. Kojima, J. Felsted, S. Kakarmath, J. Kvedar, K. Jethwani, “A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data,” BMC Med. Inform. Decis. Mak., vol. 18, no. 1, pp. 44, 2018.
27. E. Öztemel, Yapay Sinir Ağları. 4. Baskı, Papatya Bilim Üniversite Yayıncılığı, İstanbul. 2016.
28. M.J. Madić, M.R. Radovanović, “Optimal selection of ANN training and architectural parameters using Taguchi method: A case study,” FME Trans., vol. 39, pp. 79-86, 2011.
29. M. Timothy, Practical Neural Network Recipes in C++. Academic Press, pp. 174-175, 1993.