Document Type : Research Paper


1 Department Industrial of Engineering, School of Engineering, Damghan University, Damghan, Iran.

2 Department of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran.

3 Royan Institute, Royan Stem Cell Technology Company, Tehran, Iran.


The saving banks of “umbilical cord blood stem cells” are considered as strategic health-based institutions in most countries. Due to the limited capacity of cord blood sample storage tanks, the samples should be evaluated according to their quality. So these banks need a method to assess quality. In this paper, first, the effective factors on the quality index of the extracted cord blood from newborn infants are identified using the electronic records and database of Royan’s umbilical cord blood bank. Then by machine learning and various statistical methods such as multilayer perceptron neural networks, radial basis function neural networks, logistic regression, and C4.5 decision tree, the quality value of blood samples and their proper category (for discarding or freezing) are determined. Two different sets of data have been used to evaluate the proposed methods. The results show that the ensemble of radial basis function neural network with k-means clustering model has the best accuracy compared to other methods, which categorizes the samples with 91.5% accuracy for the first data set and 81.6% accuracy for the second one. The results also show that using this method can save about $1 million annually.


Main Subjects

  • Lin, H. (2008). Cell biology of stem cells: an enigma of asymmetry and self-renewal. The journal of cell biology, 180(2), 257-260.
  • Molofsky, A. V., Pardal, R., & Morrison, S. J. (2004). Diverse mechanisms regulate stem cell self-renewal. Current opinion in cell biology16(6), 700-707.
  • Samuel, G. N., Kerridge, I. H., & O’Brien, T. A. (2008). Umbilical cord blood banking: public good or private benefit? Medical journal of Australia188(9), 533-535.
  • Wadlow, R. C., & Porter, D. L. (2002). Umbilical cord blood transplantation: where do we stand? Biology of blood and marrow transplantation8(12), 637-647.
  • Camacho, D. M., Collins, K. M., Powers, R. K., Costello, J. C., & Collins, J. J. (2018). Next-generation machine learning for biological networks. Cell173(7), 1581-1592.
  • Jerby-Arnon, L., Pfetzer, N., Waldman, Y. Y., McGarry, L., James, D., Shanks, E., Seashore-Ludlow, B., Weinstock, A., Geiger, T., & Clemons, P. A. (2014). Predicting cancer-specific vulnerability via data-driven detection of synthetic lethality. Cell158(5), 1199-1209.
  • Malta, T. M., Sokolov, A., Gentles, A. J., Burzykowski, T., Poisson, L., Weinstein, J. N., Kamińska, B., Huelsken, J., Omberg, L., & Gevaert, O. (2018). Machine learning identifies stemness features associated with oncogenic dedifferentiation. Cell173(2), 338-354.
  • Al-Sweedan, S. A., Musalam, L., & Obeidat, B. (2013). Factors predicting the hematopoietic stem cells content of the umbilical cord blood. Transfusion and apheresis science, 48(2), 247-252.
  • Lee, H. R., Park, J. S., Shin, S., Roh, E. Y., Yoon, J. H., Han, K. S., Kim, B. J., Storms, R. W., & Chao, N. J. (2012). Increased numbers of total nucleated and CD34+ cells in blood group O cord blood: an analysis of neonatal innate factors in the Korean population. Transfusion52(1), 76-81.
  • Abdul Wahid, F. S., Nasaruddin, M. Z., Mohd Idris, M. R., Tusimin, M., Tumian, N. R., & Abdullah Mahdy, Z. (2012). Effects of preeclampsia on the yield of hematopoietic stem cells obtained from umbilical cord blood at delivery. Journal of obstetrics and gynaecology research38(3), 490-497.
  • Jan, R. H., Wen, S. H., Shyr, M. H., & Chiang, B. L. (2008). Impact of maternal and neonatal factors on CD34+ cell count, total nucleated cells, and volume of cord blood. Pediatric transplantation12(8), 868-873.
  • Ballen, K. K., Wilson, M., Wuu, J., Ceredona, A., Hsieh, C., Stewart, F., Popovsky, M., & Quesenberry, P. J. (2001). Bigger is better: maternal and neonatal predictors of hematopoietic potential of umbilical cord blood units. Bone marrow transplantation27(1), 7-14.
  • Surbek, D. V., Visca, E., Steinmann, C., Tichelli, A., Schatt, S., Hahn, S., Gratwohl, A., & Holzgreve, W. (2000). Umbilical cord blood collection before placental delivery during cesarean delivery increases cord blood volume and nucleated cell number available for transplantation. American journal of obstetrics & gynecology, 183(1), 218-221.
  • Al-Deghaither, S. Y. (2015). Impact of maternal and neonatal factors on parameters of hematopoietic potential in umbilical cord blood. Saudi medical journal, 36(6), 704-712.
  • Nunes, R. D. & Zandavalli, F. M. (2015). Association between maternal and fetal factors and quality of cord blood as a source of stem cells. Revista brasileira de hematologia e hemoterapia, 37(1), 38-42.
  • Manegold‐Brauer, G., Borner, B., Bucher, C., Hoesli, I., Passweg, J., Girsberger, S., Schoetzau, A., Gisin, S., & Visca, E. (2014). A prenatal prediction model for total nucleated cell count increases the efficacy of umbilical cord blood banking. Transfusion, 54(11), 2946-2952.
  • Donaldson, C., Armitage, W. J., Laundy, V., Barron, C., Buchanan, R., Webster, J., Bradley, B., & Hows, J. (1999). Impact of obstetric factors on cord blood donation for transplantation. British journal of haematology, 106(1), 128-132.
  • Jaime-Pérez, J. C., Monreal-Robles, R., Rodríguez-Romo, L. N., Mancías-Guerra, C., Herrera-Garza, J. L., & Gómez-Almaguer, D. (2011). Evaluation of volume and total nucleated cell count as cord blood selection parameters: a receiver operating characteristic curve modeling approach. American journal of clinical pathology, 136(5), 721-726.
  • Wen, S.-H., Zhao, W.-L., Lin, P.-Y., & Yang, K.-L. (2012). Associations among birth weight, placental weight, gestational period and product quality indicators of umbilical cord blood units. Transfusion and apheresis science, 46(1), 39-45.
  • Cobellis, L., Castaldi, M., Trabucco, E., Imparato, G., Perricone, F., Frega, V., Signoriello, G., & Colacurci, N. (2013). Cord blood unit bankability can be predicted by prenatal sonographic parameters. European journal of obstetrics and gynecology and reproductive biology, 170(2), 391-395.
  • Mancinelli, F., Tamburini, A., Spagnoli, A., Malerba, C., Suppo, G., Lasorella, R., De Fabritiis, P., & Calugi, A. (2006). Optimizing umbilical cord blood collection: impact of obstetric factors versus quality of cord blood units. Transplantation proceedings, 38(4), 1174-1176.
  • Solves, P., Perales, A., Mirabet, V., Blasco, I., Blanquer, A., Planelles, D., Larrea, L., Monleon, J., Carbonell‐Uberos, F., & Angeles Soler, M. (2004). Optimizing donor selection in a cord blood bank. European journal of haematology, 72(2), 107-112.
  • Page, K. M., Mendizabal, A., Betz‐Stablein, B., Wease, S., Shoulars, K., Gentry, T., Prasad, V. K., Sun, J., Carter, S., & Balber, A. E. (2014). Optimizing donor selection for public cord blood banking: influence of maternal, infant, & collection characteristics on cord blood unit quality. Transfusion, 54(2), 340-352.
  • Manegold, G., Meyer‐Monard, S., Tichelli, A., Pauli, D., Holzgreve, W., & Troeger, C. (2008). Cesarean section due to fetal distress increases the number of stem cells in umbilical cord blood. Transfusion, 48(5), 871-876.
  • Wu, S., Xie, G., Wu, J., Chen, J., Lu, Y., Li, Y., Tang, X., & Liao, C. (2015). Influence of maternal, infant, & collection characteristics on high‐quality cord blood units in Guangzhou Cord Blood Bank. Transfusion, 55(9), 2158-2167.
  • Azadeh, A., Saberi, M., Ghaderi, S., Gitiforouz, A., & Ebrahimipour, V. (2008). Improved estimation of electricity demand function by integration of fuzzy system and data mining approach. Energy conversion and management, 49(8), 2165-2177.
  • Ashoori, M., & Tarokh, M. J. (2014). Applying the process mining project methodology for insurance risks reduction. International journal of research in industrial engineering, 3(4), 57-69.
  • Azadeh, A., Asadzadeh, S., & Ghanbari, A. (2010). An adaptive network-based fuzzy inference system for short-term natural gas demand estimation: uncertain and complex environments. Energy policy, 38(3), 1529-1536.
  • Oliveira, A. L. & Meira, S. R. (2006). Detecting novelties in time series through neural networks forecasting with robust confidence intervals. Neurocomputing, 70(1-3), 79-92.
  • Niska, H., Hiltunen, T., Karppinen, A., Ruuskanen, J., & Kolehmainen, M. (2004). Evolving the neural network model for forecasting air pollution time series. Engineering applications of artificial intelligence, 17(2), 159-167.
  • Jaberi, M., Najafi, S. E., Hoseinzadeh Lotfi, F., & Haji molana, M. (2021). A comprehensive hybrid Ndea- Bsc model and a new neural network for predicting organizational performance indicators. Journal of decisions and operations research6(2), 271-287. (In Persian).
  • Hagan, M. T., & Menhaj, M. B. (1994). Training feedforward networks with the Marquardt algorithm. IEEE transactions on neural networks, 5(6), 989-993.
  • Quinlan, J. R. (1993). 5: programs for machine learning. Morgan Kaufmann Publishers
  • Mitchell, T. M. (2007). Machine learning(Vol. 1). New York: McGraw-Hill.
  • Pal, S., & Gauri, S. (2018). Simultaneous optimization of quantitative and ordinal responses using Taguchi method. International journal of research in industrial engineering, 7(2), 184-205.
  • Hosmer Jr, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression(Vol. 398). John Wiley & Sons.
  • Camdeviren, H. A., Yazici, A. C., Akkus, Z., Bugdayci, R., & Sungur, M. A. (2007). Comparison of logistic regression model and classification tree: an application to postpartum depression data. Expert systems with applications, 32(4), 987-994.
  • Nakagawa, R., Watanabe, T., Kawano, Y., Kanai, S., Suzuya, H., Kaneko, M., Watanabe, H., Okamoto, Y., Kuroda, Y., & Nakayama, T. (2004). Analysis of maternal and neonatal factors that influence the nucleated and CD34+ cell yield for cord blood banking. Transfusion, 44(2), 262-267.
  • Wu, J., Liao, C., Chen, J., Xu, Z., Gu, S., Wu, S., Lu, Y., & Xie, G. (2010). Analysis of maternal and neonatal factors associated with hematopoietic reconstruction potential in umbilical cord blood units. Zhongguo shi yan xue ye xue za zhi, 18(6), 1535-1541.
  • Urciuoli, P., Passeri, S., Ceccarelli, F., Luchetti, B., Paolicchi, A., Lapi, S., Nocchi, F., Lamanna, R., Iorio, M., & Vanacore, R. (2010). Pre-birth selection of umbilical cord blood donors. Blood transfusion, 8(1), 36-43.
  • Coldwell, K. E., Lee, S. J., Kean, J., Khoo, C. P., Tsaknakis, G., Smythe, J., & Watt, S. M. (2011). Effects of obstetric factors and storage temperatures on the yield of endothelial colony forming cells from umbilical cord blood. Angiogenesis, 14(3), 381-392.
  • Keersmaekers, C. L., Mason, B. A., Keersmaekers, J., Ponzini, M., & Mlynarek, R. A. (2014). Factors affecting umbilical cord blood stem cell suitability for transplantation in an in utero collection program. Transfusion, 54(3), 545-549.
  • Abdelrazik, A. M., El Said, M. N., Abdelaziz, H. E. M., Badran, H. M., & Elal, E. Y. A. A. (2015). The impact of fetal and maternal physiologic factors on umbilical cord blood quality as a source of stem cells in Egyptian population. Transfusion, 55(12), 2882-2889.