Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

2020 | OriginalPaper | Chapter

Challenges and Limitations in Clustering Blood Donor Hemoglobin Trajectories

Authors : Marieke Vinkenoog, Mart Janssen, Matthijs van Leeuwen

Published in: Advanced Analytics and Learning on Temporal Data

Publisher: Springer International Publishing

share
SHARE

Abstract

In order to prevent iron deficiency, Sanquin—the national blood bank in the Netherlands—measures a blood donor’s hemoglobin (Hb) level before each donation and only allows a donor to donate blood if their Hb is above a certain threshold. In around 6.5% of blood bank visits by women, the donor’s Hb is too low and the donor is deferred from donation. For visits by men, this occurs in 3.0% of cases. To reduce the deferral rate and keep donors healthy and motivated, we would like to identify donors that are at risk of having a low Hb level. To this end we have historical Hb trajectories at our disposal, i.e., time series consisting of Hb measurements recorded for individual donors.
As a first step towards our long-term goal, in this paper we investigate the use of time series clustering. Unfortunately, existing methods have limitations that make them suboptimal for our data. In particular, Hb trajectories are of unequal length and have measurements at irregular intervals. We therefore experiment with two different data representations. That is, we apply a direct clustering method using dynamic time warping, and a trend clustering method using model-based feature extraction. In both cases the clustering algorithm used is k-means.
Both approaches result in distinct clusters that are well-balanced in size. The clusters obtained using direct clustering have a smaller mean within-cluster distance, but those obtained using the model-based features show more interesting trends. Neither approach results in ideal clusters though. We therefore conclude with an elaborate discussion on challenges and limitations that we hope to address in the near future.
Footnotes
1
Whole blood is standard blood; it is also possible to donate specific components.
 
Literature
1.
go back to reference Aghabozorgi, S., Shirkhorshidi, A.S., Wah, T.Y.: Time-series clustering-a decade review. Inf. Syst. 53, 16–38 (2015) CrossRef Aghabozorgi, S., Shirkhorshidi, A.S., Wah, T.Y.: Time-series clustering-a decade review. Inf. Syst. 53, 16–38 (2015) CrossRef
2.
go back to reference Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, pp. 359–370. AAAI Press (1994) Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, pp. 359–370. AAAI Press (1994)
3.
go back to reference Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 6085 (2018) CrossRef Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 6085 (2018) CrossRef
4.
go back to reference Eckner, A.: Algorithms for unevenly-spaced time series: moving averages and other rolling operators. In: Working Paper (2012) Eckner, A.: Algorithms for unevenly-spaced time series: moving averages and other rolling operators. In: Working Paper (2012)
5.
go back to reference Finch, C.A., Cook, J., Labbe, R., Culala, M.: Effect of blood donation on iron stores as evaluated by serum ferritin. Blood 50(3), 441–447 (1977) CrossRef Finch, C.A., Cook, J., Labbe, R., Culala, M.: Effect of blood donation on iron stores as evaluated by serum ferritin. Blood 50(3), 441–447 (1977) CrossRef
6.
go back to reference Gropper, S.S., Smith, J.L.: Advanced Nutrition and Human Metabolism. Cengage Learning, Boston (2012) Gropper, S.S., Smith, J.L.: Advanced Nutrition and Human Metabolism. Cengage Learning, Boston (2012)
7.
go back to reference Hawkins, W., Speck, E., Leonard, V.G.: Variation of the hemoglobin level with age and sex. Blood 9(10), 999–1007 (1954) CrossRef Hawkins, W., Speck, E., Leonard, V.G.: Variation of the hemoglobin level with age and sex. Blood 9(10), 999–1007 (1954) CrossRef
8.
go back to reference Liao, T.W.: Clustering of time series data-a survey. Pattern Recogn. 38(11), 1857–1874 (2005) CrossRef Liao, T.W.: Clustering of time series data-a survey. Pattern Recogn. 38(11), 1857–1874 (2005) CrossRef
10.
go back to reference Neil, D., Pfeiffer, M., Liu, S.C.: Phased LSTM: accelerating recurrent network training for long or event-based sequences. In: Advances in Neural Information Processing Systems, pp. 3882–3890 (2016) Neil, D., Pfeiffer, M., Liu, S.C.: Phased LSTM: accelerating recurrent network training for long or event-based sequences. In: Advances in Neural Information Processing Systems, pp. 3882–3890 (2016)
11.
go back to reference Rani, S., Sikka, G.: Recent techniques of clustering of time series data: a survey. Int. J. Comput. Appl. 52(15), 1–9 (2012) Rani, S., Sikka, G.: Recent techniques of clustering of time series data: a survey. Int. J. Comput. Appl. 52(15), 1–9 (2012)
12.
go back to reference Sak, H., Senior, A.W., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: INTERSPEECH (2014) Sak, H., Senior, A.W., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: INTERSPEECH (2014)
13.
go back to reference Zhu, Y., et al.: What to do next: modeling user behaviors by time-LSTM. In: IJCAI, pp. 3602–3608 (2017) Zhu, Y., et al.: What to do next: modeling user behaviors by time-LSTM. In: IJCAI, pp. 3602–3608 (2017)
Metadata
Title
Challenges and Limitations in Clustering Blood Donor Hemoglobin Trajectories
Authors
Marieke Vinkenoog
Mart Janssen
Matthijs van Leeuwen
Copyright Year
2020
DOI
https://doi.org/10.1007/978-3-030-39098-3_6

Premium Partner