Fusion of clinical data: A case study to predict the type of treatment of bone fractures

Haq, Anam; Wilk, Szymon; Abelló, Alberto

doi:10.2478/amcs-2019-0004

Abstract

A prominent characteristic of clinical data is their heterogeneity—such data include structured examination records and laboratory results, unstructured clinical notes, raw and tagged images, and genomic data. This heterogeneity poses a formidable challenge while constructing diagnostic and therapeutic decision models that are currently based on single modalities and are not able to use data in different formats and structures. This limitation may be addressed using data fusion methods. In this paper, we describe a case study where we aimed at developing data fusion models that resulted in various therapeutic decision models for predicting the type of treatment (surgical vs. non-surgical) for patients with bone fractures. We considered six different approaches to integrate clinical data: one fusion model based on combination of data (COD) and five models based on combination of interpretation (COI). Experimental results showed that the decision model constructed following COI fusion models is more accurate than decision models employing COD. Moreover, statistical analysis using the one-way ANOVA test revealed that there were two groups of constructed decision models, each containing the set of three different models. The results highlighted that the behavior of models within a group can be similar, although it may vary between different groups.

References

Al-Ayyoub, M. and Al-Zghool, D. (2014). Determining the type of long bone fractures in X-ray images, WSEAS Transactions on Information Science and Applications10(8): 261–270.
Search in Google Scholar Back to article
Brzezinski, J., Kosiedowski, M., Mazurek, C., Slowinski, K., Slowinski, R., Stroinski, M. and Weglarz, J. (2013). Towards telemedical centers: Digitization of inter-professional communication in healthcare, in M. Cruz-Cunha et al. (Eds.), Handbook of Research on ICTs and Management Systems for Improving Efficiency in Healthcare and Social Care, IGI Global, Hershey, PA, pp. 805–829.10.4018/978-1-4666-3990-4.ch042
Search in Google Scholar Back to article
Castanedo, F. (2013). A review of data fusion techniques, The Scientific World Journal2013: 704504, DOI: 10.1155/2013/704504.10.1155/2013/704504382633624288502
Search in Google Scholar Back to article
Cha, Y.-H., Ha, Y.-C., Yoo, J.-I., Min, Y.-S., Lee, Y.-K. and Koo, K.-H. (2017). Effect of causes of surgical delay on early and late mortality in patients with proximal hip fracture, Archives of Orthopaedic and Trauma Surgery137(5): 625–630.10.1007/s00402-017-2674-228321571
Search in Google Scholar Back to article
de Bruijne, M. (2016). Machine learning approaches in medical image analysis: From detection to diagnosis, Medical Image Analysis33: 94–97, DOI: 10.106/j.media.2016.06.032.10.1016/j.media.2016.06.032
Search in Google Scholar Back to article
Dittman, D.J., Khoshgoftaar, T.M. and Napolitano, A. (2014). Selecting the appropriate data sampling approach for imbalanced and high-dimensional bioinformatics datasets, IEEE 14th International Conference on Bioinformatics and Bioengineering, BIBE 2014, Boca Raton, FL, USA, pp. 304–310.10.1109/BIBE.2014.61
Search in Google Scholar Back to article
Douali, N. and Jaulent, M. (2012). Genomic and personalized medicine decision support system, 2012 IEEE International Conference on Complex Systems (ICCS), Agadir, Morocco, pp. 1–4.10.1109/ICoCS.2012.6458611
Search in Google Scholar Back to article
Edward, C.P. and Hepzibah, H. (2015). A robust approach for detection of the type of fracture from X-ray images, International Journal of Advanced Research in Computer and Communication Engineering4(3): 479–482.
Search in Google Scholar Back to article
Ferri, C., Hernndez-Orallo, J. and Modroiu, R. (2009). An experimental comparison of performance measures for classification, Pattern Recognition Letters30(1): 27–38.10.1016/j.patrec.2008.08.010
Search in Google Scholar Back to article
Giddins, G.E.B. (2015). The non-operative management of hand fractures, Journal of Hand Surgery (European Volume)40(1): 33–41.10.1177/175319341454817025217094
Search in Google Scholar Back to article
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P. and Witten, I.H. (2009). The WEKA data mining software: An update, ACM SIGKDD Explorations Newsletter11(1): 10–18.10.1145/1656274.1656278
Search in Google Scholar Back to article
Haq, A. and Wilk, S. (2017). Fusion of clinical data: A case study to predict the type of treatment of bone fractures, in M. Kirikova et al. (Eds.), New Trends in Databases and Information Systems, Springer, Cham, pp. 294–301.10.1007/978-3-319-67162-8_29
Search in Google Scholar Back to article
Hossain, M., Neelapala, V. and Andrew, J.G. (2008). Results of non-operative treatment following hip fracture compared to surgical intervention, Injury40(4): 418–421.10.1016/j.injury.2008.10.00119233352
Search in Google Scholar Back to article
Jesneck, J., Nolte, L., Baker, J., Floyd, C. and Lo, J. (2006). Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis, Medical Physics33(8): 2945–2954, DOI: 10.1118/1.2208934.10.1118/1.2208934256900316964873
Search in Google Scholar Back to article
Khatik, I. (2017). A study of various bone fracture detection techniques, International Journal of Engineering and Computer Science6(5): 21418–21423.10.18535/ijecs/v6i5.38
Search in Google Scholar Back to article
Kourou, K., Exarchos, T.P., Exarchos, K.P., Karamouzis, M.V. and Fotiadis, D.I. (2015). Machine learning applications in cancer prognosis and prediction, Computational and Structural Biotechnology Journal13: 8–17.10.1016/j.csbj.2014.11.005434843725750696
Search in Google Scholar Back to article
Koziarski, M. and Woźniak, M. (2017). CCR: A combined cleaning and resampling algorithm for imbalanced data classification, International Journal of Applied Mathematics and Computing Sciences27(4): 727–736, DOI: 10.1515/amcs-2017-0050.10.1515/amcs-2017-0050
Open DOI Search in Google Scholar Back to article
Kuhn, M. and Johnson, K. (2013). Applied Predictive Modeling, Springer, New York, NY.10.1007/978-1-4614-6849-3
Search in Google Scholar Back to article
Lahat, D., Adali, T. and Jutten, C. (2015). Multimodal data fusion: An overview of methods, challenges, and prospects, Proceedings of the IEEE103(9): 1449–1477.10.1109/JPROC.2015.2460697
Search in Google Scholar Back to article
Lanckriet, G., Deng, M., Cristianini, N., Jordan, M. and Noble, W. (2004). Kernel-based data fusion and its application to protein function prediction in yeast, Pacific Symposium on Biocomputing (PSB 2004), Big Island, HI, USA, pp. 300–311.10.1142/9789812704856_0029
Search in Google Scholar Back to article
Lee, G., Doyle, S., Monaco, J., Madabhushi, A., Feldman, M.D., Master, S.R. and Tomaszewski, J.E. (2009). A knowledge representation framework for integration, classification of multi-scale imaging and non-imaging data: Preliminary results in predicting prostate cancer recurrence by fusing mass spectrometry and histology, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, pp. 77–80.10.1109/ISBI.2009.5192987
Search in Google Scholar Back to article
Mitchell, H.B. (2014). Data Fusion: Concepts and Ideas, Springer, Berlin/Heidelberg.
Search in Google Scholar Back to article
Ponti, M. (2011). Combining classifiers: From the creation of ensembles to the decision fusion, 2011 24th SIBGRAPI Conference on Graphics, Patterns, and Images Tutorials, Maceio, Alagoas, Brazil, pp. 1–10.10.1109/SIBGRAPI-T.2011.9
Search in Google Scholar Back to article
Rohlfing, T., Pfefferbaum, A., Sullivan, E. and Maurer, C. (2005). Information fusion in biomedical image analysis: Combination of data vs combination of interpretations, 19th International Conference on Information Processing in Medical Imaging (IPMI’05), Glenwood Springs, CO, USA, pp. 150–161.10.1007/11505730_13
Search in Google Scholar Back to article
Salzberg, S.L. and Fayyad, U. (1997). On comparing classifiers: Pitfalls to avoid and a recommended approach, Data Mining and Knowledge Discovery1(3): 317–328, DOI: 10.1023/A:1009752403260.10.1023/A:1009752403260
Open DOI Search in Google Scholar Back to article
Sim, L.L.W., Ban, K.H.K., Tan, T.W., Sethi, S.K. and Loh, T.P. (2017). Development of a clinical decision support system for diabetes care: A pilot study, PLOS ONE12(2): 1–15, DOI:10.1371/journal.pone.0173021.10.1371/journal.pone.0173021532556528235017
Open DOI Search in Google Scholar Back to article
Tiwari, P., Viswanath, S., Lee, G. and Madabhushi, A. (2011). Multi-modal data fusion schemes for integrated classification of imaging and non-imaging biomedical data, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Chicago, IL, USA, pp. 165–168.10.1109/ISBI.2011.5872379
Search in Google Scholar Back to article
Viswanath, S.E., Tiwari, P., Lee, G. and Madabhushi, A. (2017). Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: Concepts, workflow, and use-cases, BMC Medical Imaging17(1): 2.10.1186/s12880-016-0172-6521766528056889
Search in Google Scholar Back to article
Wilk, S., Stefanowski, J., Wojciechowski, S., Farion, K.J. and Michalowski, W. (2016). Application of preprocessing methods to imbalanced clinical data: An experimental study, in E. Pietka et al. (Eds.), Information Techmologies in Medicine, Springer, Berlin/Heidelberg, pp. 503–515.10.1007/978-3-319-39796-2_41
Search in Google Scholar Back to article
Yuksel, S.E., Wilson, J.N. and Gader, P.D. (2012). Twenty years of mixture of experts, IEEE Transactions on Neural Networks and Learning Systems23(8): 1177–1193.10.1109/TNNLS.2012.220029924807516
Search in Google Scholar Back to article
Zorluoglu, G. and Agaoglu, M. (2015). Diagnosis of breast cancer using ensemble of data mining classification methods, International Journal of Bioinformatics and Biomedical Engineering1(3): 318–322.
Search in Google Scholar Back to article

Fusion of clinical data: A case study to predict the type of treatment of bone fractures

Abstract

Paradigm

My account