Abstract
The knowledge of dependency of a particular factor on another is a very important aspect in the healthcare field. If we have a rough idea about the effect a prescribed drug has on the cure of a disease or sufficient information about certain symptoms of a disease being linked to each other, we can make an informed decision about its treatment over a period of time. This paper proposes a method which makes use of a special kind of recurrent neural network (RNN) known as long short term memory network (LSTM) to make predictions for time series data. Genetic algorithms are also incorporated to identify the most important concepts affecting a patient over that period of time. The output of the LSTM network is in the form of binary strings and is utilized to generate a fuzzy cognitive map (FCM) for the same and a novel method is proposed to find the values of the interdependencies between various concepts, an approach which can be applied in clinical decision support systems. This method makes use of the weight matrices obtained after training the neural network. It is shown to be an improvement over the previous work done in this domain. The proposed method was tested with various clinical datasets and results were obtained for the same.
Similar content being viewed by others
References
Cai M, Liu J (2016) Maxout neurons for deep convolutional and LSTM neural networks in speech recognition. Speech Commun 77:53–64. https://doi.org/10.1016/j.specom.2015.12.003
Chen L, He Y, Fan L (2017) Let the robot tell: describe car image with natural language via LSTM. Pattern Recogn Lett 98:75–82. https://doi.org/10.1016/j.patrec.2017.09.007
Chougrad H, Zouaki H, Alheyane O (2018) Deep convolutional neural networks for breast cancer screening. Comput Methods Programs Biomed 157:19–30. https://doi.org/10.1016/j.cmpb.2018.01.011
Chowanda A, Chowanda AD (2017) Recurrent neural network to deep learn conversation in Indonesian. Proc Comput Sci 116:579–586. https://doi.org/10.1016/j.procs.2017.10.078
Ding W, Lin CT, Chen S, Zhang X, Hu B (2018) Multiagent-consensus-MapReduce-based attribute reduction using co-evolutionary quantum PSO for big data applications. Neurocomputing 272:136–153. https://doi.org/10.1016/j.neucom.2017.06.059
Froelich W, Wakuliczdeja A (2010) Medical diagnosis support by the application of associational cognitive maps. Control Cybern 39:439–456
Froelich W, Papageorgiou EI, Samarinas M, Skriapas K (2012) Application of evolutionary fuzzy cognitive maps to the long-term prediction of prostate cancer. Appl Soft Comput 12(12):3810–3817. https://doi.org/10.1016/j.asoc.2012.02.005
Furfaro R, Fink W, Kargel JS (2012) Autonomous real-time landing site selection for Venus and Titan using evolutionary fuzzy cognitive maps. Appl Soft Comput 12(12):3825–3839. https://doi.org/10.1016/j.asoc.2012.01.014
Giabbanelli PJ, Torsney-Weir T, Mago VK (2012) A fuzzy cognitive map of the psychosocial determinants of obesity. Appl Soft Comput 12(12):3711–3724. https://doi.org/10.1016/j.asoc.2012.02.006
Glykas M (2010) Fuzzy cognitive maps: advances in theory, methodologies, tools and applications. In: Studies in fuzziness and soft computing, vol 247. Springer, Berlin
He X, Shi B, Bai X, Xia GS, Zhang Z, Dong W (2017) Image caption generation with part of speech guidance. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2017.10.018 (in press)
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Kyriakarakos G, Dounis AI, Arvanitis KG, Papadakis G (2012) A fuzzy cognitive maps–petri nets energy management system for autonomous polygeneration microgrids. Appl Soft Comput 12(12):3785–3797. https://doi.org/10.1016/j.asoc.2012.01.024
Li F, Zhang M, Tian B, Chen B, Fu G, Ji D (2017) Recognizing irregular entities in biomedical text via deep neural networks. Pattern Recogn Lett 105:105–113. https://doi.org/10.1016/j.patrec.2017.06.009
Luan XY, Li ZP, Liu TZ (2016) A novel attribute reduction algorithm based on rough set and improved artificial fish swarm algorithm. Neurocomputing 174:522–529. https://doi.org/10.1016/j.neucom.2015.06.090
Papageorgiou EI, Markinos AT, Gemtos TA (2010) Soft computing technique of fuzzy cognitive maps to connect yield defining parameters with yield in cotton crop production in central Greece as a basis for a decision support system for precision agriculture application. In: Fuzzy cognitive maps. Springer, Berlin, pp 325–362
Qing X, Niu Y (2018) Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy 148:461–468. https://doi.org/10.1016/j.energy.2018.01.177
Son HH (2017) Toward a proposed framework for mood recognition using LSTM recurrent neuron network. Proc Comput Sci 109:1028–1034. https://doi.org/10.1016/j.procs.2017.05.378
Stach W, Kurgan LA, Pedrycz W (2008) Numerical and linguistic prediction of time series with the use of fuzzy cognitive maps. IEEE Trans Fuzzy Syst 16(1):61–72
Tepper JA, Shertil MS, Powell HM (2016) On the importance of sluggish state memory for learning long term dependency. Knowl Based Syst 96:104–114. https://doi.org/10.1016/j.knosys.2015.12.024
Thakur S, Dharavath R (2018) Artificial neural network based prediction of malaria abundances using big data: a knowledge capturing approach. Clin Epidemiol Glob Health. https://doi.org/10.1016/j.cegh.2018.03.001 (in press)
Unanue IJ, Borzeshi EZ, Piccardi M (2017) Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition. J Biomed Inform 76:102–109. https://doi.org/10.1016/j.jbi.2017.11.007
Wang Y, Wang H (2017) Multilingual convolutional, long short-term memory, deep neural networks for low resource speech recognition. Proc Comput Sci 107:842–847. https://doi.org/10.1016/j.procs.2017.03.179
Xia W, Zhu W, Liao B, Chen M, Cai L, Huang L (2018) Novel architecture for long short-term memory used in question classification. Neurocomputing 299:20–31. https://doi.org/10.1016/j.neucom.2018.03.020
Yang J, Kim J (2018) An accident diagnosis algorithm using long short-term memory. Nucl Eng Technol 50(4):582–588. https://doi.org/10.1016/j.net.2018.03.010
Zhao A, Qi L, Dong J, Yu H (2018) Dual channel LSTM based multi-feature extraction in gait for diagnosis of neurodegenerative diseases. Knowl Based Syst 145:91–97. https://doi.org/10.1016/j.knosys.2018.01.004
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Duneja, A., Puyalnithi, T., Vankadara, M.V. et al. Analysis of inter-concept dependencies in disease diagnostic cognitive maps using recurrent neural network and genetic algorithms in time series clinical data for targeted treatment. J Ambient Intell Human Comput 10, 3915–3923 (2019). https://doi.org/10.1007/s12652-018-1116-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-1116-5