Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

Keynote webinar | Spotlight on medication adherence

LIVE: Thursday 27th June 2024, 18:00-19:30 (CEST)
Join our expert panel to discover why you need to understand the drivers of non-adherence in your patients, and how you can optimize medication adherence in your clinics to drastically improve patient outcomes.
ADVANCED SEARCH
Log in
Top
Journal of Medical Systems
Published in: Journal of Medical Systems 5/2019

01-05-2019 | Heart Failure | Mobile & Wireless Health

RETRACTED ARTICLE: LSTM Model for Prediction of Heart Failure in Big Data

Authors: G. Maragatham, Shobana Devi

Published in: Journal of Medical Systems | Issue 5/2019

Login to get access

Abstract

The combination of big data and deep learning is a world-shattering technology that can make a great impact on any industry if used in a proper way. With the availability of large volume of health care datasets and progressions in deep learning techniques, systems are now well equipped in diagnosing many health problems. Utilizing the intensity of substantial historical information in electronic health record (EHR), we built up, a conventional predictive temporal model utilizing recurrent neural systems (RNN) like LSTM and connected to longitudinal time stepped EHR. Experience records were contribution to RNN to anticipate the analysis and prescription classes for a resulting visit during heart disappointment (e.g. diagnosis codes, drug codes or method codes). In this paper, we also investigated whether use of deep learning to model temporal relations among events in electronic health records (EHRs) would enhance the model performance in predicting initial diagnosis of heart failure (HF) compared to some of the traditional methods that disregard temporality. By examining these time stamped EHRs, we could recognize the associations between various diagnosis occasions and finally predicate when a patient is being analyzed for a disease. In any case, it is hard to access the current EHR data straightforwardly, since almost all data are sparse and not standardized. Along these lines, we proposed a robust model for prediction of heart failure. The fundamental commitment of this paper is to predict the failure of heart by means of a neural network model based on patient’s electronic medicinal information. In order to, demonstrate the diagnosis events and prediction of heart failure, we used the medical concept vectors and the essential standards of a long short-term memory (LSTM) deep network model. The proposed LSTM model uses SiLU and tanh as activation function in the hidden layers and Softmax in output layer in the network. Bridgeout is used as a regularization technique for weight optimization throughout the network. Assessments subject to the real-time data exhibit the favorable effectiveness and feasibility of recommended model in the risk of heart failure prediction. The results showed improved accuracy in heart failure detection and the model performance is compared using the existing deep learning models. Enhanced prior detection could expose novel chances for deferring or anticipating movement to analysis of heart failure and diminish cost.
Literature
1.
Huang, H. et al., Uric acid and risk of heart failure: A systematic review and meta-analysis. Eur. J. Heart Fail. 16(1):15–24, 2014.CrossRef
2.
Ford, I. et al., ``Top ten risk factors for morbidity and mortality in patients with chronic systolic heart failure and elevated heart rate: The SHIFT risk model. Int. J. Cardiol. 184:163–169, 2015.CrossRef
3.
Choi, E., Schuetz, A., Stewart, W. F., and Sun, J., ``Using recurrent neural network models for early detection of heart failure onset. J. Amer. Med.Inform. Assoc. 24(2):361–370, 2016.CrossRef
4.
Hripcsak, G., and Albers, D. J., ``Next-generation phenotyping of electronic health records. J. Amer. Med. Inform. Assoc. 20(1):117–121, 2012.CrossRef
5.
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M., Time Series Analysis: Forecasting and Control. Hoboken: Wiley, 2015.
6.
Bianchi, F. M., De Santis, E., Rizzi, A., and Sadeghian, A., ``Short-term electric load forecasting using echo state networks and PCA decomposition. IEEE Access 3:1931–1943, 2015.CrossRef
7.
Pati, J., Kumar, B., Manjhi, D., and Shukla, K. K., ``A comparison among ARIMA, BP-NN, and MOGA-NN for software clone evolution prediction. IEEE Access 5:11841–11851, 2017.CrossRef
8.
Su, Y.-T., Lu, Y., Chen, M., and Liu, A.-A., Spatiotemporal joint mitosis detection using CNN-LSTM network in time-lapse phase contrast microscopy images. IEEE Access 5:18033–18041, 2017.CrossRef
9.
Zhu, G., Zhang, L., Shen, P., and Song, J., ``Multimodal gesture recognition using 3-D convolution and convolutional LSTM. IEEE Access 5:4517–4524, 2017.CrossRef
10.
Roger, V. L., Weston, S. A., Redfield, M. M. et al., Trends in heart failure incidence and survival in a community-based population. JAMA. 292(3):344–350, 2004.CrossRef
11.
Murphy, S. L., Xu, J., and Kochanek, K. D., Deaths: final data for 2010. Natl Vital Stat Rep. 61(4):1–117, 2010.
12.
Arnold, J., Yusuf, S., Young, J. et al., Prevention of heart failure in patients in the Heart Outcomes Prevention Evaluation (HOPE) study. Circulation. 107(9):1284–1290, 2003.CrossRef
13.
Sciarretta, S., Palano, F., Tocci, G., Baldini, R., and Volpe, M., Antihypertensive treatment and development of heart failure in hypertension: a Bayesian network meta-analysis of studies in patients with hypertension and high cardiovascular risk. Arch. Intern. Med. 171(5):384–394, 2011.PubMed
14.
Wang, C.-H., Weisel, R., Liu, P., Fedak, P., and Verma, S., Glitazones and heart failure critical appraisal for the clinician. Circulation. 107(10):1350–1354, 2003.CrossRef
15.
Wang Y, Ng K, Byrd R, et al., Early detection of heart failure with varying prediction windows by structured and unstructured data in electronic health records. In IEEE Engineering in Medicine and Biology Society. 2530–2533, 2015.
16.
Sun J, Hu J, Luo D, et al., Combining knowledge and data driven insights for identifying risk factors using electronic health records. In American Medical Informatics Association. 901–910, 2012.
17.
Wu, J., Roy, J., and Stewart, W., Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Med. Care 48(6):S106–S113, 2010.CrossRef
18.
Karpathy A, and Li, F., Deep visual-semantic alignments for generating image descriptions. Computer Vision and Pattern Recognition (CVPR), pp. 3128–3137. Boston, 2015.
19.
Cho K, Van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Doha, 2014.
20.
Hinton, G., Osindero, S., and Teh, Y.-W., A fast learning algorithm for deep belief nets. Neural Comput. 18(7):1527–1554, 2006.CrossRef
21.
Bengio, Y., Learning deep architectures for AI. Foundations Trends Machine Learning. 2(1):1–127, 2009.CrossRef
22.
Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS), pp. 1106–1114. Lake Tahoe, 2012.
23.
Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. In International Conference on Machine learning (ICML), pp. 1096–1103. Helsinki, 2008.
24.
Le Q, Ranzato M, Monga R, et al. Building high-level features using large scale unsupervised learning. In International Conference on Machine Learning (ICML), Edinburgh, 2012.
25.
Lee, H., Pham, P., Largman, Y., and Ng, A., Unsupervised feature learning for audioclassification using convolutional deep belief networks. In Advances in Neural Information Processing Systems (NIPS), pp. 1096–1104.Vancouver, 2009.
26.
Hinton, G., Deng, L., Yu, D. et al., Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. Signal Process Mag. 29(6):82–97, 2012.CrossRef
27.
Mikolov, T., Chen, K., Corrado, G., and Dean, J., Efficient estimation of word representations in vector space. In arXiv preprint arXiv:1301.3781. 2013.
28.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J., Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems (NIPS), pp. 3111–3119. Lake Tahoe, 2013.
29.
Socher R, Pennington J, Huang E, Ng A, Manning C. Semi-supervised recursive autoencoders for predicting sentiment distributions. In Empirical Methods in Natural Language Processing (EMNLP), pp. 151–161. Edinburgh, 2011.
30.
Hochreiter, S., and Schmidhuber, J., Long short-term memory. Neural Comput. 9(8):1735–1780, 1997.CrossRef
31.
Grosicki, E., El Abed, H., ICDAR 2009 handwriting recognition competition. In International Conference on Document Analysis and Recognition, pp. 1398–1402. Barcelona, 2009.
32.
Sak, H., Senior, A., and Beaufays, F., Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In International Speech Communication Association, pp. 338–342. Singapore, 2014.
33.
Zaremba, W., Sutskever, I., and Vinyals, O., Recurrent neural network regularization. In arXiv preprint arXiv:1409.2329, 2014.
34.
Luong, M.-T., Sutskever, I., Le, Q., Vinyals, O., Zaremba, W., Addressing the rare word problem in neural machine translation. In Association for Computational Linguistics (ACL), pp. 11–19. Beijing, 2015.
35.
Jozefowicz, R., Zaremba, W., and Sutskever, I., An empirical exploration of recurrent network architectures. In International Conference on Machine Learning (ICML), pp. 2342–2350. Lille, 2015.
36.
Lasko, T., Denny, J., and Levy, M., Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data. PLoS One 8(6):e66341, 2013.CrossRef
37.
Che Z, Kale D, Li W, Bahadori M, Liu Y. Deep computational phenotyping. In Knowledge Discovery and Data Mining (KDD), pp. 507–516. Sydney, 2015.
38.
Hammerla N, Fisher J, Andras P, Rochester L, Walker R, Plotz T. PD disease state assessment in naturalistic environments using deep learning. In AAAI, pp. 1742–1748. Austin, 2015.
39.
Lipton, Z., Kale, D., Elkan, C., Wetzell, R., Learning to diagnose with LSTM recurrent neural networks. In arXiv preprint arXiv: 1511.03677, 2016.
40.
Minarro-Gimenez, J., Marin-Alonso, O., and Samwald, M., Exploring the application of deep learning techniques on medical text corpora. Stud Health Technol Inform. 205:584–588, 2013.
41.
De Vine, L., Zuccon, G., Koopman, B., Sitbon, L., and Bruza, P., Medical semantic similarity with a neural language model. In International Conference on Information and Knowledge Management (CIKM), pp. 1819–1822. Shanghai, 2014.
42.
Choi, Y., Chiu, C., and Sontag, D., Learning low-dimensional representations of medical concepts. San Francisco: American Medical Informatics Association on Clinical Research Informatics, 2016.
43.
Choi, E., Schuetz, A., Stewart, W., Sun, J., Medical concept representation learning from electronic health records and its application on heart failure prediction. In arXiv preprint arXiv:1602.03686, 2016.
44.
Tangri, N., Stevens, L., Griffith, J. et al., A predictive model for progression of chronic kidney disease to kidney failure. JAMA. 305(15):1553–1559, 2011.CrossRef
45.
Sukkar, R., Katz, E., Zhang, Y., Raunig, D., and Wyman, B., Disease progression modeling using hidden Markov models. Engineering in Medicine and Biology Society.:2845–2848, 2012, 2012.
46.
Zhou, J., Liu, J., Narayan, V., and Ye, J., Modeling disease progression via multi-task learning. NeuroImage. 78:233–248, 2013.CrossRef
47.
Liu, Y.-Y., Ishikawa, H., Chen, M., Wollstein, G., Schuman, J., Rehg, J., Longitudinal modeling of glaucoma progression using 2-dimensional continuous-time hidden Markov model. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 444–451. Nagoya, 2013.
48.
Schulam, P., Saria, S., A framework for individualizing predictions of disease trajectories by exploiting multi-resolution structure. In Advances in Neural Information Processing Systems (NIPS), pp. 748–756. Montreal, 2015.
49.
Wang, X., Sontag, D., and Wang, F., Unsupervised learning of disease progression models. In Knowledge Discovery and Data Mining (KDD), pp. 85–94. New York, 2014.
50.
Choi, E., Du, N., Chen, R., Song, L., and Sun, J., Constructing disease network and temporal progression model via context-sensitive Hawkes process. In International Conference on Data Mining (ICDM), pp. 721–726. Atlantic City, 2015.
51.
Zhang, G. P., ``Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175, 2003.CrossRef
52.
Jenkins, G. M., and Alavi, A. S., Some aspects of modelling and forecasting multivariate time series. J. Time Ser. Anal. 2(1):1–47, 1981.CrossRef
53.
Brown, R. G., ``Exponential smoothing for predicting demand. Oper. Res. 5(1):145–145, 1957.CrossRef
54.
Box, G. E. P., Jenkins, G. M., and Reinsel, G. C., Linear Nonstationary Models Time Series Analysis. 4th edition. Hoboken: Wiley, 1976, 93–136.
55.
Gers, F. A., and Schmidhuber, J., Recurrent nets that time and count. Proc. IEEE-INNS-ENNS Int. Joint Conf. Neural Netw. (IJCNN) 3:189–194, 2000.CrossRef
56.
57.
Vijayakrishnan, R., Steinhubl, S., Ng, K. et al., Prevalence of heart failure signs and symptoms in a large primary care population identified through the use of text and data mining of the electronic health record. J. Card. Fail. 20(7):459–464, 2014.CrossRef
58.
Gurwitz, J., Magid, D., Smith, D. et al., Contemporary prevalence and correlates of incident heart failure with preserved ejection fraction. Am. J. Med. 126(5):393–400, 2013.CrossRef
59.
60.
61.
62.
Zeiler, M., ADADELTA: An adaptive learning rate method. In arXiv preprint arXiv:1212.5701, 2012.
63.
Karpathy, A., Johnson, J., and Li, F., Visualizing and understanding recurrent networks. In arXiv preprint arXiv:1506.02078, 2015.
Metadata
Title
RETRACTED ARTICLE: LSTM Model for Prediction of Heart Failure in Big Data
Authors
G. Maragatham
Shobana Devi
Publication date
01-05-2019
Publisher
Springer US
Keyword
Heart Failure
Published in
Journal of Medical Systems / Issue 5/2019
Print ISSN: 0148-5598
Electronic ISSN: 1573-689X
DOI
https://doi.org/10.1007/s10916-019-1243-3

Other articles of this Issue 5/2019

Journal of Medical Systems 5/2019 Go to the issue

Image & Signal Processing

Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears

Image & Signal Processing

Glioma Tumor Grade Identification Using Artificial Intelligent Techniques

Mobile & Wireless Health

Construction of medical equipment-based doctor health monitoring system

Education & Training

Design of a Functional Splint for Rehabilitation of Achilles Tendon Injury Using Advanced Manufacturing (AM) Techniques. Implementation Study

Systems-Level Quality Improvement

Evaluation of eSie VVI Technology on Left Ventricular Systolic Function Changes in Uremic Patients Undergoing Dialysis

Image & Signal Processing

A Novel Technique for Multi Biometric Cryptosystem Using Fuzzy Vault