Open Access
Issue
Published:
02 May 2024
Acute Complication Prediction and Diagnosis Model CLSTM-BPR: A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking
)
Download citation
9
Views
14
Downloads
0
Crossref
0
WoS
0
Scopus
0
CSCD
Acute complication prediction model is of great importance for the overall reduction of premature death in chronic diseases. The CLSTM-BPR proposed in this paper aims to improve the accuracy, interpretability, and generalizability of the existing disease prediction models. Firstly, through its complex neural network structure, CLSTM-BPR considers both disease commonality and patient characteristics in the prediction process. Secondly, by splicing the time series prediction algorithm and classifier, the judgment basis is given along with the prediction results. Finally, this model introduces the pairwise algorithm Bayesian Personalized Ranking (BPR) into the medical field for the first time, and achieves a good result in the diagnosis of six acute complications. Experiments on the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset show that the average Mean Absolute Error (MAE) of biomarker value prediction of the CLSTM-BPR model is 0.26, and the average accuracy (ACC) of the CLSTM-BPR model for acute complication diagnosis is 92.5%. Comparison experiments and ablation experiments further demonstrate the reliability of CLSTM-BPR in the prediction of acute complication, which is an advancement of current disease prediction tools.
menu
Acute Complication Prediction and Diagnosis Model CLSTM-BPR: A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking
)
Abstract
Acute complication prediction model is of great importance for the overall reduction of premature death in chronic diseases. The CLSTM-BPR proposed in this paper aims to improve the accuracy, interpretability, and generalizability of the existing disease prediction models. Firstly, through its complex neural network structure, CLSTM-BPR considers both disease commonality and patient characteristics in the prediction process. Secondly, by splicing the time series prediction algorithm and classifier, the judgment basis is given along with the prediction results. Finally, this model introduces the pairwise algorithm Bayesian Personalized Ranking (BPR) into the medical field for the first time, and achieves a good result in the diagnosis of six acute complications. Experiments on the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset show that the average Mean Absolute Error (MAE) of biomarker value prediction of the CLSTM-BPR model is 0.26, and the average accuracy (ACC) of the CLSTM-BPR model for acute complication diagnosis is 92.5%. Comparison experiments and ablation experiments further demonstrate the reliability of CLSTM-BPR in the prediction of acute complication, which is an advancement of current disease prediction tools.
References(39)
V.-A. Lioutas, A. S. Beiser, H. J. Aparicio, J. J. Himali, M. H. Selim, J. R. Romero, and S. Seshadri, Assessment of incidence and risk factors of intracerebral hemorrhage among participants in the Framingham heart study between 1948 and 2016, JAMA Neurol., vol. 77, no. 10, p. 1252, 2020.
J. Rashid, S. Batool, J. Kim, M. Wasif Nisar, A. Hussain, S. Juneja, and R. Kushwaha, An augmented artificial intelligence approach for chronic diseases prediction, Front. Public Health, vol. 10, p. 860396, 2022.
K. Li, J. Daniels, C. Liu, P. Herrero, and P. Georgiou, Convolutional recurrent neural networks for glucose prediction, IEEE J. Biomed. Health Inform., vol. 24, no. 2, pp. 603–613, 2020.
K. C. Koo, K. S. Lee, S. Kim, C. Min, G. R. Min, Y. H. Lee, W. K. Han, K. H. Rha, S. J. Hong, S. C. Yang et al., Long short-term memory artificial neural network model for prediction of prostate cancer survival outcomes according to initial treatment strategy: Development of an online decision-making support system, World J. Urol., vol. 38, no. 10, pp. 2469–2476, 2020.
J. J. Lee, J. H. Heo, J. H. Han, B. R. Kim, H. Y. Gwon, and Y. R. Yoon, Prediction of ankle brachial index with photoplethysmography using convolutional long short term memory, J. Med. Biol. Eng., vol. 40, no. 2, pp. 282–291, 2020.
Y. A. Choi, S. J. Park, J. A. Jun, C. S. Pyo, K. H. Cho, H. S. Lee, and J. H. Yu, Deep learning-based stroke disease prediction system using real-time bio signals, Sensors, vol. 21, no. 13, p. 4269, 2021.
S. Dutta, J. K. Mandal, T. H. Kim, and S. K. Bandyopadhyay, Breast cancer prediction using stacked GRU-LSTM-BRNN, Appl. Comput. Syst., vol. 25, no. 2, pp. 163–171, 2020.
S. Mohan, C. Thirumalai, and G. Srivastava, Effective heart disease prediction using hybrid machine learning techniques, IEEE Access, vol. 7, pp. 81542–81554, 2019.
Y. Jin, C. Qin, Y. Huang, W. Zhao, and C. Liu, Multi-domain modeling of atrial fibrillation detection with twin attentional convolutional long short-term memory neural networks, Knowl. Based Syst., vol. 193, p. 105460, 2020.
W. Wang, M. Tong, and M. Yu, Blood glucose prediction with VMD and LSTM optimized by improved particle swarm optimization, IEEE Access, vol. 8, pp. 217908–217916, 2020.
N. A. Othman, M. A. Abdel-Fattah, and A. T. Ali, A hybrid deep learning framework with decision-level fusion for breast cancer survival prediction, Big Data Cogn. Comput., vol. 7, no. 1, p. 50, 2023.
M. Mahmudimanesh, M. Mirzaee, A. Dehghan, and A. Bahrampour, Forecasts of cardiac and respiratory mortality in Tehran, Iran, using ARIMAX and CNN-LSTM models, Environ. Sci. Pollut. Res. Int., vol. 29, no. 19, pp. 28469–28479, 2022.
G. Swapna, R. Vinayakumar, and S. K. P, Diabetes detection using deep learning algorithms, ICT Express, vol. 4, no. 4, pp. 243–246, 2018.
D. de A. Rodrigues, R. F. Ivo, S. C. Satapathy, S. Wang, J. Hemanth, and P. P. R. Filho, A new approach for classification skin lesion based on transfer learning, deep learning, and IoT system, Pattern Recognit. Lett., vol. 136, pp. 8–15, 2020.
T. H. H. Aldhyani, A. S. Alshebami, and M. Y. Alzahrani, Soft clustering for enhancing the diagnosis of chronic diseases over machine learning algorithms, J. Healthc. Eng., vol. 2020, p. 4984967, 2020.
W. Yue, Z. Wang, H. Chen, A. Payne, and X. Liu, Machine learning with applications in breast cancer diagnosis and prognosis, Designs, vol. 2, no. 2, p. 13, 2018.
A. Nithya, A. Appathurai, N. Venkatadri, D. R. Ramji, and C. A. Palagan, Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images, Measurement, vol. 149, p. 106952, 2020.
L. W. Braun, M. A. T. Martins, J. Romanini, P. V. Rados, M. D. Martins, and V. C. Carrard, Continuing education activities improve dentists’ self-efficacy to manage oral mucosal lesions and oral cancer, Eur. J. Dent. Educ., vol. 25, no. 1, pp. 28–34, 2021.
G. Battineni, G. G. Sagaro, N. Chinatalapudi, and F. Amenta, Applications of machine learning predictive models in the chronic disease diagnosis, J. Pers. Med., vol. 10, no. 2, p. 21, 2020.
R. R. Janghel and Y. K. Rathore, Deep convolution neural network based system for early diagnosis of Alzheimer’s disease, IRBM, vol. 42, no. 4, pp. 258–267, 2021.
H. Kanegae, K. Suzuki, K. Fukatani, T. Ito, N. Harada, and K. Kario, Highly precise risk prediction model for new-onset hypertension using artificial intelligence techniques, J. Clin. Hypertens., vol. 22, no. 3, pp. 445–450, 2020.
B. Liu and B. Wang, Pairwise learning for personalized ranking with noisy comparisons, Inf. Sci., vol. 623, pp. 242–257, 2023.
K. Shawwa, E. Ghosh, S. Lanius, E. Schwager, L. Eshelman, and K. B. Kashani, Predicting acute kidney injury in critically ill patients using comorbid conditions utilizing machine learning, Clin. Kidney J., vol. 14, no. 5, pp. 1428–1435, 2021.
W. T. Liu, X. Q. Liu, T. T. Jiang, M. Y. Wang, Y. Huang, Y. L. Huang, F. Y. Jin, Q. Zhao, Q. Y. Wu, B. C. Liu et al., Using a machine learning model to predict the development of acute kidney injury in patients with heart failure, Front. Cardiovasc. Med., vol. 9, p. 911987, 2022.
T. Fan, J. Wang, L. Li, J. Kang, W. Wang, and C. Zhang, Predicting the risk factors of diabetic ketoacidosis-associated acute kidney injury: A machine learning approach using XGBoost, Front. Public Health, vol. 11, p. 1087297, 2023.
C. Peng, F. Yang, L. Li, L. Peng, J. Yu, P. Wang, and Z. Jin, A machine learning approach for the prediction of severe acute kidney injury following traumatic brain injury, Neurocrit. Care, vol. 38, no. 2, pp. 335–344, 2023.
A. Talaei-Khoei, M. Tavana, and J. M. Wilson, A predictive analytics framework for identifying patients at risk of developing multiple medical complications caused by chronic diseases, Artif. Intell. Med., vol. 101, p. 101750, 2019.
M. Zuo, W. Zhang, Q. Xu, and D. Chen, Deep personal multitask prediction of diabetes complication with attentive interactions predicting diabetes complications by multitask-learning, J. Healthc. Eng., vol. 2022, p. 5129125, 2022.
S. Ito, H. Nakashima, T. Yoshii, S. Egawa, K. Sakai, K. Kusano, S. Tsutui, T. Hirai, Y. Matsukura, K. Wada, et al., Deep learning-based prediction model for postoperative complications of cervical posterior longitudinal ligament ossification, Eur. Spine J., vol. 32, no. 11, pp. 3797–3806, 2023.
Publication history
Copyright
Acknowledgements
This work was partly supported by the Social Science Fund of China (No. 19BTQ072).
Rights and permissions
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
FEEDBACK 
TOP