Email Alert | RSS

Journal of Peking University(Health Sciences) ›› 2019, Vol. 51 ›› Issue (3): 602-608. doi: 10.19723/j.issn.1671-167X.2019.03.034

Previous Articles    

Application of recurrent neural network in prognosis of peritoneal dialysis

Wen TANG1△(),Jun-yi GAO2,Xin-yu MA2,3,Chao-he ZHANG2,Lian-tao MA2,3,Ya-sha WANG2,4△()   

  • Received:2019-03-18 Online:2019-05-22 Published:2019-06-26
  • Supported by:
    Supported by the Fundamental Research Funds for the Central Universities: Peking University Medicine Seed Fund for Interdisciplinary Research (BMU20160584)

RICH HTML

   

PDF (PC)

Abstract: Objective: Deep learning models, including recurrent neural network (RNN) and gated recurrent unit (GRU), were used to construct the clinical prognostic prediction models for peritoneal dialysis (PD) patients based on routine clinical data. The performance of the RNN and GRU were compared with logistic regression (LR), which is commonly used in medical researches. The possible underlining clinical implications based on the result from the GRU model were also investigated.Methods: We used the clinical data from the PD center of Peking University Third Hospital as the data source. Both the baseline data at the beginning of dialysis, and the follow-up and prognostic data of the patients were used by the RNN and GRU prediction models. The hyper-parameters were tuned based on the 10-fold cross-validation. The risk prediction performance of each model was evaluated via area under the receiver ope-ration characteristic curve (AUROC), recall rate and F1-score on the testset. Results: A total of 656 patients with the 261 occurrences of death were included in the experiment. The total number of all diagnostic records were 13 091. The results on the testset showed that the AUROC of the LR model, RNN mo-del, and GRU model was 0.701 4, 0.786 0, and 0.814 7, respectively. The predictive performances of the GRU and RNN models were significantly better than that of the LR model. The performances of the GRU and RNN models assessed by recall rate and F1-score were also significantly better than that of the LR model, in which the GRU model reached the best performance. In addition, the recall rates were different among different causes of death or by different prediction time windows.Conclusion: The recurrent neural network model, especially the GRU model, is more effective in predicting PD patients’ prognosis as compared with the LR model. This new model may be helpful for clinicians to provide timely intervention, thus improving the quality of care of PD.

Key words: Peritoneal dialysis, Prognosis, Mortality risk prediction, Recurrent neural network, Gated recurrent unit

CLC Number: 

  • R459.51

Table 1

Clinical features of peritoneal dialysis"

Categories of Features
Dynamic features
Blood test
Blood routine: WBC counts, Hb
ALB
Renal function: urea, Cr, uric acid
Electrolyte: K, Na, Cl, CO2CP
Others: Glu, hs-CRP, Ca, P, iPTH
Complications: peritonitis, catheter-related infections, other infections, cardiovascular disease, diabetic foot, cerebrovascular disease, cancer,
hernia, fracture, upper respiratory tract infection, other complications
Nutrition & physical tests: weight, systolic pressure, diastolic pressure
Static baseline features
Demographic features: age, gender
Underlying diseases: baseline comorbidities
Physical tests: height

Figure 1

Definition of health risk labels"

Figure 2

Recurrent neural network"

Table 2

Statistics of peritoneal dialysis clinical features in the dataset"

Feature Mean Std Median
Cl/(mmol/L) 98.01 4.84 98.00
CO2CP 27.39 3.64 27.40
Blood uric acid/(mmol/L) 391.61 148.41 380.00
WBC counts/(×109/L) 8.30 55.51 7.49
Hb/(g/L) 114.77 16.83 115.00
Urea/(mmol/L) 19.96 5.46 19.60
Ca/(mmol/L) 2.40 0.37 2.38
K/(mmol/L) 4.32 0.72 4.24
Na/(mmol/L) 138.54 3.88 139.00
Cr/(μmol/L) 857.34 283.70 839.00
P/(mmol/L) 1.60 0.43 1.56
ALB/(g/L) 37.65 4.44 37.90
iPTH/(pg/mL) 214.63 237.93 141.60
hs-CRP/(mg/L) 8.68 15.92 3.34
Glu/(mmol/L) 6.67 3.05 5.70

Table 3

Statistics of peritoneal dialysis complications in the dataset"

Disease Percentage of diagnosed patients
Peritonitis 60.82%
Upper respiratory tract infection 26.98%
Catheter-related infections 9.76%
Other infections 22.10%
Cardiovascular disease 11.74%
Cerebrovascular disease 2.59%
Diabetic foot 3.05%
Cancer 4.12%
Hernia 2.13%
Fracture 1.37%
Other complications 19.21%

Figure 3

Gated recurrent unit, which is used to perform classification based on time series data"

Table 4

Statistics information of patients"

Statistics Mean Median Maximum Minimum Std
Age of the patients 58.55 60.70 97.45 16.79 15.81
Number of visits 19.95 16 69 1 13.53
Number of visits that are one year before the death 2 0 29 0 2.95

Figure 4

Data distribution of age and visiting frequency in the dataset"

Table 5

Average performance of each prediction model in testset"

Metric LR RNN GRU
AUROC 70.14% 78.60% 81.47%
F1-score 79.32% 86.84% 88.01%
Recall 26.13% 39.42% 48.19%

Figure 5

ROC of prediction models AUROC, area under the receiver operation characteristic curve."

Figure 6

Recall of different death reasons at different prediction windows PDAP, peritoneal dialysis associated peritonitis; PVD, peripheral vascular disease; GI, gastrointestinal."

[1] Li KT, Chow KM , Van de Luijtgaarden MW, et al. Changes in the worldwide epidemiology of peritoneal dialysis[J]. Nat Rev Nephrol, 2017,13(2):90-103.
doi: 10.1038/nrneph.2016.181
[2] Lee C, Luo Z, Ngiam KY , et al. Big healthcare data analytics: Challenges and applications[M] //Handbook of large-scale distributed computing in smart healthcare. German: Springer, 2017: 11-41.
[3] Schalkoff RJ . Artificial neural networks[M]. New York: McGraw-Hill, 1997.
[4] Ma F, Chitta R, Zhou J, et al. Dipole: diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks [C]. Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, 2017: 1903-1911.
[5] Khitan Z, Shapiro AP, Shah PT , et al. Predicting adverse outcomes in chronic kidney disease using machine learning methods: data from the modification of diet in renal disease[J]. Marshall J Med, 2017,3(4):67.
[6] Korchiyne R, Farssi SM, Sbihi A , et al. A combined method of fractal and GLCM features for MRI and CT scan images classification[J]. Signal & Image Processing: An International Journal, 2014,5(4):85.
[7] Lipton ZC, Berkowitz J , Elkan C. A critical review of recurrent neural networks for sequence learning [J/OL]. ( 2015 -10-17)[2019-01-10]. https://arxiv.org/pdf/1506.00019.pdf.
[8] Chung J, Gulcehre C, Cho KH , et al. Empirical evaluation of gated recurrent neural networks on sequence modeling [J/OL]. ( 2014 -12-11)[2019-01-10]. https://arxiv.org/pdf/1412.3555.pdf.
[1] Lingfu ZHANG, Ming CHEN, Xiaoyu ZHAO, Gang WANG, Long CUI, Xiaofeng LING, Lixin WANG, Zhi XU, Limei GUO, Chunsheng HOU. Gross classification of gallbladder cancer with primary lesion limited to the gallbladder wall and its correlation with prognosis and precancerous lesions [J]. Journal of Peking University (Health Sciences), 2026, 58(1): 184-189.
[2] Boda GUO, Min LU, Guoliang WANG, Hongxian ZHANG, Lei LIU, Xiaofei HOU, Lei ZHAO, Xiaojun TIAN, Shudong ZHANG. Clinicopathological and prognostic differences between clear cell and non-clear cell renal cell carcinoma with venous tumor thrombus [J]. Journal of Peking University (Health Sciences), 2025, 57(4): 644-649.
[3] Weihao LI, Jing LI, Xuemin ZHANG, Wei LI, Qingle LI, Xiaoming ZHANG. Effect of intraoperative blood salvage autotransfusion on the prognosis of patients after carotid body tumor resection [J]. Journal of Peking University (Health Sciences), 2025, 57(2): 272-276.
[4] Aichun LIU, Huiping ZHAO, Bei WU, Shuying ZHENG, Li ZUO, Mei WANG. Bacterial biofilm formation of peritoneal dialysis catheter in patients with peritonitis-associated catheter removal [J]. Journal of Peking University (Health Sciences), 2025, 57(1): 161-165.
[5] Yaqing MAO, Zhen CHEN, Yao YU, Wenbo ZHANG, Yang LIU, Xin PENG. Impact of type 2 diabetes mellitus on the prognosis of patients with oral squamous cell carcinoma [J]. Journal of Peking University (Health Sciences), 2024, 56(6): 1089-1096.
[6] Junyong OU,Kunming NI,Lulin MA,Guoliang WANG,Ye YAN,Bin YANG,Gengwu LI,Haodong SONG,Min LU,Jianfei YE,Shudong ZHANG. Prognostic factors of patients with muscle invasive bladder cancer with intermediate-to-high risk prostate cancer [J]. Journal of Peking University (Health Sciences), 2024, 56(4): 582-588.
[7] Shuai LIU,Lei LIU,Zhuo LIU,Fan ZHANG,Lulin MA,Xiaojun TIAN,Xiaofei HOU,Guoliang WANG,Lei ZHAO,Shudong ZHANG. Clinical treatment and prognosis of adrenocortical carcinoma with venous tumor thrombus [J]. Journal of Peking University (Health Sciences), 2024, 56(4): 624-630.
[8] Le YU,Shaohui DENG,Fan ZHANG,Ye YAN,Jianfei YE,Shudong ZHANG. Clinicopathological characteristics and prognosis of multilocular cystic renal neoplasm of low malignant potential [J]. Journal of Peking University (Health Sciences), 2024, 56(4): 661-666.
[9] Zezhen ZHOU,Shaohui DENG,Ye YAN,Fan ZHANG,Yichang HAO,Liyuan GE,Hongxian ZHANG,Guoliang WANG,Shudong ZHANG. Predicting the 3-year tumor-specific survival in patients with T3a non-metastatic renal cell carcinoma [J]. Journal of Peking University (Health Sciences), 2024, 56(4): 673-679.
[10] Yangyi FANG,Qiang LI,Zhigao HUANG,Min LU,Kai HONG,Shudong ZHANG. Well-differentiated papillary mesothelial tumour of the tunica vaginalis: A case report [J]. Journal of Peking University (Health Sciences), 2024, 56(4): 741-744.
[11] Yuanyuan ZENG,Yun XIE,Daonan CHEN,Ruilan WANG. Related factors of euthyroid sick syndrome in patients with sepsis [J]. Journal of Peking University (Health Sciences), 2024, 56(3): 526-532.
[12] Wanyin HOU,Jie DONG. Acquired cystic kidney hemorrhage in peritoneal dialysis patients: A report of three cases [J]. Journal of Peking University (Health Sciences), 2024, 56(3): 546-550.
[13] Jian-bin LI,Meng-na LYU,Qiang CHI,Yi-lin PENG,Peng-cheng LIU,Rui WU. Early prediction of severe COVID-19 in patients with Sjögren’s syndrome [J]. Journal of Peking University (Health Sciences), 2023, 55(6): 1007-1012.
[14] Huan-rui LIU,Xiang PENG,Sen-lin LI,Xin GOU. Risk modeling based on HER-2 related genes for bladder cancer survival prognosis assessment [J]. Journal of Peking University (Health Sciences), 2023, 55(5): 793-801.
[15] Zi-xuan XUE,Shi-ying TANG,Min QIU,Cheng LIU,Xiao-jun TIAN,Min LU,Jing-han DONG,Lu-lin MA,Shu-dong ZHANG. Clinicopathologic features and prognosis of young renal tumors with tumor thrombus [J]. Journal of Peking University (Health Sciences), 2023, 55(5): 802-811.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Peking University (Health Sciences), All Rights Reserved.
Powered by Beijing Magtech Co. Ltd