Skip to main content
SpringerLink
Log in

ChroNet: A multi-task learning based approach for prediction of multiple chronic diseases

  • 1181: Multimedia-based Healthcare Systems using Computational Intelligence
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Chronic diseases (such as diabetes, hypertension, etc) are generally of long duration and slow progression. These diseases may be implied in electronic medical records (EMR), and one chronic disease may be accompanied by another. Recently, many methods have been proposed for chronic disease prediction and early detection. However, previous methods mainly focused on predicting one individual disease, thus possibly neglecting potential correlations among multiple diseases. In this paper, we propose a new framework for chronic disease prediction which can take into account possible correlations among multiple chronic diseases, called ChroNet. We propose a Multi-task Learning (MTL) based framework, for multiple chronic disease prediction. First, based on the characteristics of EMR, we introduce a novel approach for data embedding, including Content Embedding and Spatial Embedding. Then, an MTL convolutional neural network (CNN) is designed to perform multiple chronic disease prediction simultaneously. We collect a dataset from 5 local hospitals, involving 48953 patients’ records. Then we conduct abundant experiments for hypertension and type 2 diabetes prediction, based on our dataset. For both hypertension and type 2 diabetes prediction, our proposed framework outperforms known single-task models (with the same CNN layers yet a single branch). Further, our MTL-based framework outperforms several most commonly used traditional machine learning models and convolutional neural networks. Theoretically, our framework can capture general features of different diseases and focus its attention on those features that actually matter for each disease. The performance superiority in experiments indicates that our framework may be able to capture more detailed characteristics of medical structural data after specific embedding, comparing with known single-task models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Apidechkul T (2018) Prevalence and factors associated with type 2 diabetes mellitus and hypertension among the hill tribe elderly populations in northern Thailand. BMC Public Health 18(1):694

    Article  Google Scholar 

  2. Baxter J (1997) A Bayesian/information theoretic model of learning to learn via multiple task sampling. Mach Learn 28(1):7–39

    Article  MATH  Google Scholar 

  3. Bello-Ovosi BO, Asuke S, Abdulrahman SO, Ibrahim MS, Ovosi JO et al (2018) Prevalence and correlates of hypertension and diabetes mellitus in an urban community in North-Western Nigeria. Pan African Med J 29(1):1–7

    Google Scholar 

  4. Beratarrechea A, Lee AG, Willner JM, Jahangir E et al (2014) The impact of mobile health interventions on chronic disease outcomes in developing countries: A systematic review. Telemed e-Health 20(1):75–82

    Article  Google Scholar 

  5. Chen M, Hao Y, Hwang K, Wang L, Wang L (2017) Disease prediction by machine learning over big data from healthcare communities. IEEE Access 5:8869–8879

    Article  Google Scholar 

  6. Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794

  7. Duong L, Cohn T, Bird S, Cook P (2015) Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (vol 2: Short Papers), pp 845–850

  8. Ebrahim S, Pearce N, Smeeth L, Casas JP, Jaffar S et al (2013) Tackling non-communicable diseases in low-and middle-income countries: is the evidence from high-income countries all we need? PLoS Med 10(1)

  9. Fu J (2017) Systems diagnosis in chronic disease: Prediction and evaluation. PhD thesis

  10. Goldstein BA, Navar AM, Pencina MJ, Ioannidis J (2017) Opportunities and challenges in developing risk prediction models with electronic health records data: A systematic review. J Am Med Inform Assoc 24(1):198–208

    Article  Google Scholar 

  11. Ijaz MF, Alfian G, Syafrudin M, Rhee J (2018) Hybrid prediction model for type 2 diabetes and hypertension using DBSCAN-based outlier detection, synthetic minority over sampling technique (SMOTE), and random forest. Appl Sci 8(8):1325

    Article  Google Scholar 

  12. Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY (2017) LightGBM: A highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, pp 3146–3154

  13. Kim C, Son Y, Youm S (2019) Chronic disease prediction using character-recurrent neural network in the presence of missing information. Appl Sci 9(10):2170

    Article  Google Scholar 

  14. Kim MJ, Lim NK, Choi SJ, Park HY (2015) Hypertension is an independent risk factor for type 2 diabetes: The Korean genome and epidemiology study. Hypertens Res 38(11):783–789

    Article  Google Scholar 

  15. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  16. Lin TY, Goyal P, Girshick R, He K, Dollár P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980–2988

  17. Mancia G (2016) The association between diabetes and hypertension: An overview of its clinical impact. Dialogues Cardiovasc Med 21:91–109

    Google Scholar 

  18. Martín V, Dávila-Batista V, Castilla J, Godoy P, Delgado-Rodríguez M, Soldevila N, Molina AJ, Fernandez-Villa T, Astray J, Castro A et al (2015) Comparison of body mass index (BMI) with the CUN-BAE body adiposity estimator in the prediction of hypertension and type 2 diabetes. BMC Public Health 16(1):82

    Article  Google Scholar 

  19. Mohanty S, Kishore S, Mishra S, Usha P (2018) Prevalence of hypertension and risk factors associated with it in subjects attending health camp in Rishikesh, Uttarakhand. Indian J Commun Health 30(1)

  20. Organization WH (1998) The world health report 1998: Life in the 21st century a vision for all. Geneva Switzerland Who (3) 391–392

  21. Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A (2018) CatBoost: Unbiased boosting with categorical features. In: Advances in neural information processing systems, pp 6638–6648

  22. Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv:170605098

  23. Safar ME, Asmar R, Benetos A, Blacher J, Boutouyrie P et al (2018) Interaction between hypertension and arterial stiffness: An expert reappraisal. Hypertension 72(4):796–805

    Article  Google Scholar 

  24. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618–626

  25. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556

  26. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  27. Tripathi S, Singh C, Kumar A, Pandey C, Jain N (2019) Bidirectional transformer based multi-task learning for natural language understanding. In: International conference on applications of natural language to information systems. Springer, pp 54–65

  28. Wang A, An N, Chen G, Li L, Alterovitz G (2015) Predicting hypertension without measurement: A non-invasive, questionnaire-based approach. Expert Syst Appl 42(21):7601–7609

    Article  Google Scholar 

  29. Yang Y, Hospedales TM (2016) Trace norm regularised deep multi-task learning. arXiv:160604038

  30. Zhang X, Zhao H, Zhang S, Li R (2019) A novel deep neural network model for multi-label chronic disease prediction. Front Genet 10

Download references

Acknowledgements

The research of J. Wu was partially supported by the National Research and Development Program of China under grant No. 2019YFB1404802, No. 2019YFC0118802, and No. 2018AAA0102102, the National Natural Science Foundation of China under grant No. 61672453, the Zhejiang University Education Foundation under grants No. K18-511120-004, No. K17-511120-017, and No. K17-518051-02, the Zhejiang public welfare technology research project under grant No. LGF20F020013, and the Key Laboratory of Medical Neurobiology of Zhejiang Province. D. Z. Chen’s research was supported in part by NSF Grant CCF-1617735.

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Zhejiang University, Hangzhou, 310027, China

    Ruiwei Feng, Yan Cao, Xuechen Liu, Tingting Chen, Jintai Chen & Jian Wu

  2. Real Doctor AI Research Centre, Zhejiang University, Hangzhou, China

    Ruiwei Feng, Yan Cao, Xuechen Liu, Tingting Chen, Jintai Chen & Jian Wu

  3. Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, 46556, USA

    Danny Z. Chen

  4. School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China

    Honghao Gao

  5. Gachon University, Gyeonggi-Do, 461-701, South Korea

    Honghao Gao

Authors
  1. Ruiwei Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yan Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xuechen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tingting Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jintai Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Danny Z. Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Honghao Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jian Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Ruiwei Feng contributed to the idea of the work, performed investigation for the task, designed the methods, and finished the original draft of this paper. Yan Cao conducted the experiments. Xuechen Liu proposed improvements to the method and modified the original draft. Tingting Chen and Jintai Chen interpreted the results, editing and reviewing the draft. Denny Z. Chen modified and improved the manuscript. Honghao Gao and Jian Wu contributed to editing and reviewing the manuscript.

Corresponding authors

Correspondence to Honghao Gao or Jian Wu.

Ethics declarations

Conflict of Interests

The authors declare no competing financial interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Feng, R., Cao, Y., Liu, X. et al. ChroNet: A multi-task learning based approach for prediction of multiple chronic diseases. Multimed Tools Appl 81, 41511–41525 (2022). https://doi.org/10.1007/s11042-020-10482-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-10482-8

Keywords

Search

Navigation