Skip to main content
SpringerLink
Log in

Deep learning architecture to predict daily hospital admissions

  • Review Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Air pollution and airborne pollen play a key role in respiratory and circulatory disorders and thus have a direct relation to hospital admissions for these causes. Knowing in advance the influx of patients to emergency services allows clinical institutions to optimize resources and to improve their service. Since the variables influencing respiratory and circulatory-related hospital admissions belong to fields such aerobiology or meteorology, we aim for a data-based system which is able to predict admissions without a priori assumptions. Given the number and distribution of observation stations (meteorological, pollen and chemical pollution stations and hospital), previous approaches generate many model-dependent systems that need to be combined in order to obtain the full representation of future environmental conditions. A unified approach able to extract all temporal dynamics as well as all spatial relations would allow a better representation of the aforementioned conditions and consequently a more precise hospital admissions forecast. The proposed system is based on a specific neural network topology of long short-term memories and convolutional neural networks to obtain the spatio-temporal relations between all independent and target variables. It was applied to forecast daily hospital admissions due to respiratory- and circulatory-related disorders. The proposal outperforms the benchmark approaches by reducing as an average the prediction error by 28% and 20% for the circulatory and respiratory cases, respectively. Consequently, the system extracts all relevant information without specific field knowledge and provides accurate hospital admissions forecasts.

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

Similar content being viewed by others

Notes

  1. https://www.who.int/healthinfo/global_burden_disease/estimates/en/index1.html.

References

  1. Abdeljaber O, Avci O, Kiranyaz S, Boashash B, Sodano H, Inman D (2017) 1-D CNNs for structural damage detection: verification on a structural health monitoring benchmark data. Neurocomputing 275:1308–1317

    Google Scholar 

  2. Abraham G, Byrnes GB, Bain CA (2009) Short-term forecasting of emergency inpatient flow. Inf Technol Biomed 13:380–388

    Google Scholar 

  3. Alberdi JC, Díaz J, Montero JC, Mirón IJ (1998) Daily mortality in madrid community (Spain) 1986–1991: relationship with atmospheric variables. Eur J Epidemiol 14:571–578

    Google Scholar 

  4. Anwar MY, Lewnard JA, Parikh S, Pitzer VE (2016) Time series analysis of malaria in Afghanistan: using arima models to predict future trends in incidence. Malar J 15:566

    Google Scholar 

  5. Baghban A, Jalali A, Shafiee M, Ahmadi M (2018) Developing an anfis based swarm concept model for estimating relative viscosity of nanofluids. Eng Appl Comput Fluid Mech 13:08

    Google Scholar 

  6. Bergmeir C, Hyndman RJ, Koo B (2018) A note on the validity of cross-validation for evaluating autoregressive time series prediction. Comput Stat Data Anal 120:70–83

    MathSciNet  MATH  Google Scholar 

  7. Cannell MGR, Smith RI (1983) Thermal time, chill days and prediction of budburst in Picea sitchensis. J Appl Ecol 20:269–275

    Google Scholar 

  8. Díaz J, Alberdi JC, Pajares MS, López R, López C, Otero A (2001) A model for forecasting emergency hospital admissions: effect of environmental variables. J Environ Health 64:9–15

    Google Scholar 

  9. Díaz J, Carmona R, Mirón JL, Ortiz C, León I, Linares C (2015) Geographical variation in relative risks associated with heat: update of Spain’s heat wave prevention plan. Environ Int 85:273–283

    Google Scholar 

  10. Díaz J, García R, López C, Linares C (2005) Mortality impact of extreme winter temperatures. Int J Biometeorol 49:179–183

    Google Scholar 

  11. Díaz J, García R, Ribera P, Alberdi JC, Hernández E, Pajares MS (1999) Modeling of air pollution and its relationship with mortality and morbidity in madrid (Spain). Int Arch Occup Environ Health 75:366–376

    Google Scholar 

  12. Díaz J, Linares C, Tobías A (2007) Short term effects of pollen species on hospital admissions in the city of madrid in terms of specific causes and age. Aerobiologia 23:231–238

    Google Scholar 

  13. Díaz J, López C, Jordán A, Alberdi JC, García R, Hernández E, Otero A (2002) Heat waves in Madrid, 1986–1997: effects on the health of the elderly. Int Arch Occup Environ Health 75:163–170

    Google Scholar 

  14. Dominak M, Swiecicki L, Rybakowski J (2015) Psychiatric hospitalizations for affective disorders in Warsaw, Poland: effect of season and intensity of sunlight. Phychiatry Res 229:289–294

    Google Scholar 

  15. Donahue J, Anne Hendricks L, Rohrbach M, Venugopalan S, Guadarrama S, Saenko K, Darrell T (2014) Long-term recurrent convolutional networks for visual recognition and description. arXiv eprint. arXiv:1411.4389

  16. de Jesus Rubio J (2009) SOFMLS: online self-organizing fuzzy modified least-squares network. IEEE Trans Fuzzy Syst 17:1296–1309

    Google Scholar 

  17. de Jesus Rubio J, Cruz D, Elias Barrón I, Ochoa G, Balcazarand Ricardo, Aguilar Arturo (2019) ANFIS system for classification of brain signals. J Intell Fuzzy Syst 37:4033–4041

    Google Scholar 

  18. de Jesus Rubio J, García-Trinidad E, Ochoa G, Elias Barrón I, Cruz D, Balcazar R, Lopez-Gomez J, Novoa J (2019) Unscented kalman filter for learning of a solar dryer and a greenhouse. J Intell Fuzzy Syst 37:6731–6741

    Google Scholar 

  19. Earnest A, Chen MI, Ng D, Sin LY (2005) Using autoregressive integrated moving average (arima) models to predict and monitor the number of beds occupied during a sars outbreak in a tertiary hospital in Singapore. BMC Health Serv Res 5:36

    Google Scholar 

  20. Faizollahzadeh Ardabili S, Najafi B, Shamshirband S, Minaei Bidgoli B, Deo RC, Chau KW (2018) Computational intelligence approach for modeling hydrogen production: a review. Eng Appl Comput Fluid Mech 12(1):438–458

    Google Scholar 

  21. Fotovatikhah F, Herrera M, Shamshirband S, Chau KW, Faizollahzadeh Ardabili S, Piran MJ (2018) Survey of computational intelligence as basis to big flood management: challenges, research directions and future work. Eng Appl Comput Fluid Mech 12(1):411–437

    Google Scholar 

  22. Gamboa JCB (2017) Deep learning for time-series analysis. CoRR. arXiv:1701.01887

  23. Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN (2017) Convolutional sequence to sequence learning. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning, volume 70 of proceedings of machine learning research. International Convention Centre, Sydney, Australia, 06–11 Aug 2017. PMLR, pp 1243–1252

  24. Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: continual prediction with LSTM. Neural Comput 12:2451–2471

    Google Scholar 

  25. Giap CN, Son LH, Chiclana F (2018) Dynamic structural neural network. J Intell Fuzzy Syst 34:2479–2490

    Google Scholar 

  26. Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J (2015) LSTM: a search space odyssey. CoRR. arXiv:1503.04069

  27. Hochreiter S, Bengio Y, Frasconi P, Schmidhuber J (2001) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer SC, Kolen JF (eds) A field guide to dynamical recurrent neural networks. IEEE Press, New Jersey

    Google Scholar 

  28. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780

    Google Scholar 

  29. Hu X, Xu D, Wan Q (2018) Short-term trend forecast of different traffic pollutants in minnesota based on spot velocity conversion. Int J Environ Res Public Health 15:1925

    Google Scholar 

  30. Kelly FJ, Fussell JC (2015) Air pollution and public health: emerging hazards and improved understanding of risk. Environ Geochem Health 37:631–649

    Google Scholar 

  31. Kingma D, Ba J (2014) Adam: a method for stochastic optimization. CoRR. arXiv:1412.6980

  32. Kiranyaz S, Ince T, Gabbouj M (2015) Real-time patient-specific ECG classification by 1D convolutional neural networks. IEEE Trans Bio-Med Eng 63:08

    Google Scholar 

  33. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25. Curran Associates, Inc., New York, pp 1097–1105

    Google Scholar 

  34. Kumar V, Mangal A, Panesar S, Yadav G, Talwar R, Raut D, Singh S (2014) Forecasting malaria cases using climatic factors in Delhi, India: a time series analysis. Malar Res Treat 2014:482851

    Google Scholar 

  35. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Google Scholar 

  36. Li X, Qin T, Yang J, Liu T-Y (2016) LightRNN: memory and computation-efficient recurrent neural networks. arXiv eprint. arXiv:1610.09893

  37. Linares C, Mirón IJ, Sánchez R, Carmona R, Díaz J (2016) Time trend in natural-cause, circulatory-cause and respiratory-cause mortality associated with cold waves in Spain, 1975–2008. Stoch Res Risk Assess 30:1565–1574

    Google Scholar 

  38. Masuko T (2017) Computational cost reduction of long short-term memory based on simultaneous compression of input and hidden state. In: 2017 IEEE automatic speech recognition and understanding workshop (ASRU), pp 126–133

  39. McWilliams S, Kinsella A, O’Callaghan E (2014) Daily weather variables and affective disorder admissions to psychiatric hospitals. Int J Biometeorol 58:2045–57

    Google Scholar 

  40. Moazenzadeh R, Mohammadi B, Shamshirband S, Chau KW (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in Northern Iran. Eng Appl Comput Fluid Mech 12(1):584–597

    Google Scholar 

  41. Montero JC, Mirón IJ, Criado-Álvarez JJ, Linares C, Díaz J (2012) Relationship between mortality and heat waves in Castile-la Mancha (1975–2003): influence of local factors. Sci Total Environ 414:73–78

    Google Scholar 

  42. Navares R, Aznarte JL (2016) Predicting the Poaceae pollen season: six month-ahead forecasting and identification of relevant features. Int J Biometeorol. https://doi.org/10.1007/s00484-016-1242-8

    Article  Google Scholar 

  43. Navares R, Aznarte JL (2017) Forecasting the start and end of pollen season in Madrid. Springer, Berlin

    Google Scholar 

  44. Navares R, Aznarte JL (2019) Forecasting plantago pollen: improving feature selection through random forests, clustering, and friedman tests. Theor Appl Climatol 139:08

    Google Scholar 

  45. Navares R, Díaz J, Linares C, Aznarte JL (2018) Comparing arima and computational intelligence methods to forecast daily hospital admissions due to circulatory and respiratory causes in Madrid. Stoch Environ Res Risk Assess 32:2849–2859

    Google Scholar 

  46. Obermeyer Z, Emanuel EJ (2016) Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med 375:1216–1219

    Google Scholar 

  47. Roldán E, Gómez M, Pino MR, Pórtoles J, Linares C, Díaz J (2016) The effect of climate-change-related heat waves on mortality in Spain: uncertainties in health on a local scale. Stoch Res Risk Assess 30:831–839

    Google Scholar 

  48. Ruder S (2016) An overview of gradient descent optimization algorithms. CoRR. arXiv:1609.04747

  49. Rumelhart DE, Hinton GE, Ronald RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    MATH  Google Scholar 

  50. Sabariego S, Cuesta P, Fernández-González F, Pérez-Badia R (2012) Models for forecasting airborne cupressaceae pollen levels in central Spain. Int J Biometeorol 56:253–258

    Google Scholar 

  51. Schaber J, Badeck F-W (2003) Physiology-based phenology models for forest tree species in Germany. Int J Biometeorol 47:193–201

    Google Scholar 

  52. Shamshirband S, Rabczuk T, Chau K-W (2019) A survey of deep learning techniques: application in wind and solar energy resources. IEEE Access 7:164650–164666

    Google Scholar 

  53. Silva-Palacios I, Fernández-Rodríguez S, Durán-Barroso P, Tormo-Molina R, Maya-Manzano JM, Gonzalo-Garijo A (2016) Temporal modelling and forecasting of the airborne pollen of Cupressaceae on the southwestern Iberian peninsula. Int J Biometeorol 60:1509–1517

    Google Scholar 

  54. Smith M, Emberlin J (2006) A 30-day-ahead forecast model for grass pollen in north London, UK. Int J Biometeorol 50:233–242

    Google Scholar 

  55. Subiza J, Jerez M, Jiménez JA, Narganes MJ, Cabrera M, Varela S, Subiza E (1995) Allergenic pollen pollinosis in Madrid. J Allergy Clin Immunol 96:15–23

    Google Scholar 

  56. Soldevilla CG, González PC, Teno PA, Vílches ED (2007) Manual de Calidad y Gestión de la Red Española de Aerobiología. Universidad de Córdoba, Córdoba

    Google Scholar 

  57. Valput D, Navares R, Aznarte JL (2019) Forecasting hourly NO2 concentrations by ensembling neural networks and mesoscale models. Neural Comput Applic. https://doi.org/10.1007/s00521-019-04442-z

    Article  Google Scholar 

  58. Vinyals O, Toshev A, Bengio S, Erhan D (2014) Show and tell: a neural image caption generator. CoRR. arXiv:1411.4555

  59. Yousefi M, Yousefi M, Ferreira R Poley Martins, Kim JH, Fogliatto FS (2018) Chaotic genetic algorithm and adaboost ensemble metamodeling approach for optimum resource planning in emergency departments. Artif Intell Med 84:23–33

    Google Scholar 

  60. Zhu T, Luo L, Zhang X, Shi Y, Shen W (2015) Time series approaches for forecasting the number of hospital daily discharged inpatients. IEEE J Biomed Health Inform 21:515–526

    Google Scholar 

Download references

Acknowledgements

This work was only possible thanks to the ongoing fruitful collaboration with Julio Díaz and Cristina Linares, from the Carlos III National Institute of Health, Madrid, Spain. References [16,17,18, 25] were added upon request by Reviewer 3.

Author information

Authors and Affiliations

  1. Department of Artificial Intelligence, UNED, Juan del Rosal, 16, 28040, Madrid, Spain

    Ricardo Navares & José L. Aznarte

Authors
  1. Ricardo Navares
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José L. Aznarte
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ricardo Navares.

Ethics declarations

Conflict of interest

The authors declare no conflict of interests.

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

Navares, R., Aznarte, J.L. Deep learning architecture to predict daily hospital admissions. Neural Comput & Applic 32, 16235–16244 (2020). https://doi.org/10.1007/s00521-020-04840-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-04840-8

Keywords

Search

Navigation