Skip to main content

Advertisement

SpringerLink
Log in

Artificial neural networks and risk stratification in emergency departments

  • EM - ORIGINAL
  • Published:
Internal and Emergency Medicine Aims and scope Submit manuscript

Abstract

Emergency departments are characterized by the need for quick diagnosis under pressure. To select the most appropriate treatment, a series of rules to support decision-making has been offered by scientific societies. The effectiveness of these rules affects the appropriateness of treatment and the hospitalization of patients. Analyzing a sample of 1844 patients and focusing on the decision to hospitalize a patient after a syncope event to prevent severe short-term outcomes, this work proposes a new algorithm based on neural networks. Artificial neural networks are a non-parametric technique with the well-known ability to generalize behaviors, and they can thus predict severe short-term outcomes with pre-selected levels of sensitivity and specificity. This innovative technique can outperform the traditional models, since it does not require a specific functional form, i.e., the data are not supposed to be distributed following a specific design. Based on our results, the innovative model can predict hospitalization with a sensitivity of 100% and a specificity of 79%, significantly increasing the appropriateness of medical treatment and, as a result, hospital efficiency. According to Garson’s Indexes, the most significant variables are exertion, the absence of symptoms, and the patient’s gender. On the contrary, cardio-vascular history, hypertension, and age have the lowest impact on the determination of the subject’s health status. The main application of this new technology is the adoption of smart solutions (e.g., a mobile app) to customize the stratification of patients admitted to emergency departments (ED)s after a syncope event. Indeed, the adoption of these smart solutions gives the opportunity to customize risk stratification according to the specific clinical case (i.e., the patient’s health status) and the physician’s decision-making process (i.e., the desired levels of sensitivity and specificity). Moreover, a decision-making process based on these smart solutions might ensure a more effective use of available resources, improving the management of syncope patients and reducing the cost of inappropriate treatment and hospitalization.

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

Similar content being viewed by others

Notes

  1. The tansigmoidal function has a logsigmoidal form with a codomain range from − 1 to + 1.

References

  1. Cournane S, Conway R, Creagh D, Byrne DG, Silke B (2015) Consultant duration of clinical practice as a cost determinant of an emergency medical admission. Eur J Health Econ 2015(16):561–567. https://doi.org/10.1007/s10198-014-0619-z

    Article  Google Scholar 

  2. Eriksen BO, Førde OH, Kristiansen IS et al (2000) Cost savings and health losses from reducing inappropriate admissions to a department of internal medicine. Int J Technol Assess Health Care 16(4):1147–1157

    Article  PubMed  CAS  Google Scholar 

  3. Lee A, Clarke B, Hazlett SC et al (2003) How to minimize inappropriate utilization of Accident and Emergency Departments: improve the validity of classifying the general practice cases amongst the A&E attendees. Health Policy 66(2):159–168. https://doi.org/10.1016/S0168-8510(03)00023-X

    Article  PubMed  Google Scholar 

  4. Casagranda I, Costantino G, Falavigna G, Furlan R, Ippoliti R (2016) Artificial Neural Networks and risk stratification models in Emergency Departments: the policy maker’s perspective. Health Policy 120(1):111–119

    Article  PubMed  Google Scholar 

  5. Weingart S, Wyer P (2006) Emergency medicine decision making: critical choices in chaotic environments. McGraw-Hill, New York

    Google Scholar 

  6. McDonagh MS, Smith DH, Goddard M (2000) Measuring appropriate use of acute beds. A systematic review of methods and results. Health Policy 53(3):157–184. https://doi.org/10.1016/s0168-8510(00)00092-0

    Article  PubMed  CAS  Google Scholar 

  7. Fellin G, Apolone G, Tampieri A et al (1995) Appropriateness of hospital use: an overview of Italian studies. Int J Qual Health Care 7(3):219–225

    Article  PubMed  CAS  Google Scholar 

  8. Propper C, Burgess S, Green K (2004) Does competition between hospitals improve the quality of care? Hospital death rates and the NHS internal market. J Public Econ 88(7–8):1247–1272

    Article  Google Scholar 

  9. Chua CL, Palangkaraya A, Yong J (2010) A two-stage estimation of hospital quality using mortality outcome measure: an application using hospital administrative data. Health Econ 19:1404–1424. https://doi.org/10.1002/hec.1560

    Article  PubMed  Google Scholar 

  10. Ippoliti R, Falavigna G (2012) Efficiency of medical care industry: evidence from the Italian regional system. Eur J Oper Res 217(2012):643–652. https://doi.org/10.1016/j.ejor.2011.10.010

    Article  Google Scholar 

  11. Quaglio GL, Karapiperis T, Van Woensel L et al (2013) Austerity and health in Europe. Health Policy 113(1):13–19. https://doi.org/10.1016/j.healthpol.2013.09.005

    Article  PubMed  Google Scholar 

  12. Ippoliti R, Falavigna G, Grosso F, Maconi A, Randi L, Numico G (2018) The economic impact of clinical research in an Italian public hospital: the malignant pleural mesothelioma case study. Int J Health Policy Manag 7(8):728–737. https://doi.org/10.15171/ijhpm.2018.13

    Article  PubMed  PubMed Central  Google Scholar 

  13. De Vos P, Orduñez-García P, Santos-Peña M et al (2010) Public hospital management in times of crisis: lessons learned from Cienfuegos, Cuba (1996–2008). Health Policy 96(1):64–71. https://doi.org/10.1016/j.healthpol.2010.01.005

    Article  PubMed  Google Scholar 

  14. Ippoliti R, Allievi I, Falavigna G, Rizzi S, Moda G (2018) The sustainability of a community nurses programme aimed at supporting active ageing in mountain areas. Int J Health Plan Manag. https://doi.org/10.1002/hpm.2591 (forthcoming)

    Article  Google Scholar 

  15. Costantino G, Falavigna G, Solbiati M, Furlan R, Ippoliti R (2017) Neural networks as a tool to predict syncope risk in the Emergency Department. Europace 19(11):1891–1895. https://doi.org/10.1093/europace/euw336

    Article  PubMed  Google Scholar 

  16. Costantino G, Sun B, Barbic F et al (2015) Syncope clinical management in the ED: a consensus from the first international workshop on syncope risk stratification in the ED. Eur Heart J. https://doi.org/10.1093/eurheartj/ehv378

    Article  PubMed Central  PubMed  Google Scholar 

  17. Sun B, Costantino G, Barbic F et al (2014) Priorities for emergency department syncope research. Ann Emerg Med 64(6):649–655. https://doi.org/10.1016/j.annemergmed.2014.04.014

    Article  PubMed  Google Scholar 

  18. Quinn J, McDermott D, Stiell I, Kohn M, Wells G (2006) Prospective validation of the San Francisco Syncope Rule to predict patients with serious outcomes. Ann Emerg Med 47(5):448–454

    Article  PubMed  Google Scholar 

  19. Costantino G, Furlan R (2013) Syncope risk stratification in the emergency department. Cardiol Clin 31(2013):27–38. https://doi.org/10.1016/j.ccl.2012.10.003

    Article  PubMed  Google Scholar 

  20. Quinn JV, Stiell IG, McDermott DA, Sellers KL, Kohn MA, Wells GA (2004) Derivation of the San Francisco Syncope Rule to predict patients with short-term serious outcomes. Ann Emerg Med 43(2):224–232

    Article  PubMed  Google Scholar 

  21. Quinn J, McDermott D (2011) Electrocardiogram findings in emergency department patients with syncope. Acad Emerg Med 18(7):714–718

    Article  PubMed  Google Scholar 

  22. Dipaola F, Costantino G, Perego F et al (2010) San Francisco syncope rule, Osservatorio epidemiologico sulla sincope nel lazio risk score, and clinical judgment in the assessment of short-term outcome of syncope. Am J Emerg Med 2010(28):432–439

    Article  Google Scholar 

  23. Constantino G, Perego F, Dipaola F et al (2008) Short and long-term prognosis of syncope, risk factors, and role of hospital admission. J Am Coll Cardiol 51(30):276–283

    Article  Google Scholar 

  24. Del Rosso A, Ungar A, Maggi R et al (2008) Clinical predictors of cardiac syncope at initial evaluation in patients referred urgently to a general hospital: the EGSYS score. Heart 94:1620–1626

    Article  PubMed  Google Scholar 

  25. Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. CRC Press, Boca Raton

    Google Scholar 

  26. Trichakis I, Nikolos I, Karatzas GP (2011) Comparison of bootstrap confidence intervals for an ANN model of a karstic aquifer response. Hydrol Process 25(18):2827–2836

    Article  Google Scholar 

  27. Falavigna G (2008) New contents and perspectives in the risk analysis of enterprises. Int J Bus Perform Manag 10(2/3):136–173

    Article  Google Scholar 

  28. Heckerling PS, Canaris GJ, Flach SD, Tape TG, Wigton RS, Gerber BS (2007) Predictors of urinary tract infection based on artificial neural networks and genetic algorithms. Int J Med Inform 76(4):289–296

    Article  PubMed  Google Scholar 

  29. Tenório JM, Hummel AD, Cohrs FM, Sdepanian VL, Pisa IT, de Fátima Marin H (2011) Artificial intelligence techniques applied to the development of a decision–support system for diagnosing celiac disease. Int J Med Inform 80(11):793–802

    Article  PubMed  PubMed Central  Google Scholar 

  30. Ellenius J, Groth T (2000) Methods for selection of adequate neural network structures with application to early assessment of chest pain patients by biochemical monitoring. Int J Med Inform 57(2–3):181–202

    Article  PubMed  CAS  Google Scholar 

  31. Parmanto B, Deneault LG, Denault AY (2001) Detection of hemodynamic changes in clinical monitoring by time-delay neural networks. Int J Med Inform 63(1–2):91–99

    Article  PubMed  CAS  Google Scholar 

  32. Baxt WG, Shofer FS, Sites FD, Hollander JE (2002) A neural network aid for the early diagnosis of cardiac ischemia in patients presenting to the emergency department with chest pain. Ann Emerg Med 40(6):575–583

    Article  PubMed  Google Scholar 

  33. Harrison RF, Kennedy RL (2005) Artificial neural network models for prediction of acute coronary syndromes using clinical data from the time of presentation. Ann Emerg Med 46(5):431–439

    Article  PubMed  Google Scholar 

  34. Bektaş F, Eken C, Soyuncu S et al (2008) Artificial neural network in predicting craniocervical junction injury: an alternative approach to trauma patients. Eur J Emerg Med 15(6):318–323. https://doi.org/10.1097/MEJ.0b013e3282fce7af

    Article  PubMed  Google Scholar 

  35. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366

    Article  Google Scholar 

  36. Kim KJ (2003) Financial time series forecasting using support vector machines. Neurocomputing 55(1):307–319

    Article  Google Scholar 

  37. Min JH, Lee YC (2005) Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Syst Appl 28(4):603–614

    Article  Google Scholar 

  38. Patuwo E, Hu MY, Hung MS (1993) Two-group classification using neural networks. Decis Sci 24(4):825–845

    Article  Google Scholar 

  39. Nath R, Rajagopalan B, Ryker R (1997) Determining the saliency of input variables in neural network classifiers. Comput Oper Res 24(8):767–773

    Article  Google Scholar 

  40. Chauhan N, Ravi V, Karthik Chandra D (2009) Differential evolution trained wavelet neural networks: application to bankruptcy prediction in banks. Expert Syst Appl 36(4):7659–7665

    Article  Google Scholar 

  41. Salchenberger LM, Cinar E, Lash NA (1992) Neural networks: a new tool for predicting thrift failures. Decis Sci 23(4):899–916

    Article  Google Scholar 

  42. Olmeda I, Fernández E (1997) Hybrid classifiers for financial multicriteria decision making: the case of bankruptcy prediction. Comput Econ 10(4):317–335

    Article  Google Scholar 

  43. Garson GD (1991) Interpreting neural-network connection weights. AI Expert 6(4):46–51

    Google Scholar 

  44. Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480

    Article  Google Scholar 

  45. Falavigna G (2012) Financial ratings with scarce information: a neural network approach. Expert Syst Appl 39(2):1784–1792. https://doi.org/10.1016/j.eswa.2011.08.074 (ISSN: 0957-4174)

    Article  Google Scholar 

  46. Reid MC, Lane DA, Feinstein AR (1998) Academic calculations versus clinical judgments: practicing physicians’ use of quantitative measures of test accuracy. Am J Med 104(4):374–380

    Article  PubMed  CAS  Google Scholar 

  47. Gardner M, Altman DG (2000) Statistics with confidence: confidence intervals and statistical guidelines. BMJ Books, London

    Google Scholar 

  48. McGee S (2002) Simplifying likelihood ratios. J Gen Intern Med 17(8):647–650. https://doi.org/10.1046/j.1525-1497.2002.10750.x

    Article  PubMed Central  Google Scholar 

  49. Henderson MC, Tierney LM, Smetana GW (2012) The patient history, 2nd edn. McGraw-Hill, New York, p 30 (ISBN 978-0-07-162494-7)

    Google Scholar 

  50. Kunene KN, Weistroffer HR (2008) An approach for predicting and describing patient outcome using multicriteria decision analysis and decision rules. Eur J Oper Res 185(3):984–997

    Article  Google Scholar 

  51. West D, Mangiameli P, Rampal R, West V (2005) Ensemble strategies for a medical diagnostic decision support system: a breast cancer diagnosis application. Eur J Oper Res 162(2):532–551

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. CNR-IRCrES, Research Institute on Sustainable Economic Growth, Moncalieri, Italy

    Greta Falavigna

  2. Clinical Medicine Department, Fondazione IRCCS, Ca’ Granda, Ospedale Maggiore Policlinico, Milan, Italy

    Giorgio Costantino

  3. Department of Biomedical Sciences, Humanitas University, Humanitas Research Hospital, Rozzano, Italy

    Raffaello Furlan

  4. Division of Emergency Medicine, Stanford University, Stanford, CA, USA

    James V. Quinn

  5. Syncope Unit, Geriatric Medicine and Cardiology, Careggi University Hospital, Florence, Italy

    Andrea Ungar

  6. Department of Management, University of Turin, Turin, Italy

    Roberto Ippoliti

Authors
  1. Greta Falavigna
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giorgio Costantino
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Raffaello Furlan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. James V. Quinn
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Andrea Ungar
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Roberto Ippoliti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Greta Falavigna.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Statement of human and animal rights

This is a retrospective analysis on anonymous data, previously collected by the hospitals, without formal ethical approval according to national law.

Informed consent

Patients’ informed consents have been collected by the hospitals before treatments and clinical procedures.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Falavigna, G., Costantino, G., Furlan, R. et al. Artificial neural networks and risk stratification in emergency departments. Intern Emerg Med 14, 291–299 (2019). https://doi.org/10.1007/s11739-018-1971-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11739-018-1971-2

Keywords

Search

Navigation