Home Integrating artificial neural network and scoring systems to increase the prediction accuracy of patient mortality and organ dysfunction
Article
Licensed
Unlicensed Requires Authentication

Integrating artificial neural network and scoring systems to increase the prediction accuracy of patient mortality and organ dysfunction

  • Seyed Ayoob Noorbakhsh , Mahmood Mahmoodi-Eshkaftaki EMAIL logo and Zahra Mokhtari
Published/Copyright: June 29, 2020
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Biomedical Engineering / Biomedizinische Technik
From the journal Biomedical Engineering / Biomedizinische Technik Volume 65 Issue 6

Abstract

The aim of this study was to develop and compare techniques to increase the prediction accuracy of patient mortality and organ dysfunction in the Intensive Care Units (hereinafter ICU) of hospitals. Patient mortality was estimated with two models of artificial neural network (ANN)-backpropagation (BP) and simplified acute physiology score (SAPS). Organ dysfunction was predicted by coupled ANN self-organizing map (SOM) and logistic organ dysfunction score (LODS) method on the basis of patient conditions. Input dataset consisted of 36 features recorded for 4,000 patients in the ICU. An integrated response surface methodology (RSM) and genetic algorithm (GA) was developed to achieve the best topology of the ANN-BP model. Although mortality prediction of the best ANN-BP (MSE = 0.0036, AUC = 0.83, R2 = 0.81) was more accurate than that of the SAPS score model (MSE = 0.0056, AUC = 0.82, R2 = 0.78), the execution time of the former (=45 min) was longer than that of the latter (=20 min). Therefore, the principal component analysis (PCA) was used to reduce the input feature dimensions, which, in turn, reduced the execution time up to 50%. Data reduction also helped to increase the network accuracy up to 90%. The likelihood of organ dysfunction determined by coupled ANN and scoring method technique can be much more efficient than the LODS model alone because the SOM could successfully classify the patients in 64 classes. The primary patient classification plays a major role in increasing the efficiency of an estimator.

Keywords: artificial neural network; data mining; mortality prediction; optimization; organ dysfunction
Corresponding author: Mahmood Mahmoodi-Eshkaftaki, Department of Mechanical Engineering of Biosystems, Jahrom University, P.O. Box 74135-111, Jahrom, Iran, E-mail: .

  1. Research funding: None declared.

  2. Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  3. Competing interests: Authors state no conflict of interest.

  4. Informed consent: Informed consent was obtained from all individuals included in this study.

References

1. Sculier, JP, Paesmans, M, Markiewicz, E, Berghmans, T. Scoring systems in cancer patients admitted for an acute complication in a medical intensive care unit. Crit Care Med 2000;28:2786–92. https://doi.org/10.1097/00003246-200008000-00018.Search in Google Scholar PubMed

2. Moemen, ME. Prognostic categorization of intensive care septic patients. World J Crit Care Med 2012;1:67–79. https://doi.org/10.5492/wjccm.v1.i3.67.Search in Google Scholar PubMed PubMed Central

3. Brendan, GC, Jeremy, MK, Raina, MM, Andrew, AK, Robert, WN. Inter-hospital variability in post-cardiac arrest mortality. Resuscitation 2009;80:30–4. https://doi.org/10.1016/j.resuscitation.2008.09.001.Search in Google Scholar PubMed

4. Moreno, RP, Metnitz, PGH, Almeida, E, Jordan, B, Bauer, P, SAPS III-From evaluation of the patient to evaluation of the intensive care unit, Part 2: development of a prognostic model for hospital mortality at ICU. Intensive Care Med 2005;31:1345–55. https://doi.org/10.1007/s00134-005-2763-5.Search in Google Scholar PubMed PubMed Central

5. Zimmerman, JE, Kramer, AA, McNair, DS, Malila, FM. Acute physiology and chronic health evaluation (APACHE) IV: hospital mortality assessment for today’s critically ill patients. Crit Care Med. 2006;34:297–310. https://doi.org/10.1097/01.ccm.0000215112.84523.f0.Search in Google Scholar

6. Higgins, TL, Teres, D, Copes, WS, Nathanson, BH, Stark, M. Assessing contemporary intensive care unit outcome: an updated mortality probability admission model (MPM0-II). Crit Care Med 2007;35:827–35. https://doi.org/10.1097/01.CCM.0000257337.63529.9F.Search in Google Scholar PubMed

7. Le Gall, JR, Lemeshow, S, Saulnier, F. A new simplified acute physiology score (SAPS-II) based on a European/North American multicenter study. J Am Med Assoc 1993;270:2957–63. https://doi.org/10.1001/jama.1993.03510240069035.Search in Google Scholar

8. Arabi, Y, Haddad, S, Goraj, R, Al-Shimemeri, A, Al-Malik, S. Assessment of performance of four mortality prediction systems in a Saudi Arabian intensive care unit. Crit Care (London) 2002;6:166–74. https://doi.org/10.1186/cc1477.Search in Google Scholar PubMed PubMed Central

9. Beal, AL, Cerra, FB. Multiple organ failure syndrome in the 1990s. Systemic inflammatory response and organ dysfunction. J Am Med Assoc 1994;271:226–33. https://doi.org/10.1001/jama.1994.03510270072043.Search in Google Scholar

10. Bodin Khwannimit, MD. Serial evaluation of the MODS, SOFA and LOD scores to predict ICU mortality in mixed critically Ill patients. J Med Assoc Thail 2008;91:1336–43.Search in Google Scholar

11. Uyar, K, Ilhan, A. Diagnosis of heart disease using genetic algorithm based trained recurrent fuzzy neural networks. Procedia Comput Sci 2017;120:588–93. https://doi.org/10.1016/j.procs.2017.11.283.Search in Google Scholar

12. Gortzis, LG, Sakellaropoulos, F, Ilias, I, Stamoulis, K, Dimopoulou, I. Predicting ICU survival: a meta-level approach. BMC Health Serv Res 2008;8:157. https://doi.org/10.1186/1472-6963-8-157.Search in Google Scholar PubMed PubMed Central

13. Lorent, M, Giral, M, Foucher, Y. Net time‐dependent ROC curves: a solution for evaluating the accuracy of a marker to predict disease‐related mortality. Stat Med 2014;33:2379–89. https://doi.org/10.1002/sim.6079.Search in Google Scholar PubMed

14. Bosnjak, A, Montilla, G. Predicting mortality of ICU patients using statistics of physiological variables and support vector machines. Comput Cardiol 2012;39:481–4.Search in Google Scholar

15. Ribas, V, Vellido, A, Ruiz-Rodriguez, J, Rello, J. Severe sepsis mortality prediction with logistic regression over latent factors. Expert Syst Appl 2012;39:15. https://doi.org/10.1016/j.eswa.2011.08.054.Search in Google Scholar

16. Krajnak, M, Xue, J, Kaiser, W, Balloni, W. Combining machine learning and clinical rules to build an algorithm for predicting ICU mortality risk. Comput Cardiol 2012;39:401–4.Search in Google Scholar

17. Granholm, A, Perner, A, Krag, M. Simplified Mortality Score for the Intensive Care Unit (SMS-ICU): protocol for the development and validation of a bedside clinical prediction rule. BMJ Open 2017;7:1–7. https://doi.org/10.1136/bmjopen-2016-015339.Search in Google Scholar PubMed PubMed Central

18. Mahmoodi-Eshkaftaki, M, Ebrahimi, R, Torki-Harchegani, M. Determination of critical conditions for puncturing almonds using coupled response surface methodology and genetic algorithm. Food Technol Biotechnol 2013;51:500–8. https://hrcak.srce.hr/114466.Search in Google Scholar

19. Kohavi, R, Provost, F. On applied research in machine learning, In editorial for the special issue on applications of machine learning and the knowledge discovery process. New York: Columbia University; 1998.Search in Google Scholar

20. Kumar, S, Dabas, C, Godara, S. Classification of brain MRI tumor images: a hybrid approach. Procedia Comput Sci 2017;122:510–7. https://doi.org/10.1016/j.procs.2017.11.400.Search in Google Scholar

21. Kohonen, T. Self-organized formation of topologically correct feature maps. Biol Cybern 1982;43:59–69. https://doi.org/10.1007/bf00337288.Search in Google Scholar

22. Heldwein, MB, Akmal, MAB, Doerr, F, Lehmann, T, Bayer, O, Doenst, T, Logistic organ dysfunction score (LODS): A reliable postoperative risk management score also in cardiac surgical patients. J Cardiothorac Surg 2011;6:1–6. https://doi.org/10.1186/1749-8090-6-110.Search in Google Scholar PubMed PubMed Central

23. Wang, S, Phillips, P, Yang, J, Sun, P, Zhang, Y. Magnetic resonance brain classification by a novel binary particle swarm optimization with mutation and time-varying acceleration coefficients. Biomed Eng 2016;61:431–41. https://doi.org/10.1515/bmt-2015-0152.Search in Google Scholar PubMed

24. Johnson, S, Avr, S. Comparison of different scoring systems used in the intensive care unit. J Pulm Respir Med 2015;5:1–4. https://doi.org/10.4172/2161-105x.1000276.Search in Google Scholar

25. Kao, R, Priestap, F, Donner, A. Develop a regional ICU mortality prediction model during the first 24 h of ICU admission utilizing MODS and NEMS with six other independent variables from the critical care information system (CCIS) Ontario, Canada. J Intensive Care Med 2016;4:1–12. https://doi.org/10.1186/s40560-016-0143-6.Search in Google Scholar PubMed PubMed Central

26. Rendy, L, Sapan, HB, Kalesaran, LTB. Multiple organ dysfunction syndrome (MODS) prediction score in multi-trauma patients. Int J Surg Open 2017;8:1‒6. https://doi.org/10.1016/j.ijso.2017.05.003.Search in Google Scholar
Received: 2018-11-03
Accepted: 2020-03-27
Published Online: 2020-06-29
Published in Print: 2020-11-18

© 2020 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Reviews
  3. A review of foot pose and trajectory estimation methods using inertial and auxiliary sensors for kinematic gait analysis
  4. EEG Source Imaging (ESI) utility in clinical practice
  5. Research articles
  6. A multi-source co-frequency stimulus method for electroencephalogram (EEG) enhancement
  7. Analysis of statistical coefficients and autoregressive parameters over intrinsic mode functions (IMFs) for epileptic seizure detection
  8. Scalp electroencephalography (sEEG) based advanced prediction of epileptic seizure time and identification of epileptogenic region
  9. A simple model to detect atrial fibrillation via visual imaging
  10. Insertion torque/time integral as a measure of primary implant stability
  11. A microelectromechanical system (MEMS) capacitive accelerometer-based microphone with enhanced sensitivity for fully implantable hearing aid: a novel analytical approach
  12. Integrating artificial neural network and scoring systems to increase the prediction accuracy of patient mortality and organ dysfunction
  13. Sparse-FCM and Deep Convolutional Neural Network for the segmentation and classification of acute lymphoblastic leukaemia
https://doi.org/10.1515/bmt-2018-0216
Keywords for this article
artificial neural network; data mining; mortality prediction; optimization; organ dysfunction

Articles in the same Issue

  1. Frontmatter
  2. Reviews
  3. A review of foot pose and trajectory estimation methods using inertial and auxiliary sensors for kinematic gait analysis
  4. EEG Source Imaging (ESI) utility in clinical practice
  5. Research articles
  6. A multi-source co-frequency stimulus method for electroencephalogram (EEG) enhancement
  7. Analysis of statistical coefficients and autoregressive parameters over intrinsic mode functions (IMFs) for epileptic seizure detection
  8. Scalp electroencephalography (sEEG) based advanced prediction of epileptic seizure time and identification of epileptogenic region
  9. A simple model to detect atrial fibrillation via visual imaging
  10. Insertion torque/time integral as a measure of primary implant stability
  11. A microelectromechanical system (MEMS) capacitive accelerometer-based microphone with enhanced sensitivity for fully implantable hearing aid: a novel analytical approach
  12. Integrating artificial neural network and scoring systems to increase the prediction accuracy of patient mortality and organ dysfunction
  13. Sparse-FCM and Deep Convolutional Neural Network for the segmentation and classification of acute lymphoblastic leukaemia
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 14.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/bmt-2018-0216/html?lang=en
Scroll to top button