Top

Intensive Care Medicine

Published in:

01-02-2004 | Original

Prediction of mortality in an Indian intensive care unit

Comparison between APACHE II and artificial neural networks

Authors: Ashish Nimgaonkar, Dilip R. Karnad, S. Sudarshan, Lucila Ohno-Machado, Isaac Kohane

Published in: Intensive Care Medicine | Issue 2/2004

Abstract

Objective

To compare hospital outcome prediction using an artificial neural network model, built on an Indian data set, with the APACHE II (Acute Physiology and Chronic Health Evaluation II) logistic regression model.

Design

Analysis of a database containing prospectively collected data.

Setting

Medical-neurological ICU of a university hospital in Mumbai, India.

Subjects

Two thousand sixty-two consecutive admissions between 1996 and1998.

Interventions

None.

Measurements and results

The 22 variables used to obtain day-1 APACHE II score and risk of death were recorded. Data from 1,962 patients were used to train the neural network using a back-propagation algorithm. Data from the remaining 1,000 patients were used for testing this model and comparing it with APACHE II. There were 337 deaths in these 1,000 patients; APACHE II predicted 246 deaths while the neural network predicted 336 deaths. Calibration, assessed by the Hosmer-Lemeshow statistic, was better with the neural network (Ĥ=22.4) than with APACHE II (Ĥ=123.5) and so was discrimination (area under receiver operating characteristic curve =0.87 versus 0.77, p=0.002). Analysis of information gain due to each of the 22 variables revealed that the neural network could predict outcome using only 15 variables. A new model using these 15 variables predicted 335 deaths, had calibration (Ĥ=27.7) and discrimination (area under receiver operating characteristic curve =0.88) which was comparable to the 22-variable model (p=0.87) and superior to the APACHE II equation (p<0.001).

Conclusion

Artificial neural networks, trained on Indian patient data, used fewer variables and yet outperformed the APACHE II system in predicting hospital outcome.

Available only for authorised users

Knaus WA, Draper EA, Wagner DP, Zimmerman JE (1985) APACHE II: a severity of disease classification system. Crit Care Med 13:818–829CrossRef

Knaus WA, Wagner DP, Draper EA, Zimmerman JE, Bergner M, Bastos PG, Sirio CA, Murphy DJ, Lotring T, Damiano (1991) The APACHE III prognostic system. Risk prediction of hospital mortality for critically ill hospitalized adults. Chest 100:1619–1636CrossRef

Le Gall JR, Lemeshow S, Saulnier F (1993) A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. JAMA 270:2957–2963CrossRef

Lemeshow S, Le Gall JR (1994) Modeling the severity of illness of ICU patients. A systems update. JAMA 272:1049–1055CrossRef

Lemeshow S, Teres D, Klar J, Avrunin JS, Gehlbach SH, Rapoport J (1993) Mortality Probability Models (MPM II) based on an international cohort of intensive care unit patients. JAMA 270:2478–2486CrossRef

Cross SS, Harrison RF, Kennedy RL (1995) Introduction to neural networks. Lancet 346:1075–1079CrossRef

Hinton GE (1992) How neural networks learn from experience. Sci Am 267:144–151CrossRef

Frize M, Ennett CM, Stevenson M, Trigg HC (2001) Clinical decision support systems for intensive care units: using artificial neural networks. Med Eng Phys 23:217–225CrossRef

Hanson CW 3rd, Marshall BE (2001) Artificial intelligence applications in the intensive care unit. Crit Care Med 29:427–435CrossRef

10.

Dybowski R, Weller P, Chang R, Gant V (1996) Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. Lancet 347:1146–1150CrossRef

11.

Doig GS, Inman KJ, Sibbald WJ, Martin CM, Robertson JM (1993) Modeling mortality in the intensive care unit: comparing the performance of a back-propagation, associative-learning neural network with multivariate logistic regression. Proc Annu Symp Comput Appl Med Care 361–365

12.

Clermont G, Angus DC, DiRusso SM, Griffin M, Linde-Zwirble WT (2001) Predicting hospital mortality for patients in the intensive care unit: a comparison of artificial neural networks with logistic regression models. Crit Care Med 29:291–296CrossRef

13.

Angus DC, Sirio CA, Clermont G, Bion J (1997) International comparisons of critical care outcome and resource consumption. Crit Care Clin 13:389–407CrossRef

14.

Markgraf R, Deutschinoff G, Pientka L, Scholten T (2000) Comparison of acute physiology and chronic health evaluations II and III and simplified acute physiology score II: a prospective cohort study evaluating these methods to predict outcome in a German interdisciplinary intensive care unit. Crit Care Med 28:26–33CrossRef

15.

Von Bierbrauer A, Riedel S, Cassel W, von Wichert P (1998) Validation of the acute physiology and chronic health evaluation (APACHE) III scoring system and comparison with APACHE II in German intensive care units. Anaesthesist 47:30–38CrossRef

16.

Jacobs S, Chang RW, Lee B (1988) Audit of intensive care: a 30-month experience using the APACHE II severity of disease classification system. Intensive Care Med 14:567–574CrossRef

17.

Arabi Y, Haddad S, Goraj R, Al-Shimemeri A, Al-Malik S (2002) Assessment of performance of four mortality prediction systems in a Saudi Arabian intensive care unit. Crit Care 6:166–174CrossRef

18.

Sirio CA, Tajimi K, Tase C, Knaus WA, Wagner DP, Hirasawa H, Sakanishi N, Katsuya H, Taenaka N (1992) An initial comparison of intensive care in Japan and the United States. Crit Care Med 20:1207–1215CrossRef

19.

Abu-Zidan FM, Plank LD, Windsor JA (2002) Proteolysis in severe sepsis is related to oxidation of plasma protein. Eur J Surg 168:119–123CrossRef

20.

Cavalcante NJ, Sandeville ML, Medeiros EA (2001) Incidence of and risk factors for nosocomial pneumonia in patients with tetanus. Clin Infect Dis 33:1842–1846CrossRef

21.

Shukla VK, Ojha AK, Pandey M, Pandey BL (2001) Pentoxifylline in perforated peritonitis: results of a randomised, placebo controlled trial. Eur J Surg 167:622–624CrossRef

22.

Parikh CR, Karnad DR (1999) Quality, cost and outcome of intensive care in a public hospital in Bombay, India. Crit Care Med 27:1754–1759CrossRef

23.

Tom M (1997) Decision tree learning. Machine learning. McGraw-HIll, New York, pp 55–60

24.

Lemeshow S, Hosmer DW Jr (1982) A review of goodness of fit statistics for use in the development of logistic regression models. Am J Epidemiol 115:92–106CrossRef

25.

Hosmer DW, Lemeshow S (1980) A goodness-of-fit test for the multiple logistic regression model. Commu in Stat A10:1043–1069CrossRef

26.

Hosmer DW, Lemeshow S (1989) Applied logistic regression. Wiley, New York

27.

Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36CrossRef

28.

Hanley JA, McNeil BJ (1983) A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 148:839–843CrossRef

29.

Wong LS, Young JD (1999) A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks. Anaesthesia 54:1048–1054CrossRef

30.

Becalick DC, Coats TJ (2001) Comparison of artificial intelligence techniques with UKTRISS for estimating probability of survival after trauma. UK Trauma and Injury Severity Score. J Trauma 51:123–133CrossRef

31.

Sachdeva RC, Guntupalli KK (1999) International comparisons of outcomes in intensive care units. Crit Care Med 27:2032–2033CrossRef

32.

Atienza F, Martinez-Alzamora N, De Velasco JA, Dreiseitl S, Ohno-Machado (2000) Risk stratification in heart failure using artificial neural networks. Proc AMIA Symp pp 32–36

33.

Dreiseitl S, Ohno-Machado L, Vinterbo S (1999) Evaluating variable selection methods for diagnosis of myocardial infarction. Proc AMIA Symp pp 246–250

34.

Vinterbo S, Ohno-Machado L (2000) A genetic algorithm approach to multi-disorder diagnosis. Artif Intell Med 18:117–132CrossRef

35.

Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Contr 19:716–723CrossRef

Title: Prediction of mortality in an Indian intensive care unit
Comparison between APACHE II and artificial neural networks
Authors: Ashish Nimgaonkar
Dilip R. Karnad
S. Sudarshan
Lucila Ohno-Machado
Isaac Kohane
Publication date: 01-02-2004
Publisher: Springer Berlin Heidelberg
Published in: Intensive Care Medicine / Issue 2/2004
Print ISSN: 0342-4642
Electronic ISSN: 1432-1238
DOI: https://doi.org/10.1007/s00134-003-2105-4

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Prediction of mortality in an Indian intensive care unit

Comparison between APACHE II and artificial neural networks

Abstract

Objective

Design

Setting

Subjects

Interventions

Measurements and results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Design

Setting

Subjects

Interventions

Measurements and results

Conclusion

Please log in to get access to this content

Other articles of this Issue 2/2004

Effects on skeletal muscle of intravenous glutamine supplementation to ICU patients

Patient State Index (PSI) measures depth of sedation in intensive care patients

Volume of activity and occupancy rate in intensive care units. Association with mortality

Transport of critically ill children in a resource-limited setting: alternatives to a specialized retrieval team

The effect of waiving consent on enrollment in a sepsis trial

Relationship of thyroid function to post-traumatic S-100b serum levels in survivors of severe head injury: preliminary results