Volume 24, Issue 4 (Jul 2016)                   JSSU 2016, 24(4): 286-295 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Khalili-Zadeh-Mahani G, Pajoohan M, Derhami V, Khoshnood A. Predicting Calcium Values for Gastrointestinal Bleeding Patients in Intensive Care Unit Using Clinical Variables and Fuzzy Modeling. JSSU. 2016; 24 (4) :286-295
URL: http://jssu.ssu.ac.ir/article-1-3507-en.html
Abstract:   (2503 Views)

Introduction: Reducing unnecessary laboratory tests is an essential issue in the Intensive Care Unit. One solution for this issue is to predict the value of a laboratory test to specify the necessity of ordering the tests. The aim of this paper was to propose a clinical decision support system for predicting laboratory tests values. Calcium laboratory tests of three categories of patients, including upper and lower gastrointestinal bleeding, and unspecified hemorrhage of gastrointestinal tract, have been selected as the case studies for this research.

Method: In this research, the data have been collected from MIMIC-II database. For predicting calcium laboratory values, a Fuzzy Takagi-Sugeno model is used and the input variables of the model are heart rate and previous value of calcium laboratory test.

Results: The results showed that the values of calcium laboratory test for the understudy patients were predictable with an acceptable accuracy. In average, the mean absolute errors of the system for the three categories of the patients are 0.27, 0.29, and 0.28, respectively.

Conclusion: In this research, using fuzzy modeling and two variables of heart rate and previous calcium laboratory values, a clinical decision support system was proposed for predicting laboratory values of three categories of patients with gastrointestinal bleeding. Using these two clinical values as input variables, the obtained results were acceptable and showed the capability of the proposed system in predicting calcium laboratory values. For achieving better results, the impact of more input variables should be studied. Since, the proposed system predicts the laboratory values instead of just predicting the necessity of the laboratory tests; it was more generalized than previous studies. So, the proposed method let the specialists make the decision depending on the condition of each patient.

Full-Text [PDF 1188 kb]   (711 Downloads)    
Type of Study: Original article | Subject: Internal diseases
Received: 2015/11/30 | Accepted: 2016/09/28 | Published: 2016/09/28

References
1. Cismondi F. Reducing unnecessary lab testing in the ICU with artificial intelligence. Int J Med Inform 2013; 82(5): 345-58.
2. Kwok J, Jones B, Unnecessary repeat requesting of tests: an audit in a government hospital immunology laboratory. J Clin Pathol 2005; 58(5): 457-62.
3. Honarmand A, Safavi M, Prediction of arterial blood gas values from arterialized earlobe blood gas values in patients treated with mechanical ventilation. Indian J Crit Care Med 2008; 12(3): 96-101.
4. Kumwilaisak K, et al., Effect of laboratory testing guidelines on the utilization of tests and order entries in a surgical intensive care unit. Crit Care Med 2008; 36(11): 2993-9.
5. Khalifa M, Khalid P. Reducing unnecessary laboratory testing using health informatics applications: a case study on a tertiary care hospital. Procedia Comput Sci 2014; 37: 253-60.
6. Cismondi F, Fialho AS, Vieira SM, Sousa JM, Reti SR, Celi LA, Howell MD, Finkelstein SN. Predicting laboratory testing in intensive care using fuzzy and neural modeling. Fuzzy Systems, IEEE International Conference 2011: 2096-103.
7. Clifford GD, Scott DJ, Villarroel M. User guide and documentation for the MIMIC II database. MIMIC-II database version 2009; 2: 95.
8. Han J, Kamber M, Pei J, Data Mining: Concepts and Techniques. San Francisco, CA, itd: Morgan Kaufman; 2011: pp.113-4.
9. Jang J-S R, Sun C-T, Mizutani E. Neuro-fuzzy and soft computing; a computational approach to learning and machine intelligence. Prentice-Hall International 1997: 104-6.
10. Hug C W, Clifford G D. An analysis of the errors in recorded heart rate and blood pressure in the ICU using a complex set of signal quality metrics. Computers in Cardiology 2007: 641-4.
11. Abhyankar S, Demner-Fushman D, McDonald C J, Standardizing clinical laboratory data for secondary use. J Biomed Inform 2012; 45(4): 642-50.

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author


© 2018 All Rights Reserved | SSU_Journals

Designed & Developed by : Yektaweb