ChiaMing Chen
ABSTRACT
The rapid shallow breathing index (RSBI) is commonly used clinically for predicting the outcome of ventilator weaning. However, the results of prediction are controversial. This study employs decision tree analysis of data mining to construct ventilator weaning prediction model in order to improve the accuracy of ventilator weaning prediction and medication quality. Between January 2014 and December 2015, 656 patients with respiratory failure using mechanical ventilator in the ICU of a regional hospital in central Taiwan were included. We recorded demographic and clinical data and analyzed these data with C4.5 decision tree model and RSBI. From decision tree model, we found that admission source and the reason for using ventilator were important predictors of ventilator weaning. The prediction model constructed by decision tree achieves 78% of sensitivity, 74% of specificity and 77% of accuracy in test set for predicting whether ventilator weaning will be successful within 21 days, while using RSBI<105 can reach 78%t of sensitivity with only 50% of specificity and 72% of accuracy. Base on this result, the decision tree model is a good method in predicting ventilator weaning. Furthermore, our study could help clinicians in clinical decision making to improve ventilator weaning rate.
- C. Chiao, K. Ksobiech, C.Y. Wei. 2014. National health insurance and life satisfaction in late life: longitudinal findings from a natural experiment in Taiwan. Journal of Public Health. 36(2), 308--16.Google Scholar
Cross Ref
- Ministry of the Interior. 2008. White Paper of Population Policy. 2008. Taipei.Google Scholar
- S.H. Cheng, I.S. Jan, P.C. Liu. 2008. The soaring mechanic ventilator utilization under a universal health insurance in Taiwan. Health Policy. 86(2-3), 288--294.Google ScholarCross Ref
- E.C. Goncalves, A.F. Lago, E.C. Silva, M.B. de Almeida,A. Basile-Filho, A.C. Gastaldi. 2017. How Mechanical Ventilation Measurement, Cutoff and Duration Affect Rapid Shallow Breathing Index Accuracy: A Randomized Trial. Journal of Clinical Medicine Research. 9(4), 289--296.Google ScholarCross Ref
- K.L. Yang, M.J. Tobin. 1991. A prospective study of indexes predicting the outcome of trials of weaning from mechanical ventilation. New England Journal of Medicine. 324(21), 1445-- 1450.Google ScholarCross Ref
- M. Meade, G. Guyatt, D. Cook, L. Griffith, T. Sinuff, C. Kergl, J. Mancebo, A. Esteban, S. Epstein. 2001. Predicting success in weaning from mechanical ventilation. Chest. (120:6_suppl), 400S--424S.Google Scholar
- C.S.V. Barbas, G.C. Lopes, D.F. Vieira, L.P. Couto, L.K. Dourado, E. Caser, S.R. and Publishing, S. R. 2012. Respiratory evaluation of patients requiring ventilator support due to acute respiratory failure. Open Journal of Nursing. 2, 336--340.Google ScholarCross Ref
- H.M. Lu, L.K. Chen, J.D. Wang, M.C. Hung, M.S. Lin, Y.H. Yan, C.R. Chen, P.S. Fan, L.C. Huang, K.N. Kuo. 2012. Outcomes of prolonged mechanic ventilation: a discrimination model based on longitudinal health insurance and death certificate data. BMC health services study. 12(1), 100.Google Scholar
- J. Boles, J. Bion, A. Connors, M. Herridge, B. Marsh, C. Melot, R. Pearl, H. Silverman, M. Stanchina, A. Vieillard-Baron, T. Welte. 2007. Weaning from mechanical ventilation. The European respiratory journal. 29(5), 1033--1056.Google Scholar
- S. Caroleo, F. Agnello, K. Abdallah, E, Santangelo, B. Amantea. 2007. Weaning from mechanical ventilation: an open issue. Minerva anestesiologica. (73:7/8), 417--427.Google Scholar
- S. Sahetya, S. Allgood, P.C. Gay, N. Lechtzin. 2016. Long-term mechanical ventilation. Clinics in Chest Medicine. 37(4), 753--63.Google ScholarCross Ref
- A.R. Mahoori, S. Nowruzinia, R. Farasatkish, G.A. Mollasadeghi, A. Abbas. 2007. Assessment of the rapid shallow breathing index as a predictor of weaning of patients with prolonged mechanical ventilation. Tanaffos. 6(3), 30--35.Google Scholar
- J. Han, M. Kamber. 2006. Data mining: Concepts and techniques (2nd Ed.), Morgan Kaufmann. Google ScholarDigital Library
- A.G. Singal, A. Mukherjee, B.J. Elmunzer, et al. 2013. Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma. The American Journal of Gastroenterology. 108(11). 1723--1730.Google ScholarCross Ref
- N. Li, C. Yang, L. Zhang. 2017. The Purpose for the HER2 Positive Breast Cancer Treatment Research. In Proceedings of the 7th International Conference on Bioscience, Biochemistry and Bioinformatics (ICBBB '17). ACM, New York, NY, USA, 34--37. Google ScholarDigital Library
- C. Arizmendi, J. Viviescas, H. González, B. Giraldo. 2014. Patients classification on weaning trials using neural networks and wavelet transform. Studies in health technology and informatics. 202, 107--110.Google Scholar
- A. Garde, R. Schroeder, A. Voss, P. Caminal, S. Benito, B. Giraldo. 2010. Patients on weaning trials classified with support vector machines. Physiological measurement. 31(7), 979--993.Google Scholar
- J.D. Olden, M.K. Joy, R.G. Death. 2004. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecological Modeling. (178:s 3--4), 389--397.Google Scholar
- P.K. Singh, M.S. and Husain. 2014. Methodological study of opinion mining and sentiment analysis techniques. International Journal on Soft Computing. 5(1), 11--21.Google ScholarCross Ref
- J.R. Quinlan. 1987. Generating production rules from decision trees. Morgan Kaufmann Publishers, 304--307. Google ScholarDigital Library
- H.K. Chou, S. Su, H.G. Hwang, M.T. Tsai, L.C. Woung. 2006. Utilization of a Decision Tree for High Expenditure Patients in the Emergency Department. Taiwan Journal of Public Health. 25(6), 430--439.Google Scholar
- Y.J. Su, T.K. Wu, Y.R. Meng. 2007. Application of decision tree algorithm to the identification of students with learning disabilities. Journal of Information Technology and Applications. 2(2), 107--115.Google Scholar
- J.R. Quinlan. 1986. Induction of decision trees. Machine learning. 1(1), 81--106. Google ScholarDigital Library
- J.R. Quinlan, J. Ross. 1993. C4.5: Programs for machine learning. Morgan Kaufmann Publishers. Google ScholarDigital Library
- P.H. Yang, J.Y. Hung, C.J. Yang, J.R. Tsai, T.H. Wang, J.C. Lee, M.S. Huang. 2008. Successful weaning predictors in a respiratory care center in Taiwan. The Kaohsiung journal of medical sciences. 24(2), 85--91.Google Scholar
- E. Estenssoro, F. González, E. Laffaire, H. Canales, G. Sáenz, R. Reina, A. Dubin, A. 2005.Shock on admission day is the best predictor of prolonged mechanical ventilation in the ICU. Chest. 127(2), 598--603.Google ScholarCross Ref
- J. Stauffer, N. Fayter, B. Graves, M. Cromb, J. Lynch, P. Goebel. 1993. Survival following mechanical ventilation for acute respiratory failure in adult men. Chest. 104(4), 1222--1229.Google ScholarCross Ref
- P.L. Jen. 2007. The Relationship between Nosocomial Infections and Medical Resources Consumption as well as the Prognosis in Long-Term Care Facilities? Example of Veteran Healthcare System Nursing Home. Master's thesis. China Medical University, Taichung, Taiwan.Google Scholar
Index Terms
- Early Prediction of Ventilator Weaning with Decision Tree Analysis
Recommendations
Design and Construction of a Microcontroller-Based Ventilator Synchronized with Pulse Oximeter
AbstractThis study aims to introduce a novel device with which mechanical ventilator and pulse oximeter work in synchronization. Serial communication technique was used to enable communication between the pulse oximeter and the ventilator. The SpO2 value ...
Construction of prediction module for successful ventilator weaning
IEA/AIE'07: Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systemsVentilator weaning is the process of discontinuing mechanical ventilation from patients with respiratory failure. Previous investigations reported that 39%-40% of the intensive care unit (ICU) patients need mechanical ventilator for sustaining their ...
Decision-making model for early diagnosis of congestive heart failure using rough set and decision tree approaches
Graphical abstractDisplay Omitted Highlights We have developed a decision-making model for CHF that uses RS and DT approaches. The model provides five critical factors and four decision rules associated with CHF. The four rules were found to be ...
Comments