Customized Prediction of Short Length of Stay Following Elective Cardiac Surgery in Elderly Patients Using a Genetic Algorithm

Joon Lee, Sapna Govindan, Leo A. Celi, Kamal R. Khabbaz, Balachundhar Subramaniam

Beth Israel Deaconess Medical Center, Boston, USA.
Harvard-MIT Division of Health Sciences and Technology, Cambridge, USA.
School of Public Health and Health Systems, University of Waterloo, Waterloo, Canada.

DOI: 10.4236/wjcs.2013.35034                

Abstract

Objective: To develop a customized short LOS (<6 days) prediction model for geriatric patients receiving cardiac surgery, using local data and a computational feature selection algorithm. Design: Utilization of a machine learning algorithm in a prospectively collected STS database consisting of patients who received cardiac surgery between January 2002 and June 2011. Setting: Urban tertiary-care center. Participants: Geriatric patients aged 70 years or older at the time of cardiac surgery. Interventions: None. Measurements and Main Results: Predefined morbidity and mortality events were collected from the STS database. 23 clinically relevant predictors were investigated for short LOS prediction with a genetic algorithm (GenAlg) in 1426 patients. Due to the absence of an STS model for their particular surgery type, STS risk scores were unavailable for 771 patients. STS prediction achieved an AUC of 0.629 while the GenAlg achieved AUCs of 0.573 (in those with STS scores) and 0.691 (in those without STS scores). Among the patients with STS scores, the GenAlg features significantly associated with shorter LOS were absence of congestive heart failure (CHF) (OR = 0.59, p = 0.04), aortic valve procedure (OR = 1.54, p = 0.04), and shorter cross clamp time (OR = 0.99, p = 0.004). In those without STS prediction, short LOS was significantly correlated with younger age (OR = 0.93, p < 0.001), absence of CHF (OR = 0.53, p = 0.007), no preoperative use of beta blockers (OR = 0.66, p = 0.03), and shorter cross clamp time (OR = 0.99, p < 0.001). Conclusion: While the GenAlg-based models did not outperform STS prediction for patients with STS risk scores, our local-data-driven approach reliably predicted short LOS for cardiac surgery types that do not allow STS risk calculation. We advocate that each institution with sufficient observational data should build their own cardiac surgery risk models.

Keywords

Cardiac Surgery; Elderly; Length of Stay; Risk Prediction; Genetic Algorithm

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	B. H. Scott, F. C. Seifert, R. Grimson and P. S. A. Glass, “Octogenarians Undergoing Coronary Artery Bypass Graft Surgery: Resource Utilization, Postoperative Mortality, and Morbidity,” Journal of Cardiothoracic and Vascular Anesthesia, Vol. 19, No. 5, 2005, pp. 583-588. doi:10.1053/j.jvca.2005.03.030
[2]	S. A. M. Nashef, F. Roques, P. Michel, E. Gauducheau, S. Lemeshow and R. Salamon, “European System for Cardiac Operative Risk Evaluation (EuroSCORE),” European Journal Cardio-Thoracic Surgery, Vol. 16, No. 1, 1999, pp. 9-13. doi:10.1016/S1010-7940(99)00134-7
[3]	D. M. Shahian, S. M. O’Brien, G. Filardo, V. A. Ferraris, C. K. Haan, J. B. Rich, et al., “The Society of Thoracic Surgeons 2008 Cardiac Surgery Risk Models: Part 1— Coronary Artery Bypass Grafting Surgery,” The Annals of Thoracic Surgery, Vol. 88, Supplement 1, 2009, pp. S2-S22. doi:10.1016/j.athoracsur.2009.05.053
[4]	P. Pinna-Pintor, M. Bobbio, S. Colangelo, F. Veglia, M. Giammaria, D. Cuni, et al., “Inaccuracy of Four Coronary Surgery Risk-Adjusted Models to Predict Mortality in Individual Patients,” European Journal Cardio-Thoracic Surgery, Vol. 21, No. 2, 2002, pp. 199-204. doi:10.1016/S1010-7940(01)01117-4
[5]	W. F. Northrup, R. W. Emery, D. M. Nicoloff, T. J. Lillehei, A. R. Holter and D. P. Blake, “Opposite Trends in Coronary Artery and Valve Surgery in a Large Multisurgeon Practice, 1979-1999,” The Annals of Thoracic Surgery, Vol. 77, No. 2, 2004, pp. 488-495. doi:10.1016/S0003-4975(03)01359-6
[6]	A. Maslow, P. Casey, A. Poppas, C. Schwartz and A. Singh, “Aortic Valve Replacement with or Without Coronary Artery Bypass Graft Surgery: The Risk of Surgery in Patients ≥80 Years Old,” Journal of Cardiothoracic and Vascular Anesthesia, Vol. 24, No. 1, 2010, pp. 18-24. doi:10.1053/j.jvca.2009.07.010
[7]	J. G. M. J. H. Heijmans and P. M. H. J. Roekaerts, “Risk Stratification for Adverse Outcome in Cardiac Surgery,” European Journal of Anesthesiology, Vol. 20, No. 7, 2003, pp. 515-527. doi:10.1097/00003643-200307000-00002
[8]	R. G. A. Ettema, L. M. Peelen, M. J. Schuurmans, A. P. Nierich, C. J. Kalkman and K. G. M. Moons, “Prediction Models for Prolonged Intensive Care Unit Stay after Cardiac Surgery; Systematic Review and Validation Study,” Circulation, Vol. 122, No. 7, 2010, pp. 682-689. doi:10.1161/CIRCULATIONAHA.109.926808
[9]	H. K. Song, B. S. Diggs, M. S. Slater, S. W. Guyton, R. M. Ungerleider and K. F. Welke, “Improved Quality and Cost-Effectiveness of Coronary Artery Bypass Grafting in the United States from 1988 to 2005,” The Journal of Thoracic and Cardiovascular Surgery, Vol. 137, No. 1, 2009, pp. 65-69. doi:10.1016/j.jtcvs.2008.09.053
[10]	O. V. Hein, J. Birnbaum, K. Wernecke, M. England, W. Konertz and C. Spies, “Prolonged Intensive Care Unit Stay in Cardiac Surgery: Risk Factors and Long-Term-Survival,” The Annals of Thoracic Surgery, Vol. 81, No. 3, 2006, pp. 880-885. doi:10.1016/j.athoracsur.2005.09.077
[11]	R. Atoui, F. Ma, Y. Langlois and J. F. Morin, “Risk Factors for Prolonged Stay in the Intensive Care Unit and on the Ward after Cardiac Surgery,” Journal of Cardiac Surgery, Vol. 23, No. 2, 2008, pp. 99-106. doi:10.1111/j.1540-8191.2007.00564.x
[12]	D. P. Janssen, L. Noyez, C. Wouters and R. M. Brouwer, “Preoperative Prediction of Prolonged Stay in the Intensive Care Unit for Coronary Bypass Surgery,” European Journal Cardio-Thoracic Surgery, Vol. 25, No. 2, 2004, pp. 203-207. doi:10.1016/j.ejcts.2003.1
[13]	D. T. Wong, D. C. Cheng, R. Kustra, R. Tibshirani, J. Karski, J. Carroll-Munro, et al., “Risk Factors of Delayed Extubation, Prolonged Length of Stay in the Intensive Care Unit, and Mortality in Patients Undergoing Coronary Artery Bypass Graft with Fast-Track Cardiac Anesthesia: A New Cardiac Risk Score,” Anesthesiology, Vol. 91, No. 4, 1999, pp. 936-44. doi:10.1097/00000542-199910000-00012
[14]	S. N. Sivanandam and S. N. Deepa, “Introduction to Genetic Algorithms,” Springer, Berlin, 2008.
[15]	M. Y. Rady, T. Ryan and N. J. Starr, “Perioperative De-Terminants of Morbidity and Mortality in Elderly Patients Undergoing Cardiac Surgery,” Critical Care Medicine, Vol. 26, No. 2, 1998, pp. 225-235. doi:10.1097/00003246-199802000-00016
[16]	D. M. Shahian, S. M. O’Brien, G. Filardo, V. A. Ferraris, C. K. Haan, J. B. Rich, et al., “The Society of Thoracic Surgeons 2008 Cardiac Surgery Risk Models: Part 3— Valve Plus Coronary Artery Bypass Grafting Surgery,” The Annals of Thoracic Surgery, Vol. 88, Supplement 1, 2009, pp. S43-S62. doi:10.1016/j.athoracsur.2009.05.055
[17]	L. A. Celi, S. Galvin, G. Davidzon, J. Lee, D. Scott and R. Mark, “A Database-Driven Decision Support System: Customized Mortality Prediction,” Journal of Personalized Medicine, Vol. 2, No. 4, 2012, pp. 138-148. doi:10.3390/jpm2040138
[18]	M. Smith, R. Saunders, L. Stuckhardt and J. M. McGinnis, “Best Care at Lower Cost: The Path to Continuously Learning Health Care in America,” Institute of Medicine, Washington DC, 2012.
[19]	V. Parsonnet, D. Dean and A. D. Bernstein, “A Method of Uniform Stratification of Risk for Evaluating the Results of Surgery in Acquired Adult Heart Disease,” Circulation, Vol. 79, No. 6, 1989, pp. I3-I12.
[20]	S. A. Nashef, F. Roques, P. Michel, E. Gauducheau, S. Lemeshow and R. Salamon, “European System for Cardiac Operative Risk Evaluation (EuroSCORE),” European Journal Cardio-Thoracic Surgery, Vol. 16, No. 1, 1999, pp. 9-13. doi:10.1016/S1010-7940(99)00134-7
[21]	A. K. Akobeng, “Understanding Diagnostic Tests 3: Receiver Operating Characteristic Curves,” Acta Paediatrica, Vol. 96, No. 5, 2007, pp. 644-647. doi:10.1111/j.1651-2227.2006.00178.x