Preconditions and multilevel models in studying post-surgical adverse outcomes

A variety of adverse outcomes, such as kidney injury, death, cardiac injury, and respiratory failure affect a significant number of patients after surgery. Previous research has investigated possible predictors for these outcomes, including features extracted from physiologic time series, change points in the time series, and prior conditions. This study builds upon this previous work by further exploring time series statistics, such as entropy, long-term memory, and change point analysis, as possibly predictive measures of volatility. These statistics are further examined by conditioning on prior conditions using multilevel modeling. For prediction, we use both random forest models and the robust method of L1 regularized logistic regression. Predictive results from these models are evaluated using receiver operating characteristic curves and their area under the curve values. While the developed models did not show improvements in predictive accuracy, they did show that change point analysis and measures of entropy and long-term memory can be useful tools in predicting post-surgical adverse outcomes. The multilevel models show the important interactions between prior conditions and time series statistics for predicting adverse outcomes.

[1]  W. Benitz.  Mortality Reduction by Heart Rate Characteristic Monitoring in Very Low Birth Weight Neonates: A Randomized Trial , 2012 .

[2]  Zachary Terner,et al.  Automated prediction of adverse post-surgical outcomes , 2014, 2014 Systems and Information Engineering Design Symposium (SIEDS).

[3]  M. Keegan,et al.  Intraoperative Tidal Volume as a Risk Factor for Respiratory Failure after Pneumonectomy , 2006, Anesthesiology.

[4]  P. Solomon,et al.  Conventional and advanced time series estimation: application to the Australian and New Zealand Intensive Care Society (ANZICS) adult patient database, 1993-2006. , 2011, Journal of evaluation in clinical practice.

[5]  Maria Eduarda Silva,et al.  Beyond long memory in heart rate variability: an approach based on fractionally integrated autoregressive moving average time series models with conditional heteroscedasticity. , 2013, Chaos.

[6]  Nikolaos G Baikoussis,et al.  Strategies to prevent intraoperative lung injury during cardiopulmonary bypass , 2010, Journal of cardiothoracic surgery.

[7]  Achim Zeileis,et al.  Strucchange: An R package for testing for structural change in linear regression models , 2002 .

[8]  S. Socransky,et al.  Multilevel analysis of bacterial counts from chronic periodontitis after root planing/scaling, surgery, and systemic and local antibiotics: 2-year results , 2013, Journal of oral microbiology.

[9]  Honglak Lee,et al.  Efficient L1 Regularized Logistic Regression , 2006, AAAI.

[10]  Chandra Erdman,et al.  A fast Bayesian change point analysis for the segmentation of microarray data , 2008, Bioinform..

[11]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[12]  David S. Matteson,et al.  A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data , 2013, 1306.4933.

[13]  W. Henderson,et al.  Multifactorial Risk Index for Predicting Postoperative Respiratory Failure in Men After Major Noncardiac Surgery , 2000, Annals of surgery.

[14]  S. Lage,et al.  Acute kidney injury prediction following elective cardiac surgery: AKICS Score. , 2007, Kidney international.

[15]  Kelvyn Jones,et al.  Individuals and their ecologies: analysing the geography of chronic illness within a multilevel modelling framework , 1995 .

[16]  G. Moon,et al.  Context, composition and heterogeneity: using multilevel models in health research. , 1998, Social science & medicine.

[17]  Idris A. Eckley,et al.  changepoint: An R Package for Changepoint Analysis , 2014 .

[18]  J. Leung,et al.  Relative Importance of Preoperative Health Status Versus Intraoperative Factors in Predicting Postoperative Adverse Outcomes in Geriatric Surgical Patients , 2001, Journal of the American Geriatrics Society.

[19]  Ashley C. Mull.  Cardiac uncoupling and heart rate variability stratify ICU patients by mortality: A study of 2088 trauma patients , 2007 .

[20]  T. Osler,et al.  Complications in surgical patients. , 2002, Archives of surgery.

[21]  Nassib G. Chamoun,et al.  Hospital Stay and Mortality Are Increased in Patients Having a “Triple Low” of Low Blood Pressure, Low Bispectral Index, and Low Minimum Alveolar Concentration of Volatile Anesthesia , 2012, Anesthesiology.

[22]  Maria Eduarda Silva,et al.  Enhancing scaling exponents in heart rate by means of fractional integration , 2013, Computing in Cardiology 2013.

[23]  C. Vachon,et al.  Intraoperative ventilator settings and acute lung injury after elective surgery: a nested case control study , 2008, Thorax.

[24]  C. To.  Predictors of atrial fibrillation after coronary artery surgery. , 1997 .

[25]  Kurt Hornik,et al.  Testing and dating of structural changes in practice , 2003, Comput. Stat. Data Anal..

[26]  D. T. Kaplan,et al.  Aging and the complexity of cardiovascular dynamics. , 1991, Biophysical journal.

[27]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[28]  K. Pickett,et al.  Multilevel analyses of neighbourhood socioeconomic context and health outcomes: a critical review , 2001, Journal of epidemiology and community health.

[29]  W. Bouwmeester.  Prediction models: systematic reviews and clustered study data , 2012 .

[30]  Sharareh R. Niakan Kalhori,et al.  Bayesian autoregressive multilevel modeling of burden of diseases, injuries and risk factors in Iran 1990 - 2013. , 2014, Archives of Iranian medicine.

[31]  Sophia Ananiadou,et al.  Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty , 2009, ACL.

[32]  Andrew Gelman,et al.  Data Analysis Using Regression and Multilevel/Hierarchical Models: Missing-data imputation , 2006 .

[33]  Zachary Terner,et al.  Time series forecasts and volatility measures as predictors of post-surgical death and kidney injury , 2014, 2014 IEEE Healthcare Innovation Conference (HIC).

[34]  L. Cohn,et al.  Predictors of atrial fibrillation after coronary artery surgery. Current trends and impact on hospital resources. , 1996, Circulation.

[35]  Linda L. Liu,et al.  Predicting Adverse Postoperative Outcomes in Patients Aged 80 Years or Older , 2000, Journal of the American Geriatrics Society.

[36]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[37]  Douglas E. Lake,et al.  Heart rate characteristics monitoring for neonatal sepsis , 2006, IEEE Transactions on Biomedical Engineering.

[38]  M. Newman,et al.  Intraoperative physiologic variables and outcome in cardiac surgery: Part I. In-hospital mortality. , 2000, Annals of Thoracic Surgery.

[39]  J. Moorman,et al.  Predicting the need for urgent intubation in a surgical/trauma intensive care unit. , 2013, Surgery.

[40]  Benoit M Dawant,et al.  Reduced Heart Rate Volatility: An Early Predictor of Death in Trauma Patients , 2004, Annals of surgery.

[41]  Ping Yang,et al.  Adaptive Change Point Detection for Respiratory Variables , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[42]  Peter Bühlmann,et al.  MissForest - non-parametric missing value imputation for mixed-type data , 2011, Bioinform..

[43]  C. Canver,et al.  Intraoperative and postoperative risk factors for respiratory failure after coronary bypass. , 2003, The Annals of thoracic surgery.

[44]  Thai Vu,et al.  Clinical Applications of Heart Rate Variability in the Triage and Assessment of Traumatically Injured Patients , 2011, Anesthesiology research and practice.

[45]  F. Abelha,et al.  Determinants of postoperative acute kidney injury , 2009, Critical care.

[46]  J. Church,et al.  Key Factors Associated With Postoperative Complications in Patients Undergoing Colorectal Surgery , 2013, Diseases of the colon and rectum.

[47]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[48]  W. Browner,et al.  Association of Perioperative Myocardial Ischemia with Cardiac Morbidity and Mortality in Men Undergoing Noncardiac Surgery , 1990 .

[49]  King-Teh Lee,et al.  IN-HOSPITAL MORTALITY , 2013 .

[50]  E F Cook,et al.  Derivation and prospective validation of a simple index for prediction of cardiac risk of major noncardiac surgery. , 1999, Circulation.

[51]  A K Wagner,et al.  Segmented regression analysis of interrupted time series studies in medication use research , 2002, Journal of clinical pharmacy and therapeutics.

[52]  J. Tschopp,et al.  Risk Factors for Acute Lung Injury After Thoracic Surgery for Lung Cancer , 2003, Anesthesia and analgesia.

[53]  Donald E. Brown,et al.  Measures of Entropy and Change Point Analysis as Predictors of Post-Surgical Adverse Outcomes , 2014, 2014 IEEE International Conference on Bioinformatics and Bioengineering.

[54]  S. Aronson,et al.  Acute Kidney Injury following Cardiac Surgery: Role of Perioperative Blood Pressure Control , 2011, American Journal of Nephrology.

[55]  F. Fowkes,et al.  Risk factors for postoperative death following elective surgical repair of abdominal aortic aneurysm: results from the UK Small Aneurysm Trial , 2000, The British journal of surgery.

[56]  Thomas Lengauer,et al.  Permutation importance: a corrected feature importance measure , 2010, Bioinform..

[57]  C. Reid,et al.  Hospital-level associations with 30-day patient mortality after cardiac surgery: a tutorial on the application and interpretation of marginal and multilevel logistic regression , 2012, BMC Medical Research Methodology.