Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards

Critical Care Medicine

Volumn 44, Issue 2, 2016, Pages 368-374

  Churpek, Matthew M ^a   Yuen, Trevor C ^a   Winslow, Christopher ^b   Meltzer, David O ^a   Kattan, Michael W ^c   Edelson, Dana P ^a  

^a UNIVERSITY OF CHICAGO   (United States)

^b NORTHSHORE UNIVERSITY HEALTHSYSTEM   (United States)

^c LERNER RESEARCH INSTITUTE   (United States)

Author keywords

Algorithms; Artificial Intelligence; Heart Arrest; Intensive Care Units; Machine learning; Models Statistical

Indexed keywords

CREATININE;

ACCURACY; ANALYTIC METHOD; ARTIFICIAL NEURAL NETWORK; BREATHING RATE; COHORT ANALYSIS; CONFERENCE PAPER; CONTROLLED STUDY; CONVENTIONAL REGRESSION; CREATININE BLOOD LEVEL; ELECTRONIC MEDICAL RECORD; FACE VALIDITY; HEART ARREST; HEART RATE; HOSPITAL ADMISSION; HUMAN; INTENSIVE CARE UNIT; K NEAREST NEIGHBOR; LIVER FUNCTION TEST; LOGISTIC REGRESSION ANALYSIS; MACHINE LEARNING; MACHINE LEARNING METHOD; MAJOR CLINICAL STUDY; OBSERVATIONAL STUDY; PREDICTION; PRIORITY JOURNAL; RANDOM FOREST; SUPPORT VECTOR MACHINE; SYSTOLIC BLOOD PRESSURE; AGE; CLINICAL TRIAL; DIAGNOSTIC PROCEDURE; MORTALITY; MULTICENTER STUDY; ORGANIZATION AND MANAGEMENT; RECEIVER OPERATING CHARACTERISTIC; RISK ASSESSMENT; SOCIOECONOMICS; STATISTICAL MODEL; SURVIVAL ANALYSIS; TIME FACTOR; UTILIZATION; VITAL SIGN;

AGE FACTORS; COHORT STUDIES; DIAGNOSTIC TECHNIQUES AND PROCEDURES; HEART ARREST; HUMANS; INTENSIVE CARE UNITS; LOGISTIC MODELS; MACHINE LEARNING; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); RISK ASSESSMENT; ROC CURVE; SOCIOECONOMIC FACTORS; SUPPORT VECTOR MACHINE; SURVIVAL ANALYSIS; TIME FACTORS; VITAL SIGNS;

EID: 84954349720     PISSN: 00903493     EISSN: 15300293     Source Type: Journal    
DOI: 10.1097/CCM.0000000000001571     Document Type: Conference Paper

References (35)

1. IBM: What is big data? Bringing Big Data to the Enterprise. Available at: http://www-01.ibm.com/software/data/bigdata/what-is-big-data.html. Accessed on January 7, 2015
2. Iwashyna TJ, Liu V, What's so different about big data? A primer for clinicians trained to think epidemiologically. Ann Am Thorac Soc 2014 11 1130 1135
3. Bell RM, Koren Y., Lessons from the Netflix prize challenge. ACM SIGKDD Explorations Newsletter 2007 9 75 79
4. Knaus WA, Wagner DP, Draper EA, The APACHE III prognostic system. Risk prediction of hospital mortality for critically ill hospitalized adults. Chest 1991 100 1619 1636
5. Le Gall JR, Lemeshow S, Saulnier F, A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. JAMA 1993 270 2957 2963
6. Fernandez-Delgado M, Cernadas E, Barro S, Do we Need Hundreds of Classifiers to Solve Real World Classification Problems? J Mach Learn Res 2014 15 3133 3181
7. Pinsky MR, Dubrawski A, Gleaning knowledge from data in the intensive care unit. Am J Respir Crit Care Med 2014 190 606 610
8. Churpek MM, Yuen TC, Winslow C, Multicenter development and validation of a risk stratification tool for ward patients. Am J Respir Crit Care Med 2014 190 649 655
9. He H, Garcia EA, Learning from imbalanced data. IEEE Trans Knowl Data Eng 2009 21 1263 1284
10. Kuhn M, Johnson K., Applied predictive modeling 2013 New York, NY Springer. Available at: http://dx.doi.org/10.1007/978-1-4614-6849-3. Accessed December 9, 2015
11. Singer JD, Willett JB, Its About Time-Using Discrete-Time Survival Analysis to Study Duration and the Timing of Events. J Educ Stat 1993 18 155 195
12. Hastie T, Tibshirani R, Friedman J, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics) 2009 II Ed New York, NY Springer
13. Subbe CP, Kruger M, Rutherford P, Validation of a modified Early Warning Score in medical admissions. QJM 2001 94 521 526
14. Smith GB, Prytherch DR, Meredith P, The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death. Resuscitation 2013 84 465 470
15. Steyerberg EW, Clinical prediction models a practical approach to development, validation, and updating. Stat Biol Health 2009 New York Springer. Available at: http://dx.doi.org/10.1007/978-0-387-77244-8. Accessed December 9, 2015
16. Friedman JH, Greedy function approximation: A gradient boosting machine. Annals of Statistics 2001 29 1189 1232
17. van der Ploeg T, Austin PC, Steyerberg EW, Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints. BMC Med Res Methodol 2014 14 137
18. Pirracchio R, Petersen ML, Carone M, Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study. Lancet Respir Med 2015 3 42 52
19. Mao Y, Chen Y, Hackmann G, Medical Data Mining for Early Deterioration Warning in General Hospital Wards. Paper presented at: Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference
20. Badriyah T, Briggs JS, Meredith P, Decision-tree early warning score (DTEWS) validates the design of the National Early Warning Score (NEWS). Resuscitation 2014 85 418 423
21. Kattan MW, Comparison of Cox regression with other methods for determining prediction models and nomograms. J Urol 2003 170 S6 9; discussion S10
22. Austin PC, Lee DS, Steyerberg EW, Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods? Biom J 2012 54 657 673
23. van der Ploeg T, Smits M, Dippel DW, Prediction of intracranial findings on CT-scans by alternative modelling techniques. BMC Med Res Methodol 2011 11 143
24. Wolpert D, The supervised learning no-free-lunch theorems. 2001 Proceedings of the 6th Online World Conference of Soft Computing in Industrial Applications 10 24
25. Van Belle VM, Van Calster B, Timmerman D, A mathematical model for interpretable clinical decision support with applications in gynecology. PLoS One 2012 7 e34312
26. Churpek MM, Yuen TC, Huber MT, Predicting cardiac arrest on the wards: a nested case-control study. Chest 2012 141 1170 1176
27. Escobar GJ, LaGuardia JC, Turk BJ, Early detection of impending physiologic deterioration among patients who are not in intensive care: development of predictive models using data from an automated electronic medical record. J Hosp Med 2012 7 388 395
28. Sawyer AM, Deal EN, Labelle AJ, Implementation of a real-time computerized sepsis alert in nonintensive care unit patients. Crit Care Med 2011 39 469 473
29. Bailey TC, Chen Y, Mao Y, A trial of a real-time alert for clinical deterioration in patients hospitalized on general medical wards. J Hosp Med 2013 8 236 242
30. Herasevich V, Tsapenko M, Kojicic M, Limiting ventilator-induced lung injury through individual electronic medical record surveillance. Crit Care Med 2011 39 34 39
31. Hravnak M, Devita MA, Clontz A, Cardiorespiratory instability before and after implementing an integrated monitoring system. Crit Care Med 2011 39 65 72
32. Hravnak M, Chen L, Dubrawski A, Temporal distribution of instability events in continuously monitored step-down unit patients: implications for Rapid Response Systems. Resuscitation 2015 89 99 105
33. Biganzoli E, Boracchi P, Mariani L, Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med 1998 17 1169 1186
34. Bou-Hamad I, Larocque D, Ben-Ameur H, Discrete-time survival trees and forests with time-varying covariates: application to bankruptcy data. Stat Model 2011 11 429 446
35. Zupan B, Demsar J, Kattan MW, Machine learning for survival analysis: a case study on recurrence of prostate cancer. Artif Intell Med 2000 20 59 75