Predicting colorectal surgical complications using heterogeneous clinical data and kernel methods

Journal of Biomedical Informatics

Volumn 61, Issue , 2016, Pages 87-96

  Soguero Ruiz, Cristina ^a   Hindberg, Kristian ^b   Mora Jiménez, Inmaculada ^a   Rojo Álvarez, José Luis ^a   Skrøvseth, Stein Olav ^c,d,f   Godtliebsen, Fred ^b   Mortensen, Kim ^b,g   Revhaug, Arthur ^g,h   Lindsetmo, Rolv Ole ^b,g   Augestad, Knut Magne ^b,c,e,i   Jenssen, Robert ^b,c  

^a UNIVERSIDAD REY JUAN CARLOS   (Spain)

^b UNIVERSITY OF TROMSØ   (Norway)

^c Norwegian Centre for Integrated Care and Telemedicine   (Norway)

^d UNIVERSITY HOSPITAL OF NORTH NORWAY   (Norway)

^e Hammerfest Hospital   (Norway)

^f IBM T J WATSON RESEARCH CENTER   (United States)

^g UNN   (Norway)

^h Clinic for Surgery   (Norway)

ⁱ UNIVERSITY HOSPITALS OF CLEVELAND   (United States)

Author keywords

Clinical decision support; Colorectal cancer; Electronic health records; Feature selection; Heterogeneous clinical data; Kernel methods

Indexed keywords

ARTIFICIAL INTELLIGENCE; BLOOD; DECISION SUPPORT SYSTEMS; DISEASES; FEATURE EXTRACTION; FORECASTING; LEARNING SYSTEMS; RECORDS MANAGEMENT; RISK ASSESSMENT; SURGERY;

CLINICAL DATA; CLINICAL DECISION SUPPORT; COLORECTAL CANCER; ELECTRONIC HEALTH RECORD; KERNEL METHODS;

POPULATION STATISTICS;

ANASTOMOSIS LEAKAGE; ARTICLE; BLOOD EXAMINATION; BLOOD SAMPLING; CONTROLLED STUDY; ELECTRONIC MEDICAL RECORD; HUMAN; KERNEL METHOD; MACHINE LEARNING; PATIENT CODING; POSTOPERATIVE COMPLICATION; PREDICTION; PRIORITY JOURNAL; PROBABILITY; RISK ASSESSMENT; STATISTICAL MODEL; VITAL SIGN; ABDOMINAL SURGERY; COLON; ELECTRONIC HEALTH RECORD; RECTUM; SUPPORT VECTOR MACHINE; SURGERY;

ANASTOMOTIC LEAK; COLON; DIGESTIVE SYSTEM SURGICAL PROCEDURES; ELECTRONIC HEALTH RECORDS; HUMANS; MODELS, STATISTICAL; POSTOPERATIVE COMPLICATIONS; RECTUM; RISK ASSESSMENT; SUPPORT VECTOR MACHINE;

EID: 84962333241     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2016.03.008     Document Type: Article

References (45)

1. Larsen I. Cancer in Norway 2011 - cancer incidence, mortality, survival and prevalence in Norway 2013, Cancer Registry of Norway, Oslo.
2. Snijders H., Henneman D., van Leersum N., Berge M.T., Fiocco M., Karsten T., Havenga K., Wiggers T., Dekker J., Tollenaar R., Wouters M. Anastomotic leakage as an outcome measure for quality of colorectal cancer surgery. BMJ Qual. Saf. 2013, 22(9):759-767.
3. Hirst N., Tiernan J., Millner P., Jayne D. Systematic review of methods to predict and detect anastomotic leakage in colorectal surgery. Colorectal Dis. 2014, 16(2):95-109.
4. Kehlet H. Fast-track colorectal surgery. Lancet 2008, 371(9615):791-793.
5. Karliczek A., Harlaar N., Zeebregts C., Wiggers T., Baas P., van Dam G. Surgeons lack predictive accuracy for anastomotic leakage in gastrointestinal surgery. Int. J. Colorectal Dis. 2009, 24(5):569-576.
6. Jensen P.B., Jensen L.J., Brunak S. Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 2015, 13(6):395-405.
7. Gönen M., Alpaydin E. Multiple kernel learning algorithms. J. Mach. Learn. Res. 2011, 12:2211-2268.
8. Sonnenburg S., Rätsch G., Schäfer C., Schölkopf B. Large scale multiple kernel learning. J. Mach. Learn. Res. 2006, 7:1531-1565.
9. Lanckriet G.R., Cristianini N., Bartlett P., Ghaoui L.E., Jordan M.I. Learning the kernel matrix with semidefinite programming. J. Mach. Learn. Res. 2004, 5:27-72.
10. Bach F.R., Lanckriet G.R., Jordan M.I. Multiple kernel learning, conic duality, and the smo algorithm. Proceedings of the Twenty-first International Conference on Machine Learning 2004, 6. ACM.
11. Camps-Valls G., Gomez-Chova L., Muñoz-Marí J., Vila-Francés J., Calpe-Maravilla J. Composite kernels for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 2006, 3(1):93-97.
12. T. Joachims, N. Cristianini, J. Shawe-Taylor, Composite kernels for hypertext categorisation, in: ICML, vol. 1, 2001, pp. 250-257.
13. Martínez-Ramón M., Rojo-Álvarez J.L., Camps-Valls G., Muñoz-Marí J., Navia-Vázquez Á., Soria-Olivas E., Figueiras-Vidal A.R. Support vector machines for nonlinear kernel arma system identification. IEEE Trans. Neural Netw. 2006, 17(6):1617-1622.
14. Lanckriet G.R., De Bie T., Cristianini N., Jordan M.I., Noble W.S. A statistical framework for genomic data fusion. Bioinformatics 2004, 20(16):2626-2635.
15. Ye J., Chen K., Wu T., Li J., Zhao Z., Patel R., et al. Heterogeneous data fusion for alzheimer's disease study. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2008, 1025-1033. ACM.
16. Nguyen H.-N., Ohn S.-Y., Park J., Park K.-S. Combined kernel function approach in svm for diagnosis of cancer. Advances in Natural Computation 2005, 1017-1026. Springer.
17. Zhang Z., Xu Y., Liu J., Wong D.W.K., Kwoh C.K., et al. Automatic diagnosis of pathological myopia from heterogeneous biomedical data. PLOS ONE 2013, 8(6):e65736.
18. Castro E., Martínez-Ramón M., Pearlson G., Sui J., Calhoun V.D. Characterization of groups using composite kernels and multi-source fmri analysis data: application to schizophrenia. Neuroimage 2011, 58(2):526-536.
19. Schölkopf B., Smola A., Williamson R., Bartlett P. New support vector algorithms. Neural Comput. 2000, 12(5):1207-1245.
20. C. Soguero-Ruiz, K. Hindberg, J.L. Rojo-Alvarez, S.O. Skrøvseth, F. Godtliebsen, K. Mortensen, A. Revhaug, R.-O. Lindsetmo, I. Mora-Jimenez, K.M. Augestad, et al., Bootstrap resampling feature selection and support vector machine for early detection of anastomosis leakage, in: IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2014, pp. 577-580.
21. Soguero-Ruiz C., Hindberg K., Rojo-Alvarez J.L., Skrvseth S.O., Godtliebsen F., Mortensen K., Revhaug A., Lindsetmo R., Augestad K.M., Jenssen R. Support vector feature selection for early detection of anastomosis leakage from bag-of-words in electronic health records. IEEE J. Biomed. Health Inform. 2014, PP(99).
22. Skrøvseth S.O., Augestad K.M., Ebadollahi S. Data-driven approach for assessing utility of medical tests using electronic medical records. J. Biomed. Inform. 2015, 53:270-276.
23. Vapnik V. Statistical Learning Theory 1998, John Wiley and Sons, Inc., New York.
24. Schlkopf B., Smola A.J. Learning with Kernels 2002, MIT Press, Cambridge, MA.
25. Platt J., et al. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 1999, 10(3):61-74.
26. Camps-Valls G., Bruzzone L. Kernel Methods for Remote Sensing Data Analysis 2009, vol. 26. Wiley Online Library.
27. Szafranski M., Grandvalet Y., Rakotomamonjy A. Composite kernel learning. Mach. Learn. 2010, 79(1-2):73-103.
28. Qiu S., Lane T. A framework for multiple kernel support vector regression and its applications to sirna efficacy prediction. IEEE/ACM Trans. Comput. Biol. Bioinform. 2009, 6(2):190-199.
29. Rakotomamonjy A., Bach F., Canu S., Grandvalet Y. Simplemkl. J. Mach. Learn. Res. 2008, 9:2491-2521.
30. Guyon I., Weston J., Barnhill S., Vapnik V. Gene selection for cancer classification using support vector machines. Mach. Learn. 2002, 46(1):389-422.
31. Kohavi R., John G. Wrappers for feature subset selection. Artif. Intell. 1997, 97:273-324.
32. Feature Extraction: Foundations and Applications 2006, Springer, Heidelberg. I. Guyon, S. Gunn, M. Nikravesh, L.A. Zadeh (Eds.).
33. Rakotomamonjy A. Variable selection using svm based criteria. J. Mach. Learn. Res. 2003, 3:1357-1370.
34. Scholkopf B., Smola A.J. Learning with kernels. MIT Press 2002, 11:110-146.
35. Salton G., Buckley C. Term-weighting approaches in automatic text retrieval. Inform. Process. Manag. 1988, 24(5):513-523.
36. Troyanskaya O., Cantor M., Sherlock G., Brown P., Hastie T., Tibshirani R., Botstein D., Altman R.B. Missing value estimation methods for dna microarrays. Bioinformatics 2001, 17(6):520-525.
37. He H., Garcia E.A. Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 2009, 21(9):1263-1284.
38. Tang Y., Zhang Y.-Q., Chawla N.V., Krasser S. Svms modeling for highly imbalanced classification. IEEE Trans. Syst. Man Cybern. Syst. 2009, 39(1):281-288.
39. Hanley J.A., McNeil B.J. The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology 1982, 143(1):29-36.
40. Gehan E.A. A generalized wilcoxon test for comparing arbitrarily singly-censored samples. Biometrika 1965, 52(1-2):203-223.
41. Bahadori M.T., Liu Y. Granger causality analysis in irregular time series. SDM 2012, 660-671. SIAM.
42. Erb L., Hyman N.H., Osler T. Abnormal vital signs are common after bowel resection and do not predict anastomotic leak. J. Am. Coll. Surg. 2014, 218(6):1195-1199.
43. Wu Z., Freek D., Lange J. Do normal clinical signs and laboratory tests exclude anastomotic leakage?. J. Am. Coll. Surg. 2014, 219(1):164.
44. den Dulk M., Noter S.L., Hendriks E.R., Brouwers M.A., van der Vlies C.H., et al. Improved diagnosis and treatment of anastomotic leakage after colorectal surgery. Eur. J. Surg. Oncol. 2009, 35(4):420-426.
45. Campbell W., Ganna A., Ingelsson E., Janssens A.C.J. Prediction impact curve is a new measure integrating intervention effects in the evaluation of risk models. J. Clin. Epidemiol. 2016, 69:89-95.