Prognostication and Risk Factors for Cystic Fibrosis via Automated Machine Learning

Scientific Reports

Volumn 8, Issue 1, 2018, Pages

  Alaa, Ahmed M ^a   van der Schaar, Mihaela ^a,b,c  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b ALAN TURING INSTITUTE   (United Kingdom)

^c UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

BIOLOGICAL MARKER;

AUTOMATION; COMPLICATION; CYSTIC FIBROSIS; HUMAN; LUNG FUNCTION TEST; MACHINE LEARNING; MORTALITY; PATHOLOGY; PROGNOSIS; RESPIRATORY FAILURE; RISK FACTOR; SURVIVAL ANALYSIS; UNITED KINGDOM;

AUTOMATION; BIOMARKERS; CYSTIC FIBROSIS; HUMANS; MACHINE LEARNING; PROGNOSIS; RESPIRATORY FUNCTION TESTS; RESPIRATORY INSUFFICIENCY; RISK FACTORS; SURVIVAL ANALYSIS; UNITED KINGDOM;

EID: 85050676780     PISSN: None     EISSN: 20452322     Source Type: Journal    
DOI: 10.1038/s41598-018-29523-2     Document Type: Article

References (65)

1. Adler, A. I., Shine, B. S., Chamnan, P., Haworth, C. S. & Bilton, D. Genetic determinants and epidemiology of cystic fibrosis–related diabetes. Diabetes care 31, 1789–1794 (2008).
2. Fanen, P., Wohlhuter-Haddad, A. & Hinzpeter, A. Genetics of cystic fibrosis: Cftr mutation classifications toward genotype-based cf therapies. The international journal of biochemistry & cell biology 52, 94–102 (2014).
3. Mogayzel, P. J. Jr. et al. Cystic fibrosis foundation pulmonary guideline*. Pharmacologic approaches to prevention and eradication of initial pseudomonas aeruginosa infection. Annals of the American Thoracic Society 11, 1640–1650 (2014).
4. Szczesniak, R. D. et al. Phenotypes of rapid cystic fibrosis lung disease progression during adolescence and young adulthood. American Journal of Respiratory And Critical Care Medicine (2017).
5. Rowe, S. M. et al. Progress in cystic fibrosis and the cf therapeutics development network. Thorax 67, 882–890 (2012).
6. MacKenzie, T. et al. Longevity of patients with cystic fibrosis in 2000 to 2010 and beyond: Survival analysis of the cystic fibrosis foundation patient registrylifetime of patients with cystic fibrosis in 2000 to 2010 and beyond. Annals of internal medicine 161, 233–241 (2014).
7. Flume, P. A. Cystic fibrosis: when to consider lung transplantation? Chest 113, 1159–1162 (1998).
8. Liou, T. G. et al. Survival effect of lung transplantation among patients with cystic fibrosis. Jama 286, 2683–2689 (2001).
9. Hofer, M. et al. True survival benefit of lung transplantation for cystic fibrosis patients: the zurich experience. The Journal of Heart and Lung Transplantation 28, 334–339 (2009).
10. Mayer-Hamblett, N., Rosenfeld, M., Emerson, J., Goss, C. H. & Aitken, M. L. Developing cystic fibrosis lung transplant referral criteria using predictors of 2-year mortality. American journal of respiratory and critical care medicine 166, 1550–1555 (2002).
11. Liou, T. G., Adler, F. R. & Huang, D. Use of lung transplantation survival models to refine patient selection in cystic fibrosis. American journal of respiratory and critical care medicine 171, 1053–1059 (2005).
12. Weill, D. et al. A consensus document for the selection of lung transplant candidates: 2014—an update from the pulmonary transplantation council of the international society for heart and lung transplantation (2015).
13. Hook, J. L. & Lederer, D. J. Selecting lung transplant candidates: where do current guidelines fall short? Expert review of respiratory medicine 6, 51–61 (2012).
14. Hirche, T. O. et al. Practical guidelines: lung transplantation in patients with cystic fibrosis. Pulmonary medicine 2014 (2014).
15. Kerem, E., Reisman, J., Corey, M., Canny, G. J. & Levison, H. Prediction of mortality in patients with cystic fibrosis. New England Journal of Medicine 326, 1187–1191 (1992).
16. Milla, C. E. & Warwick, W. J. Risk of death in cystic fibrosis patients with severely compromised lung function. Chest 113, 1230–1234 (1998).
17. Wojewodka, G. et al. Candidate markers associated with the probability of future pulmonary exacerbations in cystic fibrosis patients. PloS one 9, e88567 (2014).
18. Ramos, K. et al. Heterogeneity in survival among adult cystic fibrosis patients with fev1 < 30% of predicted in the united states. CHEST (2017).
19. Urquhart, D. S. et al. Deaths in childhood from cystic fibrosis: 10-year analysis from two london specialist centres. Archives of disease in childhood 98, 123–127 (2013).
20. Stephenson, A. L., Stanojevic, S., Sykes, J. & Burgel, P.-R. The changing epidemiology and demography of cystic fibrosis. La Presse Médicale (2017).
21. Hayllar, K. M. et al. A prognostic model for the prediction of survival in cystic fibrosis. Thorax 52, 313–317 (1997).
22. Liou, T. G. et al. Predictive 5-year survivorship model of cystic fibrosis. American journal of epidemiology 153, 345–352 (2001).
23. Buzzetti, R. et al. Validation of a predictive survival model in italian patients with cystic fibrosis. Journal of Cystic Fibrosis 11, 24–29 (2012).
24. Aaron, S. D., Stephenson, A. L., Cameron, D. W. & Whitmore, G. A. A statistical model to predict one-year risk of death in patients with cystic fibrosis. Journal of clinical epidemiology 68, 1336–1345 (2015).
25. Cystic fibrosis trust, https://www.cysticfibrosis.org.uk/the-work-we-do/uk-cf-registry (accessed Oct 1, 2017).
26. Cystic fibrosis trust, https://www.cysticfibrosis.org.uk/the-work-we-do/uk-cf-registry/reporting-and-resources (accessed Oct 2, 2017).
27. Fink, A. K., Loeffler, D. R., Marshall, B. C., Goss, C. H. & Morgan, W. J. Data that empower: The success and promise of cf patient registries. Pediatric Pulmonology (2017).
28. Yoo, I. et al. Data mining in healthcare and biomedicine: a survey of the literature. Journal of medical systems 36, 2431–2448 (2012).
29. Luo, G. et al. Automating construction of machine learning models with clinical big data: proposal rationale and methods. JMIR Research Protocols 6 (2017).
30. Feurer, M. et al. Efficient and robust automated machine learning. In Advances in Neural Information Processing Systems, 2962–2970 (2015).
31. Ghahramani, Z. Probabilistic machine learning and artificial intelligence. Nature 521, 452 (2015).
32. Snoek, J., Larochelle, H. & Adams, R. P. Practical bayesian optimization of machine learning algorithms. In Advances in neural information processing systems, 2951–2959 (2012).
33. Thabtah, F. A review of associative classification mining. The Knowledge Engineering Review 22, 37–65 (2007).
34. Luo, G. Automatically explaining machine learning prediction results: a demonstration on type 2 diabetes risk prediction. Health information science and systems 4, 2 (2016).
35. Alaa, A. M. & van der Schaar, M. Autoprognosis: Automated clinical prognostic modeling via bayesian optimization with structured kernel learning. arXiv preprint arXiv:1802.07207 (2018).
36. Nkam, L. et al. A 3-year prognostic score for adults with cystic fibrosis. Journal of Cystic Fibrosis (2017).
37. Ratjen, F. et al. Cystic fibrosis. Nature Reviews Disease Primers (2015).
38. Stekhoven, D. J. & Bühlmann, P. Missforest—non-parametric missing value imputation for mixed-type data. Bioinformatics 28, 112–118 (2011).
39. McCarthy, C., Dimitrov, B. D., Meurling, I. J., Gunaratnam, C. & McElvaney, N. G. The cf-able score: a novel clinical prediction rule for prognosis in patients with cystic fibrosis. CHEST Journal 143, 1358–1364 (2013).
40. Dimitrov, B. D. & Jaidi, M. H. H. Cf-able-uk score: Modification and validation of a clinical prediction rule for prognosis in cystic fibrosis on data from uk cf registry (2015).
41. Orens, J. B. et al. International guidelines for the selection of lung transplant candidates: 2006 update—a consensus report from the pulmonary scientific council of the international society for heart and lung transplantation. The Journal of heart and lung transplantation 25, 745–755 (2006).
42. Braun, A. T., Dasenbrook, E. C., Shah, A. S., Orens, J. B. & Merlo, C. A. Impact of lung allocation score on survival in cystic fibrosis lung transplant recipients. The Journal of Heart and Lung Transplantation 34, 1436–1441 (2015).
43. Swets, J. A. et al. Measuring the accuracy of diagnostic systems. Science 240, 1285–1293 (1988).
44. Saito, T. & Rehmsmeier, M. The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PloS one 10, e0118432 (2015).
45. Fluss, R., Faraggi, D. & Reiser, B. Estimation of the youden index and its associated cutoff point. Biometrical journal 47, 458–472 (2005).
46. Altman, D. G. & Bland, J. M. Diagnostic tests. 1: Sensitivity and specificity. BMJ: British Medical Journal 308, 1552 (1994).
47. Davis, J. & Goadrich, M. The relationship between precision-recall and roc curves. In Proceedings of the 23rd international conference on Machine learning, 233–240 (ACM, 2006).
48. Zhu, M. Recall, precision and average precision. Department of Statistics and Actuarial Science, University of Waterloo, Waterloo 2, 30 (2004).
49. Flach, P. & Kull, M. Precision-recall-gain curves: Pr analysis done right. In Advances in Neural Information Processing Systems, 838–846 (2015).
50. Olson, R. S. et al. Applications of Evolutionary Computation: 19th European Conference, EvoApplications 2016, Porto, Portugal, March 30 – April 1, 2016, Proceedings, Part I, chap. Automating Biomedical Data Science Through Tree-Based Pipeline Optimization, 123–137, https://doi.org/10.1007/978-3-319-31204-0_9 (Springer International Publishing, 2016).
51. Orlenko, A. et al. Considerations of automated machine learning in clinical metabolic profiling: Altered homocysteine plasma concentration associated with metformin exposure. arXiv preprint arXiv:1710.03268 (2017).
52. Rowe, S. M. et al. Clinical mechanism of the cystic fibrosis transmembrane conductance regulator potentiator ivacaftor in g551d-mediated cystic fibrosis. American journal of respiratory and critical care medicine 190, 175–184 (2014).
53. Wainwright, C. E. et al. Lumacaftor–ivacaftor in patients with cystic fibrosis homozygous for phe508del cftr. New England Journal of Medicine 373, 220–231 (2015).
54. Chamnan, P., Shine, B. S., Haworth, C. S., Bilton, D. & Adler, A. I. Diabetes as a determinant of mortality in cystic fibrosis. Diabetes Care 33, 311–316 (2010).
55. Young, I. H. & Bye, P. T. Gas exchange in disease: asthma, chronic obstructive pulmonary disease, cystic fibrosis, and interstitial lung disease. Comprehensive Physiology (2011).
56. Ewence, A., Malone, S., Nutbourne, A., Higton, A. & Orchard, C. 302 a retrospective review of renal function and intravenous (iv) antibiotic use in an adult uk cystic fibrosis centre. Journal of Cystic Fibrosis 16, S139 (2017).
57. Sheikh, H. S., Tiangco, N. D., Harrell, C. & Vender, R. L. Severe hypercapnia in critically ill adult cystic fibrosis patients. Journal of clinical medicine research 3, 209 (2011).
58. KJ, R. et al. Heterogeneity in survival amongadult cystic fibrosis patients with fev1 < 30% of predicted in the united states. CHEST 151, 1320–1328 (2017).
59. Agrawal, R., Imieliński, T. & Swami, A. Mining association rules between sets of items in large databases. In Acm sigmod record, vol. 22, 207–216 (ACM, 1993).
60. Hall, M. Correlation-based feature selection for machine learning (University of Waikato Hamilton, 1999).
61. Vehtari, A. et al. GPyOpt: A bayesian optimization framework in python. http://github.com/SheffieldML/GPyOpt (2016).
62. GPy. GPy: A gaussian process framework in python. http://github.com/SheffieldML/GPy (since 2012).
63. Pedregosa, F. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, 2825–2830 (2011).
64. Ma, B. L. W. H. Y. & Liu, B. Integrating classification and association rule mining. In Proceedings of the fourth international conference on knowledge discovery and data mining (1998).
65. Fayyad, U. & Irani, K. Multi-interval discretization of continuous-valued attributes for classification learning. JPL TRS (1993).