Combining macula clinical signs and patient characteristics for age-related macular degeneration diagnosis: a machine learning approach
Tóm tắt
To investigate machine learning methods, ranging from simpler interpretable techniques to complex (non-linear) “black-box” approaches, for automated diagnosis of Age-related Macular Degeneration (AMD). Data from healthy subjects and patients diagnosed with AMD or other retinal diseases were collected during routine visits via an Electronic Health Record (EHR) system. Patients’ attributes included demographics and, for each eye, presence/absence of major AMD-related clinical signs (soft drusen, retinal pigment epitelium, defects/pigment mottling, depigmentation area, subretinal haemorrhage, subretinal fluid, macula thickness, macular scar, subretinal fibrosis). Interpretable techniques known as white box methods including logistic regression and decision trees as well as less interpreitable techniques known as black box methods, such as support vector machines (SVM), random forests and AdaBoost, were used to develop models (trained and validated on unseen data) to diagnose AMD. The gold standard was confirmed diagnosis of AMD by physicians. Sensitivity, specificity and area under the receiver operating characteristic (AUC) were used to assess performance. Study population included 487 patients (912 eyes). In terms of AUC, random forests, logistic regression and adaboost showed a mean performance of (0.92), followed by SVM and decision trees (0.90). All machine learning models identified soft drusen and age as the most discriminating variables in clinicians’ decision pathways to diagnose AMD. Both black-box and white box methods performed well in identifying diagnoses of AMD and their decision pathways. Machine learning models developed through the proposed approach, relying on clinical signs identified by retinal specialists, could be embedded into EHR to provide physicians with real time (interpretable) support.
Tài liệu tham khảo
Bressler NM: Age-Related Macular Degeneration Is the Leading Cause of Blindness.J Am Med Assoc 2004, 291:1900. 10.1001/jama.291.15.1900
Rein DB, Wittenborn JS, Zhang X, Honeycutt AA, Lesesne SB, Saaddine J: Forecasting age-related macular degeneration through the year 2050: the potential impact of new treatments.Arch Ophthalmol 2009, 127:533–40. 10.1001/archophthalmol.2009.58
Lamoureux EL, Mitchell P, Rees G, Cheung G, Yeo I, Lee SY, et al.: Impact of early and late age-related macular degeneration on vision-specific functioning.Br J Ophthalmol 2011, 95:666–70. 10.1136/bjo.2010.185207
Hee MR, Baumal CR, Puliafito CA, Duker JS, Reichel E, Wilkins JR, et al.: Optical coherence tomography of age-related macular degeneration and choroidal neovascularization.Ophthalmol 1996, 103:1260–70. 10.1016/S0161-6420(96)30512-5
Kanagasingam Y, Bhuiyan A, Abràmoff MD, Smith RT, Goldschmidt L, Wong TY: Progress on retinal image analysis for age related macular degeneration.Prog Retin Eye Res 2014, 38:20–42.
Hee MR, Puliafito CA, Duker JS, Reichel E, Coker JG, Wilkins JR, et al.: Topography of diabetic macular edema with optical coherence tomography.Ophthalmol 1998, 105:360–70. 10.1016/S0161-6420(98)93601-6
Pifer EA, Sittig DF: Improving Outcomes with Clinical Decision Support: An Implementer’ s Guide. Soc: In Chicago Healthc. Inf. Manag. Syst; 2005.
Quellec G, Russell SR, Scheetz TE, Stone EM, Abràmoff MD: Computational quantification of complex fundus phenotypes in age-related macular degeneration and Stargardt disease.Invest Ophthalmol Vis Sci 2011, 52:2976–81. 10.1167/iovs.10-6232
Sivasankari S, Narasimhan K, Ramya S: Automated diagnosis of ARMD.Int J Eng Technol 2013, 5:1462–4.
Schlanitz FG, Baumann B, Spalek T, Schütze C, Ahlers C, Pircher M, et al.: Performance of automated drusen detection by polarization-sensitive optical coherence tomography.Investig Ophthalmol Vis Sci 2011, 52:4571–9. 10.1167/iovs.10-6846
Pauleikhoff D, Barondes MJ, Minassian D, Chisholm IH, Bird AC: Drusen as risk factors in age-related macular disease.Am J Ophthalmol 1990, 109:38–43. 10.1016/S0002-9394(14)75576-X
Ferris FL, Wilkinson CP, Bird A, Chakravarthy U, Chew E, Csaky K, et al.: Clinical classification of age-related macular degeneration.Ophthalmol 2013, 120:844–51. 10.1016/j.ophtha.2012.10.036
Mehryar M, Afshin R, Ameet T: Foundations of Machine Learning. Cambridge, Massachussets, London, England: The MIT Press; 2012.
Zheng Y, Hijazi MHA, Coenen F: Automated “disease/no disease” grading of age-related macular degeneration by an image mining approach.Invest Ophthalmol Vis Sci 2012, 53:8310–8. 10.1167/iovs.12-9576
Serrano-Aguilar P, Abreu R, Antón-Canalís L, Guerra-Artal C, Ramallo-Fariña Y, Gómez-Ulla F, et al.: Development and validation of a computer-aided diagnostic tool to screen for age-related macular degeneration by optical coherence tomography.Br J Ophthalmol 2012, 96:503–7. 10.1136/bjophthalmol-2011-300660
Hijazi MHA, Coenen F, Zheng Y: Data mining techniques for the screening of age-related macular degeneration.Knowl Base Syst 2012, 29:83–92.
Liu YY, Ishikawa H, Chen M, Wollstein G, Duker JS, Fujimoto JG, et al.: Computerized macular pathology diagnosis in spectral domain optical coherence tomography scans based on multiscale texture and shape features.Investig. Ophthalmol. Vis. Sci 2011, 52:8316–22. 10.1167/iovs.10-7012
Kankanahalli S, Burlina PM, Wolfson Y, Freund DE, Bressler NM: Automated classification of severity of age-related macular degeneration from fundus photographs.Invest Ophthalmol Vis Sci 2013, 54:1789–96. 10.1167/iovs.12-10928
Bonetto M, Fraccaro P, Nicolo M, Giacomini M: A web-tool to manage ophthalmologic electronic health records.IEEE-EMBS Int. Conf. Biomed. Heal. Informatics 2014. IEEE; 2014:346–349
Fraccaro P, Dentone C, Fenoglio D, Giacomini M: Multicentre clinical trials’ data management: a hybrid solution to exploit the strengths of electronic data capture and electronic health records systems.Inform Health Soc Care 2013, 38:313–29. 10.3109/17538157.2013.812648
Murdoch IE, Morris SS, Cousens SN: People and eyes: statistical approaches in ophthalmology.Br J Ophthalmol 1998, 82:971–3. 10.1136/bjo.82.8.971
Bishop CM: Pattern Recognition and Machine Learning. Berlin, Heidelberg: Springer; 2006:738.
Hosmer DW Jr, Lemeshow S: Applied Logistic Regression. Hoboken, New Jersey: John Wiley & Sons; 2004:392.
Friedman J, Hastie T, Tibshirani R: Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors).Ann Stat 2000, 28:337–407.
Hornik K, Buchta C, Zeileis A: Open-source machine learning: R meets Weka.Comput Stat 2008, 24:225–32.
Cortes C, Vapnik V: Support-vector networks.Mach Learn 1995, 20:273–97.
Dimitriadou E, Hornik K, Leisch F, Meyer D, Weingessel A: SVM, e1071 Package, The R project for statistical computing. 2004.
Breiman L, Friedman JH, Olshen RA, Stone CJ: Classification and regression trees. Advanced B. Monterey: CA; 1984.
Hothorn T, Hornik K, Zeileis A: party: A Laboratory for Recursive Partytioning.http://cran.r-project.org/web/packages/party/index.html
Breiman L: Random Forests.Mach Learn 2001, 45:5–32. 10.1023/A:1010933404324
Liaw A, Wiener M: Classification and Regression by randomForest.R News 2002, 2:18–22.
Freund Y, Schapire RE: A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting.J Comput Syst Sci 1997, 55:119–39. 10.1006/jcss.1997.1504
Stekhoven DJ, Bühlmann P: MissForest–non-parametric missing value imputation for mixed-type data.Bioinformatics 2012, 28:112–8. 10.1093/bioinformatics/btr597
Fawcett T: An introduction to ROC analysis.Pattern Recognit Lett 2006, 27:861–74. 10.1016/j.patrec.2005.10.010
Breiman L: Bagging predictors.Mach Learn 1996, 24:123–40.
Nadeau C, Bengio Y: Inference for the Generalization Error.Mach Learn 2003, 52:239–81. 10.1023/A:1024068626366
The pre-publication history for this paper can be accessed here:http://www.biomedcentral.com/1471-2415/15/10/prepub