Abstract
This case study benchmarks a range of statistical and machine learning methods relevant to computer-based decision support in clinical medicine, focusing on the diagnosis of knee osteoarthritis at first presentation. The methods, comprising logistic regression, Multilayer Perceptron (MLP), Chi-square Automatic Interaction Detector (CHAID) and Classification and Regression Trees (CART), are applied to a public domain database, the Osteoarthritis Initiative (OAI), a 10 year longitudinal study starting in 2002 (nā=ā4,796). In this real-world application, it is shown that logistic regression is comparable with the neural networks and decision trees for discrimination of positive diagnosis on this data set. This is likely because of weak non-linearities among high levels of noise. After comparing the explanations provided by the different methods, it is concluded that the interpretability of the risk score index provided by logistic regression is expressed in a form that most naturally integrates with clinical reasoning. The reason for this is that it gives a statistical assessment of the weight of evidence for making the diagnosis, so providing a direction for future research to improve explanation of generic non-linear models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vellido, A.: Neural Comput. Appl. (2019). https://doi.org/10.1007/s00521-019-04051-w
Song, Y., Lu, Y.: Decision tree methods: applications for classification and prediction. Shanghai Arch. Psychiatry. 27, 130ā135 (2015). https://doi.org/10.11919/j.issn.1002-0829.215044
Peat, G., Mccarney, R., Croft, P.: Knee pain and osteoarthritis in older adults: a review of community burden and current use of primary health care. Ann. Rheum. Dis. 60, 91ā97 (2001). https://doi.org/10.1136/ard.60.2.91
Kohn, M.D., Sassoon, A.A., Fernando, N.D.: Classifications in brief: kellgren-lawrence classification of osteoarthritis. Clin. Orthop. Relat. Res. 474, 1886ā1893 (2016). https://doi.org/10.1007/s11999-016-4732-4
Jones, L., Golan, D., Hanna, S., Ramachandran, M.: Artificial intelligence, machine learning and the evolution of healthcare. Bone Joint Res. 7, 223ā225 (2017). https://doi.org/10.1302/2046-3758.73.BJR
Woolf, A.D., Pfleger, B.: Burden of major musculoskeletal conditions. Bull. World Health Organ. 81, 646ā656 (2003). https://doi.org/10.1590/S0042-96862003000900007
NIA: Osteoarthritis Initiative (OAI). https://www.nia.nih.gov/research/resource/osteoarthritis-initiative-oai
NIH: OAI - About OAI. https://data-archive.nimh.nih.gov/oai/about-oai
Hampton, T.: Osteoarthritis initiative. JAMA 291, 1951 (2004). https://doi.org/10.1001/jama.291.16.1951-a
Shipe, M.E., Deppen, S.A., Farjah, F., Grogan, E.L.: Developing prediction models for clinical use using logistic regression: an overview. J. Thorac. Dis. 11, 574ā584 (2019). https://doi.org/10.21037/jtd.2019.01.25
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1 (1986)
Marzban, C.: The ROC Curve and the Area under It as Performance Measures (2004)
Ing, E.B., Ing, R.: The use of a nomogram to visually interpret a logistic regression prediction model for giant cell arteritis. Neuro-Ophthalmol. 42, 284ā286 (2018). https://doi.org/10.1080/01658107.2018.1425728
Acknowledgement
This work was funded under EU Grant OActive from the European Communityās H2020 Programme. The OActive project looks to use advanced multi-scale computer models to better understand the risk factors associated with OA in order to prevent and delay the onset and progression of OA. Grant number 777159.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
McCabe, P.G., Olier, I., Ortega-Martorell, S., Jarman, I., Baltzopoulos, V., Lisboa, P. (2019). Comparative Analysis for Computer-Based Decision Support: Case Study of Knee Osteoarthritis. In: Yin, H., Camacho, D., Tino, P., TallĆ³n-Ballesteros, A., Menezes, R., Allmendinger, R. (eds) Intelligent Data Engineering and Automated Learning ā IDEAL 2019. IDEAL 2019. Lecture Notes in Computer Science(), vol 11872. Springer, Cham. https://doi.org/10.1007/978-3-030-33617-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-33617-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33616-5
Online ISBN: 978-3-030-33617-2
eBook Packages: Computer ScienceComputer Science (R0)