Comparative Analysis for Computer-Based Decision Support: Case Study of Knee Osteoarthritis
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 (n = 4,796). 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.
KeywordsComparative analysis Neural networks Logistic regression Decision trees Osteoarthritis Healthcare
This work was funded under EU Grant OActive from the European Community’s 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.
- 1.Vellido, A.: Neural Comput. Appl. (2019). https://doi.org/10.1007/s00521-019-04051-w
- 7.NIA: Osteoarthritis Initiative (OAI). https://www.nia.nih.gov/research/resource/osteoarthritis-initiative-oai
- 8.NIH: OAI - About OAI. https://data-archive.nimh.nih.gov/oai/about-oai
- 11.Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1 (1986)Google Scholar