Predicting knee osteoarthritis severity: comparative modeling based on patient's data and plain X-ray images

Abstract

Knee osteoarthritis (KOA) is a disease that impairs knee function and causes pain. A radiologist reviews knee X-ray images and grades the severity level of the impairments according to the Kellgren and Lawrence grading scheme; a five-point ordinal scale (0-4). In this study, we used Elastic Net (EN) and Random Forests (RF) to build predictive models using patient assessment data (i.e. signs and symptoms of both knees and medication use) and a convolution neural network (CNN) trained using X-ray images only. Linear mixed effect models (LMM) were used to model the within subject correlation between the two knees. The root mean squared error for the CNN, EN, and RF models was 0.77, 0.97 and 0.94 respectively. The LMM shows similar overall prediction accuracy as the EN regression but correctly accounted for the hierarchical structure of the data resulting in more reliable inference. Useful explanatory variables were identified that could be used for patient monitoring before X-ray imaging. Our analyses suggest that the models trained for predicting the KOA severity levels achieve comparable results when modeling X-ray images and patient data. The subjectivity in the KL grade is still a primary concern.

Figure 1

Boxplots of patient characteristics by Knee Osteoarthritis Severity.

Figure 2

Correlation among predictors (dark color indicates stronger correlation).

Figure 3

Estimation of hyper-parameter λ. The Y-axis represents RMSE for different values of λ whereas the upper horizontal axis represents the number of predictors. The RMSE increases as the number of predictors decrease but stabilizes after a certain number of predictors are added. The red points represents RMSE and the gray line segments represents a 95% confidence interval corresponding to each RMSE. The optimal value of λ is the minimum value corresponding to a steady-state RMSE.

Figure 4

Contribution of each variable on KOA severity score prediction by Elastic Net Regression.

Figure 5

Data pre-processing work flow. (a) Inspecting entire dataset manually to get subset of relevant candidate variables, (b) calculate percentage of missing values for each variables and also inspect sparsity of the categorical variables. Drop a variable that has more than 15% missing values or very low e.g. less than 5% into one category in a binary variable, (c) creating dummy variables from multi-category variables and then split the dataset into training and test data for predictive model building.

Figure 6

Learning curves: training and validation losses, and accuracy of the fully trained CNN.