Figures & data
Table 1. Summary of Categorical Variables.
Table 2. Summary Statistics of Study Data.
Figure 1. A plot of feature importance from A) The RF variable importance model B) The SVR variable importance.
Figure 2. Sequential backward elimination on ranked variables based on RF variable importance method.
Figure 3. Sequential backward elimination on ranked variables based on SVR variable importance method.
Table 3. Summary of the result for each of the machine learning models.
Figure 4. Boxplot of the healing weeks’ value distribution for the RF model with (A) all the variables and (B) the selected variables.
Figure 5. Boxplot of the healing week’s value distribution for the RF model with (A) all the variables and (B) the selected variables.
Figure 6. SOM U-matrix and component planes of selected variables with healing weeks.
Data availability statement
Data available in a public repository that does not issue DOIs. The data that support the findings of this study are available from the Department of Orthopaedic Surgery, University of Malaya Medical Centre (UMMC) but restrictions apply to the availability of these data, and so are not publicly available. The data belongs to the individual ministry of health universities hospitals and private hospitals that require multiple institutional agreements for data release to third parties hence ethical approval is needed for analysis. Data are however available from UMMC upon request using http://www.ummc.edu.my/department/department.asp?kodjabatan=38 or email them at [email protected]. Any findings from the data need to be reported and permission needs to be obtained from the Department of Orthopaedic Surgery, University of Malaya Medical Centre (UMMC) committee before publication.