[haldujai]

Perhaps I got lost but I am discussing your original statement of “using the patients' symptoms and objective data may actually outperform current medical standards” which relates to the model predictions/inference not training.

In this context we are talking about a pain predictor from an xray which is neat but not the point of KL grading.

KL is a system to grade severity of osteoarthritis on radiographs (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4925407/) and not a threshold for surgery or predictor of symptoms.

The comparator, current medical standards you reference, would be a model outperforming surgeon assessment in conjunction with radiographic findings. Not the predictive value of KL grade.